CALM: Class-wise Agreement and Label-gated Disagreement Modulation for Decentralized Federated Learning

• URL: http://arxiv.org/abs/2609.05884v1
• Date: Sat, 05 Sep 2026 05:13:07 GMT
• Title: CALM: Class-wise Agreement and Label-gated Disagreement Modulation for Decentralized Federated Learning
• Abstract summary: CALM replaces every hard decision with a smooth trust gate at three levels.<n>It consistently outperforms uniform and hard-filtered distillation and matches or exceeds competing heterogeneous-FL methods.
• Score: 1.1617094867403568
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conventional federated learning relies on parameter averaging, which forces clients to be doubly homogeneous: all must run an identical architecture, and accuracy degrades when local data are non-IID. Decentralized federated distillation sidesteps both: each client runs its peers' model snapshots as teachers on its own local data and distills from their soft predictions, with no server, no public data, and no shared architecture. Under severe non-IID skew, however, the trustworthiness of the aggregated teacher target is a matter of degree, yet existing pipelines make hard, all-or-nothing decisions: outlier teachers are discarded by threshold, and whatever target survives is trusted in full. We propose CALM, which replaces every hard decision with a smooth trust gate at three levels: per class, teachers are weighted by agreement with the peer consensus; per sample, distillation is scaled by the teachers' divergence from that target; and a label gate scales it by how strongly the target supports the sample's true label. None of this adds communication or auxiliary data. On CIFAR-10, SVHN, OrganAMNIST, and Google Speech Commands with heterogeneous client architectures under Dirichlet label skew, CALM consistently outperforms uniform and hard-filtered distillation and matches or exceeds competing heterogeneous-FL methods.

Related papers

• CRAD: Class-wise Reliability-Aware Distillation for Decentralized Heterogeneous Federated Learning [3.2847672479922783]
  We propose a class-wise reliability-Aware Distillation (CRAD) for federated learning.<n>CRAD weights each teacher by its per-class reliability (precision, or inverse variance)<n>It consistently outperforms competing methods in global accuracy.
  arXiv  Detail & Related papers  (2026-08-31T22:36:30Z)
• FedCC: Towards Addressing Label Distribution Skews in Distillation-Based Federated Learning [6.693752118202639]
  Federated Learning (FL) enables distributed clients to collaboratively train models without sharing raw data.<n>In distillation-based FL, each client applies its local model on an unlabeled public dataset, and shares only prediction results with the server.<n>We propose FedCC, a simple and effective algorithm for mitigating client misclassification.
  arXiv  Detail & Related papers  (2026-08-24T09:34:26Z)
• Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging [13.653084100002737]
  On-policy distillation in which a teacher corrects samples that the student itself generates presupposes that the two models speak the same language.<n>We present Any-OPD, to our knowledge the first framework for on-policy distillation between arbitrary pairs of latent flow-matching generators.
  arXiv  Detail & Related papers  (2026-08-04T08:23:57Z)
• FedQHD: Closed-Form Function-Space Federated Reinforcement Learning [18.086374545576792]
  Federated reinforcement learning enables decentralized agents to collaboratively improve policies or value estimates without exchanging raw trajectories.<n>We propose FedQHD, a federated Q-learning method using hyperdimensional (random-feature) state encoders with a linear readout.<n>We show that this gap decomposes into subspace misalignment, anchor-set conditioning, and regularization bias.
  arXiv  Detail & Related papers  (2026-05-27T18:59:40Z)
• FedFusion: Federated Learning with Diversity- and Cluster-Aware Encoders for Robust Adaptation under Label Scarcity [33.17279604575767]
  FedFusion is a federated transfer-learning framework that unifies domain adaptation and frugal labelling.<n>Labelled teacher clients guide learner clients via confidence-filtered pseudo-labels and domain-adaptive transfer.<n>FedFusion consistently outperforms state-of-the-art baselines in accuracy, robustness, and fairness.
  arXiv  Detail & Related papers  (2025-09-23T16:46:06Z)
• Federated Learning under Partially Class-Disjoint Data via Manifold Reshaping [64.58402571292723]
  We propose a manifold reshaping approach called FedMR to calibrate the feature space of local training. We conduct extensive experiments on a range of datasets to demonstrate that our FedMR achieves much higher accuracy and better communication efficiency.
  arXiv  Detail & Related papers  (2024-05-29T10:56:13Z)
• Exploring Vacant Classes in Label-Skewed Federated Learning [113.65301899666645]
  This paper introduces FedVLS, a novel approach to label-skewed federated learning.<n>It integrates vacant-class distillation and logit suppression simultaneously.<n>Experiments validate the efficacy of FedVLS, demonstrating superior performance compared to previous state-of-the-art (SOTA) methods.
  arXiv  Detail & Related papers  (2024-01-04T16:06:31Z)
• Appeal: Allow Mislabeled Samples the Chance to be Rectified in Partial Label Learning [55.4510979153023]
  In partial label learning (PLL), each instance is associated with a set of candidate labels among which only one is ground-truth. To help these mislabeled samples "appeal," we propose the first appeal-based framework.
  arXiv  Detail & Related papers  (2023-12-18T09:09:52Z)
• JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification [65.268245109828]
  Semi-supervised text classification (SSTC) has gained increasing attention due to its ability to leverage unlabeled data. Existing approaches based on pseudo-labeling suffer from the issues of pseudo-label bias and error accumulation. We propose JointMatch, a holistic approach for SSTC that addresses these challenges by unifying ideas from recent semi-supervised learning.
  arXiv  Detail & Related papers  (2023-10-23T05:43:35Z)
• Rethinking Client Drift in Federated Learning: A Logit Perspective [125.35844582366441]
  Federated Learning (FL) enables multiple clients to collaboratively learn in a distributed way, allowing for privacy protection. We find that the difference in logits between the local and global models increases as the model is continuously updated. We propose a new algorithm, named FedCSD, a Class prototype Similarity Distillation in a federated framework to align the local and global models.
  arXiv  Detail & Related papers  (2023-08-20T04:41:01Z)
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
  Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
  arXiv  Detail & Related papers  (2022-11-12T09:21:49Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.