Federated Learning with Energy-Based Structured Probabilistic Inference

• URL: http://arxiv.org/abs/2606.30161v1
• Date: Mon, 29 Jun 2026 11:38:46 GMT
• Title: Federated Learning with Energy-Based Structured Probabilistic Inference
• Abstract summary: Federated learning typically aggregates client updates using fixed or weighting rules.<n>We propose a framework that refines client aggregation weights using Conditional Random Fields (CRFs)<n>Our method defines unary potentials for individual clients and pairwise potentials for all client pairs, allowing the server to model both client-specific reliability and interactions between clients.
• Score: 7.122698354756618
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated learning typically aggregates client updates using fixed or heuristic weighting rules, which can be suboptimal when clients have heterogeneous data and varying contributions to the global model. We propose a framework that refines client aggregation weights using Conditional Random Fields (CRFs). Our method defines unary potentials for individual clients and pairwise potentials for all client pairs, allowing the server to model both client-specific reliability and interactions between clients. The resulting CRF inference produces aggregation weights that enable better convergence of the global training objective. Experiments show that, under non-IID heterogeneity, our approach consistently improves performance over well-established federated learning baselines.

Related papers

• Similarity-Aware Personalized Federated Learning in Heterogeneous Environments [10.354095147014043]
  Federated Learning allows decentralized clients to train models collaboratively while preserving data privacy.<n> distribution mismatch across clients often leads to poor global generalization and degraded local client-level performance.<n>We propose SAPE-FL (Similarity-Aware Personalized Federated Learning), a novel personalization framework that anchors each client's model to both the global model and a similarity-weighted peer averaged model.
  arXiv  Detail & Related papers  (2026-09-02T07:48:04Z)
• Representation-Aligned Multi-Scale Personalization for Federated Learning [24.809441061502095]
  This paper presents FRAMP, a unified framework for personalized and resource-adaptive federated learning.<n>Instead of relying on a fixed global model, FRAMP generates client-specific models from compact client descriptors.<n>Experiments on vision and graph benchmarks demonstrate that FRAMP enhances generalization and adaptivity across a wide range of client settings.
  arXiv  Detail & Related papers  (2026-04-13T10:38:21Z)
• FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning [7.6428960455933925]
  Federated Learning (FL) enables collaborative model training across multiple clients without sharing their private data.<n>Data heterogeneity across clients leads to client drift, which degrades the overall generalization performance of the model.<n>We propose FedVG, a novel gradient-based federated aggregation framework.
  arXiv  Detail & Related papers  (2026-02-24T22:05:42Z)
• Client-Centric Federated Adaptive Optimization [78.30827455292827]
  Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private.<n>We propose Federated-Centric Adaptive Optimization, which is a class of novel federated optimization approaches.
  arXiv  Detail & Related papers  (2025-01-17T04:00:50Z)
• Towards Instance-adaptive Inference for Federated Learning [80.38701896056828]
  Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework. Our experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64% improvement against the top-performing method with less than 15% communication cost on Tiny-ImageNet.
  arXiv  Detail & Related papers  (2023-08-11T09:58:47Z)
• Personalized Federated Learning via Amortized Bayesian Meta-Learning [21.126405589760367]
  We introduce a new perspective on personalized federated learning through Amortized Bayesian Meta-Learning. Specifically, we propose a novel algorithm called emphFedABML, which employs hierarchical variational inference across clients. Our theoretical analysis provides an upper bound on the average generalization error and guarantees the generalization performance on unseen data.
  arXiv  Detail & Related papers  (2023-07-05T11:58:58Z)
• Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction [76.26710990597498]
  We show that the class-imbalance of the grouped data from randomly selected clients can lead to significant performance degradation. Based on our key observation, we design an efficient client sampling mechanism, i.e., Federated Class-balanced Sampling (Fed-CBS) In particular, we propose a measure of class-imbalance and then employ homomorphic encryption to derive this measure in a privacy-preserving way.
  arXiv  Detail & Related papers  (2022-09-30T05:42:56Z)
• Straggler-Resilient Personalized Federated Learning [55.54344312542944]
  Federated learning allows training models from samples distributed across a large network of clients while respecting privacy and communication restrictions. We develop a novel algorithmic procedure with theoretical speedup guarantees that simultaneously handles two of these hurdles. Our method relies on ideas from representation learning theory to find a global common representation using all clients' data and learn a user-specific set of parameters leading to a personalized solution for each client.
  arXiv  Detail & Related papers  (2022-06-05T01:14:46Z)
• On the Convergence of Clustered Federated Learning [57.934295064030636]
  In a federated learning system, the clients, e.g. mobile devices and organization participants, usually have different personal preferences or behavior patterns. This paper proposes a novel weighted client-based clustered FL algorithm to leverage the client's group and each client in a unified optimization framework.
  arXiv  Detail & Related papers  (2022-02-13T02:39:19Z)
• Personalized Federated Learning with First Order Model Optimization [76.81546598985159]
  We propose an alternative to federated learning, where each client federates with other relevant clients to obtain a stronger model per client-specific objectives. We do not assume knowledge of underlying data distributions or client similarities, and allow each client to optimize for arbitrary target distributions of interest. Our method outperforms existing alternatives, while also enabling new features for personalized FL such as transfer outside of local data distributions.
  arXiv  Detail & Related papers  (2020-12-15T19:30:29Z)
• Client Adaptation improves Federated Learning with Simulated Non-IID Clients [1.0896567381206714]
  We present a federated learning approach for learning a client adaptable, robust model when data is non-identically and non-independently distributed (non-IID) across clients. We show that adding learned client-specific conditioning improves model performance, and the approach is shown to work on balanced and imbalanced data set from both audio and image domains.
  arXiv  Detail & Related papers  (2020-07-09T13:48:39Z)

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.