The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective | Paper Citation Record

Observation 0bda1dda-a4fc-4d92-96f9-1624d803acf1 · outbound

This paper cites Advances and open problems in federated learning.Foundations and Trends® in Machine Learning, 14(1–2):1–210, 2021.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Advances and open problems in federated learning.Foundations and Trends® in Machine Learning, 14(1–2):1–210, 2021

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:13.233696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation db1ed7c0-b592-4618-82c0-79e03ff36843 · outbound

This paper cites Communication-efficient learning of deep networks from decentralized data.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Communication-efficient learning of deep networks from decentralized data

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.542598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 636eb726-5ecf-42fd-8e50-8e17d8e8ee88 · outbound

This paper cites Federated learning based on dynamic regularization.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Federated learning based on dynamic regularization

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.547817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aff3a6a3-b7d6-4213-a3a2-ec185ce7da5f · outbound

This paper cites Federated optimization in heterogeneous networks.Proceedings of Machine learning and systems, 2:429–450, 2020.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Federated optimization in heterogeneous networks.Proceedings of Machine learning and systems, 2:429–450, 2020

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.561249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fa9d4f4-3960-44cb-9f05-f0ae2f010d26 · outbound

This paper cites Scaffold: Stochastic controlled averaging for federated learning.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Scaffold: Stochastic controlled averaging for federated learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.566929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed306b32-f224-4181-a90a-94782d1c50de · outbound

This paper cites Personal- ized edge intelligence via federated self-knowledge distillation.IEEE Transactions on Parallel and Distributed Systems, 34(2):567–580, 2022.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Personal- ized edge intelligence via federated self-knowledge distillation.IEEE Transactions on Parallel and Distributed Systems, 34(2):567–580, 2022

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:13.175741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c6631a33-957e-4b07-98ad-34ce95e263ff · outbound

This paper cites Preservation of the global knowledge by not-true distillation in federated learning.Advances in Neural Information Processing Systems, 35:38461–38474, 2022.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Preservation of the global knowledge by not-true distillation in federated learning.Advances in Neural Information Processing Systems, 35:38461–38474, 2022

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:13.158395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 06353927-137e-456d-b867-e36aca61c8ba · outbound

This paper cites Rethinking personalized federated learning from knowledge perspective.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Rethinking personalized federated learning from knowledge perspective

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:13.141574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4158ffae-1e46-4b6c-81c1-9d682d9f4e6e · outbound

This paper cites Federated learning on non-iid data: A survey.Neurocomputing, 465:371–390, 2021.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Federated learning on non-iid data: A survey.Neurocomputing, 465:371–390, 2021

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:13.124814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 63fc7af5-9e1e-4e3e-9be6-ae29151b0cf6 · outbound

This paper cites Fedbn: Federated learning on non-iid features via local batch normalization.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Fedbn: Federated learning on non-iid features via local batch normalization

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:13.106256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 37f67c61-635a-4faf-9edf-eda2df170644 · outbound

This paper cites Bold but cautious: Unlocking the potential of personalized federated learning through cautiously aggressive collab- oration.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Bold but cautious: Unlocking the potential of personalized federated learning through cautiously aggressive collab- oration

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:13.090229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cdf67db7-cbc4-458c-a7fa-b01c947a56ea · outbound

This paper cites Model-contrastive federated learning.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Model-contrastive federated learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.607018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f40a6aea-1c65-494c-b826-3631f65cbf0c · outbound

This paper cites Federated Learning with Personalization Layers.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Federated Learning with Personalization Layers

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.611967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e019f625-530b-4d3a-837e-496338fe917c · outbound

This paper cites Think Locally, Act Globally: Federated Learning with Local and Global Representations.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Think Locally, Act Globally: Federated Learning with Local and Global Representations

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.618558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3ca8171-5356-4088-9ff0-7b0795d1128e · outbound

This paper cites Partialfed: Cross-domain personalized federated learning via partial initialization.Advances in Neural Information Processing Systems, 34:23309–23320, 2021.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Partialfed: Cross-domain personalized federated learning via partial initialization.Advances in Neural Information Processing Systems, 34:23309–23320, 2021

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:13.063956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5f684fce-790b-47a8-9a7f-32800f6f4b9c · outbound

This paper cites Where to begin? on the impact of pre-training and initialization in federated learning.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Where to begin? on the impact of pre-training and initialization in federated learning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:13.049103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation de366663-79b0-4f74-b222-337e5f373c35 · outbound

This paper cites On the importance and applicability of pre-training for federated learning.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective On the importance and applicability of pre-training for federated learning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:13.030519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0d484260-363c-4205-baed-a72025e1d8e9 · outbound

This paper cites Fedbabu: Toward enhanced representation for federated image classification.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Fedbabu: Toward enhanced representation for federated image classification

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:13.014313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 73936ff4-1f26-4ab6-8a55-fbf2426d744f · outbound

This paper cites No fear of classifier biases: Neural collapse inspired federated learning with synthetic and fixed classifier.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective No fear of classifier biases: Neural collapse inspired federated learning with synthetic and fixed classifier

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.997714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ba40726c-d861-483b-91df-e261bca06bc3 · outbound

This paper cites Methods for interpreting and understanding deep neural networks.Digital signal processing, 73:1–15, 2018.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Methods for interpreting and understanding deep neural networks.Digital signal processing, 73:1–15, 2018

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.981843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c5658e8e-e819-4463-acdc-d4f604370870 · outbound

This paper cites Explaining deep neural networks and beyond: A review of methods and applications.Proceedings of the IEEE, 109(3):247–278, 2021.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Explaining deep neural networks and beyond: A review of methods and applications.Proceedings of the IEEE, 109(3):247–278, 2021

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.966055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0ac80532-369e-4307-9293-ce2aa2cbb24e · outbound

This paper cites How transferable are features in deep neural networks?Advances in neural information processing systems, 27, 2014.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective How transferable are features in deep neural networks?Advances in neural information processing systems, 27, 2014

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.662376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e54a3903-521e-4b3f-a2b8-156fab0673e2 · outbound

This paper cites Feature visualization.Distill, 2(11): e7, 2017.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Feature visualization.Distill, 2(11): e7, 2017

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.667453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8642235a-7023-4316-aa2e-bf4b0d98842c · outbound

This paper cites The tunnel effect: Building data representations in deep neural networks.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective The tunnel effect: Building data representations in deep neural networks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.672473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5495f630-d2ac-42ce-9efc-885884e1843b · outbound

This paper cites Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.677699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0ac99a8-005f-4d67-9d72-b9f793001728 · outbound

This paper cites Visualizing and understanding convolutional networks.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Visualizing and understanding convolutional networks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.683291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b09781fa-5a9a-4068-a028-c36a63fa84d2 · outbound

This paper cites Feature learning in deep classifiers through intermediate neural collapse.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Feature learning in deep classifiers through intermediate neural collapse

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.908871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f5e846bc-161d-44b2-a86e-87c87e1814c1 · outbound

This paper cites No fear of hetero- geneity: Classifier calibration for federated learning with non-iid data.Advances in Neural Information Processing Systems, 34:5972–5984, 2021.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective No fear of hetero- geneity: Classifier calibration for federated learning with non-iid data.Advances in Neural Information Processing Systems, 34:5972–5984, 2021

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.891986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5ad1b099-cc6f-4b47-9c8c-3faab7da2c36 · outbound

This paper cites an unresolved cited work.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-09T05:31:12.874532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation af0c4494-4ee7-4dc9-bc8a-4e900a00cf78 · outbound

This paper cites Layer-wise linear mode connectivity.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Layer-wise linear mode connectivity

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.857108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eb7e8dae-5974-437f-aea8-8b990731cd04 · outbound

This paper cites Deeper, broader and artier domain generalization.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Deeper, broader and artier domain generalization

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.709907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e04a3dd5-0579-45dc-936a-d05378be0c70 · outbound

This paper cites Moment matching for multi-source domain adaptation.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Moment matching for multi-source domain adaptation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.715010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7798712-6dc8-4404-9356-b8a0d781deba · outbound

This paper cites Very Deep Convolutional Networks for Large-Scale Image Recognition.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Very Deep Convolutional Networks for Large-Scale Image Recognition

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.719948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbdfb82b-1b55-411f-8e13-2f01b8dbd53f · outbound

This paper cites Deep residual learning for image recognition.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Deep residual learning for image recognition

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.725427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26ce4162-ae09-48d3-8967-7bfae7564d59 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective An image is worth 16x16 words: Transformers for image recognition at scale

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.730750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d88f982-18dd-4b5e-bd2f-34b848b2285c · outbound

This paper cites A simple framework for contrastive learning of visual representations.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective A simple framework for contrastive learning of visual representations

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.735924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 342da9dd-5c02-4c0b-9761-f286aea4f210 · outbound

This paper cites Masked autoencoders are scalable vision learners.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Masked autoencoders are scalable vision learners

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.741705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5257a6fc-229c-4952-b0ee-a76acc53dd20 · outbound

This paper cites Does learning from decentralized non-iid unlabeled data benefit from self supervision? InThe Eleventh International Conference on Learning Representations, 2023.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Does learning from decentralized non-iid unlabeled data benefit from self supervision? InThe Eleventh International Conference on Learning Representations, 2023

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.775676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dab14f03-99d4-47c6-a108-1e88b8be1c62 · outbound

This paper cites Essai sur la géométrie à n dimensions.Bulletin de la Société mathématique de France, 3:103–174, 1875.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Essai sur la géométrie à n dimensions.Bulletin de la Société mathématique de France, 3:103–174, 1875

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.759895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eab1a85f-2c24-4fb1-b4df-7e0b7acae070 · outbound

This paper cites Numerical methods for computing angles between linear subspaces.Mathematics of computation, 27(123):579–594, 1973.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Numerical methods for computing angles between linear subspaces.Mathematics of computation, 27(123):579–594, 1973

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.743220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation de25ea6c-ec7a-478f-83e3-4530947897f7 · outbound

This paper cites Visualizing data using t-sne.Journal of machine learning research, 9(11), 2008.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Visualizing data using t-sne.Journal of machine learning research, 9(11), 2008

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.763662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99396f21-d047-4dfa-8eaa-cfa4d60cf456 · outbound

This paper cites Local sgd converges fast and communicates little.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Local sgd converges fast and communicates little

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.717888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8cbdbd3f-b389-4c90-869d-587f0e07b479 · outbound

This paper cites Is local sgd better than minibatch sgd? In International Conference on Machine Learning, pages 10334–10343.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Is local sgd better than minibatch sgd? In International Conference on Machine Learning, pages 10334–10343

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.703351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ab53ad29-c14a-44bf-887c-8bd072e925b9 · outbound

This paper cites Federated Learning with Non-IID Data.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Federated Learning with Non-IID Data

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.780627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb1dc7f5-c1aa-4170-8984-835809a24cb7 · outbound

This paper cites pfedgf: Enabling personalized federated learning via gradient fusion.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective pfedgf: Enabling personalized federated learning via gradient fusion

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.689352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 31520e58-1a43-4cff-a99b-47fa64fbe027 · outbound

This paper cites Exploiting shared representations for personalized federated learning.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Exploiting shared representations for personalized federated learning

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.674757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 789f24c0-a844-4abd-abaf-fd72fbb8bd0e · outbound

This paper cites Channelfed: Enabling personalized federated learning via localized channel attention.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Channelfed: Enabling personalized federated learning via localized channel attention

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.658654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation de5e1f3b-6799-4d19-8630-d6dd19f4aceb · outbound

This paper cites Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-08-09T05:31:12.032325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 47dafa7f-5c20-4a05-b9d8-5e80ba5ed1ef · outbound

This paper cites Fedproto: Federated prototype learning across heterogeneous clients.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Fedproto: Federated prototype learning across heterogeneous clients

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.642771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6407f486-f0fc-4cdf-9af5-75ed2fc0fbdb · outbound

This paper cites Aligning before aggregating: Enabling cross-domain federated learning via consistent feature extraction.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Aligning before aggregating: Enabling cross-domain federated learning via consistent feature extraction

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.626413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bda56b59-a44b-449a-b05a-964e0833caf6 · outbound

This paper cites Aligning before aggregating: En- abling communication efficient cross-domain federated learning via consistent feature extraction.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Aligning before aggregating: En- abling communication efficient cross-domain federated learning via consistent feature extraction

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.610585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation feb68c36-b578-4a1c-80ac-1a37ed380d26 · outbound

This paper cites Fedfa: Federated learning with feature anchors to align features and classifiers for heterogeneous data.IEEE Transactions on Mobile Computing, 2023.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Fedfa: Federated learning with feature anchors to align features and classifiers for heterogeneous data.IEEE Transactions on Mobile Computing, 2023

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.594372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1fdd65c8-8e3b-4da1-985c-361cfe99540e · outbound

This paper cites Rethinking federated learning with domain shift: A prototype view.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Rethinking federated learning with domain shift: A prototype view

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.576867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4cc6de8f-1721-4e9f-afb7-30493245eb74 · outbound

This paper cites Spherefed: Hyperspherical federated learning.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Spherefed: Hyperspherical federated learning

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.559241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 97da3618-4345-4dd5-bc67-65f1921132ff · outbound

This paper cites Towards understanding and mitigating dimensional collapse in heterogeneous federated learning.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Towards understanding and mitigating dimensional collapse in heterogeneous federated learning

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.543706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 882c2162-4da8-41da-a9b6-3e5a6507b450 · outbound

This paper cites Under- standing and mitigating dimensional collapse in federated learning.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Under- standing and mitigating dimensional collapse in federated learning.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.527301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 88f9523c-faec-4b6d-b758-877b3c895c1f · outbound

This paper cites Taming cross-domain rep- resentation variance in federated prototype learning with heterogeneous data domains.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Taming cross-domain rep- resentation variance in federated prototype learning with heterogeneous data domains

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.510800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8a6a6513-0a4c-40a3-9cb5-5a0e1c4cc283 · outbound

This paper cites Imagenet classification with deep convolutional neural networks.Advances in neural information processing systems, 25, 2012.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Imagenet classification with deep convolutional neural networks.Advances in neural information processing systems, 25, 2012

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.855925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6ac0471-df80-4f88-a7de-2f43f1541688 · outbound

This paper cites Backward feature correction: How deep learning performs deep (hierarchical) learning.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Backward feature correction: How deep learning performs deep (hierarchical) learning

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.485350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ea66d40e-a0ea-4a5b-a87f-84df673813e7 · outbound

This paper cites Dualfed: enjoying both generalization and personalization in federated learning via hierachical representations.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Dualfed: enjoying both generalization and personalization in federated learning via hierachical representations

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.470833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a61a5ecc-106d-46bf-9c7c-987178b364ac · outbound

This paper cites Head2toe: Utilizing intermediate representations for better transfer learning.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Head2toe: Utilizing intermediate representations for better transfer learning

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.455677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3b557289-d079-4721-aa48-a2a5e2441861 · outbound

This paper cites Fine- tuning can distort pretrained features and underperform out-of-distribution.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Fine- tuning can distort pretrained features and underperform out-of-distribution

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.439923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 97789a19-29b3-4195-a36f-64b26e167236 · outbound

This paper cites Understanding intermediate layers using linear classifier probes, 2017.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Understanding intermediate layers using linear classifier probes, 2017

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.881533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc296108-587c-4799-a74c-364973c0e1d0 · outbound

This paper cites Prevalence of neural collapse during the terminal phase of deep learning training.Proceedings of the National Academy of Sciences, 117 (40):24652–24663, 2020.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Prevalence of neural collapse during the terminal phase of deep learning training.Proceedings of the National Academy of Sciences, 117 (40):24652–24663, 2020

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.887070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 700fd133-a1a1-495a-9937-38afe7270743 · outbound

This paper cites Intrinsic dimension of data representations in deep neural networks.Advances in Neural Information Processing Systems, 32, 2019.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Intrinsic dimension of data representations in deep neural networks.Advances in Neural Information Processing Systems, 32, 2019

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.892446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccb3c3f3-8f48-4924-80ab-5069370abebb · outbound

This paper cites Understanding and improving transfer learning of deep models via neural collapse.Transactions on Machine Learning Research, 2024.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Understanding and improving transfer learning of deep models via neural collapse.Transactions on Machine Learning Research, 2024

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.392614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e87b90a2-f6c8-4681-9905-51ab3791d3ec · outbound

This paper cites Lempitsky.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Lempitsky

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.375756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fe564079-7c00-4944-98ab-fe36b0398ead · outbound

This paper cites Gradient-based learning applied to document recognition.Proc.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Gradient-based learning applied to document recognition.Proc

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.359173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f32bcb30-399b-4794-a9d5-a68f3b743abe · outbound

This paper cites an unresolved cited work.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-09T05:31:12.342999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5bff1c22-3090-4969-9cef-2ca011a3aa1d · outbound

This paper cites Reading digits in natural images with unsupervised feature learning.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Reading digits in natural images with unsupervised feature learning

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.918387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9229ed98-c7eb-473d-86c5-ff44100c8b4c · outbound

This paper cites Pytorch: An imperative style, high-performance deep learning library.Advances in neural information processing systems, 32, 2019.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Pytorch: An imperative style, high-performance deep learning library.Advances in neural information processing systems, 32, 2019

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-09T05:31:11.923067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 949abb2d-7a22-43ec-899b-6b3a472a16f3 · outbound

This paper cites Simulated annealing in early layers leads to better generalization.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Simulated annealing in early layers leads to better generalization

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.303933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0950afde-7f0c-4a10-a9fb-28df6b480e14 · outbound

This paper cites What variables affect out-of-distribution generalization in pretrained models? InThe Thirty- eighth Annual Conference on Neural Information Processing Systems, 2024.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective What variables affect out-of-distribution generalization in pretrained models? InThe Thirty- eighth Annual Conference on Neural Information Processing Systems, 2024

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.286163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dbfb1ee4-4ce0-4b0c-bc2b-7e6d60c87f8e · outbound

This paper cites Do vision transformers see like convolutional neural networks?Advances in neural information processing systems, 34:12116–12128, 2021.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Do vision transformers see like convolutional neural networks?Advances in neural information processing systems, 34:12116–12128, 2021

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.268801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f43b4b53-2ec8-42bf-8353-b179a78b43e3 · outbound

This paper cites Let the features of the pre-aggregated and post-aggregated models be denoted as Z ℓ pre and Z ℓ post, respectively.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Let the features of the pre-aggregated and post-aggregated models be denoted as Z ℓ pre and Z ℓ post, respectively

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.249633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 524c6a23-9f9b-4252-8708-2de069d82373 · outbound

This paper cites Discussions and Limitations.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Discussions and Limitations

Reference 76

Resolution: malformed identifier; raw_fallback, observed 2026-08-09T05:31:12.224337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9f3b3098-0605-43b2-a012-2a90ea8c52bb · outbound

This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:31:12.184901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers