Paper Citation Record · LEDGER

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach

As of 17 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 4 inbound Pith citation observations for arXiv:2502.01145.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.01145 v2

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T16:30:39.112363Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:45:45.599462Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T02:49:25.223479Z

Reference resolution

12 of 12 outbound references displayed

verified exact0
verified fuzzy9
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cfa25528-a19d-4785-b384-002c4cd7508d · outbound

This paper cites FMTL often involves clients with different data distributions, model architectures, or task objectives.

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach FMTL often involves clients with different data distributions, model architectures, or task objectives

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:30:39.238037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ef313189-123a-4381-8c21-71c96ae1cbb2 · outbound

This paper cites Sheaves provide a natural way to ensure consistency between local (client-specific) and global (network-wide) information.

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach Sheaves provide a natural way to ensure consistency between local (client-specific) and global (network-wide) information

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:30:39.229742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 72b287a5-5569-44a7-86a5-945be64345a2 · outbound

This paper cites This nuanced representation is more sophisticated than traditional approaches that often assume uniform relationships across the network.

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach This nuanced representation is more sophisticated than traditional approaches that often assume uniform relationships across the network

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:30:39.221285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 123b7b72-caa7-4063-b6e0-388b6d7d11d8 · outbound

This paper cites an unresolved cited work.

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-09T16:30:39.212852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 83003f62-779d-4917-b112-191c601a17be · outbound

This paper cites Our approach enforces consistency between the projections of local models onto the interaction space.

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach Our approach enforces consistency between the projections of local models onto the interaction space

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:30:39.203988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9133feda-08cd-4f48-aeed-4c8b09387a66 · outbound

This paper cites By minimizing the sheaf Laplacian term, local models are en- couraged to collaborate effectively, leveraging shared information to improve overall performance.

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach By minimizing the sheaf Laplacian term, local models are en- couraged to collaborate effectively, leveraging shared information to improve overall performance

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:30:39.194858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6e7fe880-c36a-40fa-b009-c0826297b240 · outbound

This paper cites Pij acts as a feature selection matrix, identifying common or comparable features between clientsi and j.

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach Pij acts as a feature selection matrix, identifying common or comparable features between clientsi and j

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:30:39.185970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5bc058e8-d0a1-4629-bf57-ab9f398083d3 · outbound

This paper cites an unresolved cited work.

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-09T16:30:39.176715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ff707f34-ae5a-4a0c-9304-9672744ff420 · outbound

This paper cites The restriction maps allow for meaningful comparisons by projecting onto a common space.

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach The restriction maps allow for meaningful comparisons by projecting onto a common space

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:30:39.167901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 37e3b8e5-3977-4029-b01f-a5121bfa08d8 · outbound

This paper cites Unlike many traditional FMTL methods that assume homogeneous models across clients, our approach naturally accommodates heterogeneous model architectures and task objectives.

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach Unlike many traditional FMTL methods that assume homogeneous models across clients, our approach naturally accommodates heterogeneous model architectures and task objectives

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:30:39.158719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 78500220-091e-4e0f-96b7-cf1424cb35c3 · outbound

This paper cites Our approach allows for more nuanced modelling of inter-client relationships through the interaction space and restriction maps.

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach Our approach allows for more nuanced modelling of inter-client relationships through the interaction space and restriction maps

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:30:39.149750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8e18b662-6abf-4f90-adef-f1e5dd2f3a15 · outbound

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

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach Think Locally, Act Globally: Federated Learning with Local and Global Representations

Reference 978

Resolution: unresolved; no resolver link, observed 2026-08-09T16:30:39.078044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 80a45442-42ab-454e-b6ff-2cdfba790987 · inbound

Resilient-native and Intelligent NextG Systems cites this paper.

Resilient-native and Intelligent NextG Systems Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:45.599462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89dec681-bfb7-49d0-9112-81a3b5247750 · inbound

MuCALD-SplitFed: Causal-Latent Diffusion for Privacy-Preserving Multi-Task Split-Federated Medical Image Segmentation cites this paper.

MuCALD-SplitFed: Causal-Latent Diffusion for Privacy-Preserving Multi-Task Split-Federated Medical Image Segmentation Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-09T06:15:37.577557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cf09c9c5-41ff-4516-9f08-1ff6baae3705 · inbound

The Sheaf Laplacian: A Topological Framework for Data Fusion and Consensus in Distributed Sensing Networks cites this paper.

The Sheaf Laplacian: A Topological Framework for Data Fusion and Consensus in Distributed Sensing Networks Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-07-04T02:49:25.225063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 531f3a3e-4ebd-45f8-95fe-662988703848 · inbound

A Sheaf-Theoretic Framework for Distributed Multi-Site Channel Charting cites this paper.

A Sheaf-Theoretic Framework for Distributed Multi-Site Channel Charting Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T02:12:36.752296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.