{"total":11,"items":[{"citing_arxiv_id":"2607.08219","ref_index":84,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Benchmark Evaluation of Federated Learning on Multi-organ Images","primary_cat":"cs.CV","submitted_at":"2026-07-09T08:14:15+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.06616","ref_index":4,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning","primary_cat":"cs.LG","submitted_at":"2026-07-07T08:25:04+00:00","verdict":"CONDITIONAL","verdict_confidence":"HIGH","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Entropy-adaptive per-class budgets let clients generate far fewer synthetic samples yet still close most of the accuracy gap caused by label skew in federated learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.32016","ref_index":199,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning","primary_cat":"cs.LG","submitted_at":"2026-06-30T17:47:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FedLAB organizes multimodal graph knowledge into typed hierarchical codebooks for modality evidence, node semantics, and topology context via federated semantic barycenter pre-training, improving performance by up to 7.53% on benchmarks while enabling semantic traceability.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22743","ref_index":55,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"SeqLoRA: Bilevel Orthogonal Adaptation for Continual Multi-Concept Generation","primary_cat":"cs.LG","submitted_at":"2026-05-21T17:13:49+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SeqLoRA applies bilevel optimization to sequential LoRA adaptation for continual multi-concept text-to-image generation with theoretical bounds on forgetting and interference.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Consider a model with L layers adapted for T concepts via SeqLoRA. At layer ℓ, the pre- trained weight is W(ℓ) 0 ∈R nℓ×mℓ and the LoRA factors for concept k are A(ℓ) k ∈R nℓ×r and B(ℓ) k ∈R mℓ×r. In the sequential continual learning setting, the accumulated weight matrix after learning concept j at layerℓis: W(ℓ) j =W (ℓ) 0 + jX k=1 A(ℓ) k (B(ℓ) k )⊤.(55) The composed output for conceptjis: Oj(X(ℓ) j ) =W (ℓ) j X(ℓ) j (56) while the composed output (with allTconcepts) is: ˜OT (X(ℓ) j ) =W (ℓ) T X(ℓ) j =O j(X(ℓ) j ) + TX k=j+1 A(ℓ) k (B(ℓ) k )⊤X(ℓ) j .(57) The total crosstalk at layerℓfor conceptjis: ∆(ℓ) j ≜ ˜OT (X(ℓ) j )−O j(X(ℓ) j ) =C (ℓ) j X(ℓ) j ∈R nℓ×p,(58) 21 where the crosstalk operator is:"},{"citing_arxiv_id":"2605.19629","ref_index":20,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation","primary_cat":"stat.ML","submitted_at":"2026-05-19T10:08:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Establishes non-asymptotic Gaussian approximation bounds for federated LSA with explicit communication-heterogeneity trade-offs and introduces an online multiplier bootstrap for last-iterate inference with validity guarantees.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18028","ref_index":4,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"FedSDR: Federated Self-Distillation with Rectification","primary_cat":"cs.LG","submitted_at":"2026-05-18T08:18:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FedSDR augments federated self-distillation with dual LoRA streams (local smoothing and global rectification) to produce globally aligned, factually faithful models under statistical heterogeneity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17508","ref_index":24,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation","primary_cat":"cs.LG","submitted_at":"2026-05-17T15:42:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16690","ref_index":31,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models","primary_cat":"cs.LG","submitted_at":"2026-05-15T23:06:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UB-SMoE balances expert utilization in heterogeneous federated SMoE fine-tuning via Dynamic Modulated Routing and Universal Pseudo-Gradient, delivering up to 45% compute reduction and 8.7x performance gains for low-resource clients over prior LoRA-rank methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15573","ref_index":81,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems","primary_cat":"cs.CL","submitted_at":"2026-05-15T03:33:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16350","ref_index":12,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Federated Nested Learning: Collaborative Training of Self-Referential Memories for Test-Time Adaptation","primary_cat":"cs.LG","submitted_at":"2026-05-08T04:31:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FedNL reformulates federated learning as nested optimization with linear attention for collaborative test-time adaptation on non-IID data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02143","ref_index":31,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Personalized Federated Learning for Gradient Alignment","primary_cat":"cs.LG","submitted_at":"2026-05-04T01:50:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"pFLAlign uses two gradient alignment mechanisms derived from PAC-Bayesian analysis to reduce variance in local training and distortion in aggregation, yielding state-of-the-art personalization in federated learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}