BESplit mitigates non-IID bias in split federated learning via evidential aggregation, bias-compensated client pairing, and dual-teacher distillation, outperforming prior methods on five benchmarks.
hub
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
representative citing papers
Risk-controlled post-processing yields a threshold-structured policy that follows the baseline except where an oracle fallback sharply reduces conditional violation risk, achieving O(log n/n) expected excess risk in i.i.d. settings and exact risk control under exchangeability.
Empirical tests with quad-mesh filling indicate that decision regions in modern image classifiers are simply connected.
SATFormer uses a context-dependent gate for selective reuse of early Transformer representations, improving validation loss and zero-shot accuracy especially on retrieval benchmarks.
NodePFN pre-trains on synthetic graphs with controllable homophily and causal feature-label models to achieve 71.27 average accuracy on 23 node classification benchmarks without graph-specific training.
An attack aligns differently shuffled intermediate activations from secure Transformer inference queries to recover model weights with low error using roughly one dollar of queries.
mHC projects hyper-connection residual spaces onto a manifold to restore identity mapping, enabling stable large-scale training with performance gains over standard HC.
A Gaussian mixture MIL framework with partially subsampled instances improves metastasis prediction accuracy on breast cancer whole-slide images over prior methods.
AgriKD distills multi-level knowledge from Vision Transformers to lightweight CNNs, achieving comparable leaf disease classification accuracy with 172x fewer parameters and 18-22x faster inference.
citing papers explorer
-
BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
BESplit mitigates non-IID bias in split federated learning via evidential aggregation, bias-compensated client pairing, and dual-teacher distillation, outperforming prior methods on five benchmarks.
-
Risk-Controlled Post-Processing of Decision Policies
Risk-controlled post-processing yields a threshold-structured policy that follows the baseline except where an oracle fallback sharply reduces conditional violation risk, achieving O(log n/n) expected excess risk in i.i.d. settings and exact risk control under exchangeability.
-
Empirical Evidence for Simply Connected Decision Regions in Image Classifiers
Empirical tests with quad-mesh filling indicate that decision regions in modern image classifiers are simply connected.
-
Transformers with Selective Access to Early Representations
SATFormer uses a context-dependent gate for selective reuse of early Transformer representations, improving validation loss and zero-shot accuracy especially on retrieval benchmarks.
-
Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
NodePFN pre-trains on synthetic graphs with controllable homophily and causal feature-label models to achieve 71.27 average accuracy on 23 node classification benchmarks without graph-specific training.
-
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
An attack aligns differently shuffled intermediate activations from secure Transformer inference queries to recover model weights with low error using roughly one dollar of queries.
-
mHC: Manifold-Constrained Hyper-Connections
mHC projects hyper-connection residual spaces onto a manifold to restore identity mapping, enabling stable large-scale training with performance gains over standard HC.
-
Detecting Breast Carcinoma Metastasis on Whole-Slide Images by Partially Subsampled Multiple Instance Learning
A Gaussian mixture MIL framework with partially subsampled instances improves metastasis prediction accuracy on breast cancer whole-slide images over prior methods.
-
AgriKD: Cross-Architecture Knowledge Distillation for Efficient Leaf Disease Classification
AgriKD distills multi-level knowledge from Vision Transformers to lightweight CNNs, achieving comparable leaf disease classification accuracy with 172x fewer parameters and 18-22x faster inference.
- Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning
- Simply Stabilizing the Loop via Fully Looped Transformer
- LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention