Federated Learning for Non-factorizable Models using Deep Generative Prior Approximations

• URL: http://arxiv.org/abs/2405.16055v1
• Date: Sat, 25 May 2024 04:44:06 GMT
• Title: Federated Learning for Non-factorizable Models using Deep Generative Prior Approximations
• Authors: Conor Hassan, Joshua J Bon, Elizaveta Semenova, Antonietta Mira, Kerrie Mengersen,
• Abstract summary: Federated learning (FL) allows for collaborative model training across decentralized clients while preserving privacy by avoiding data sharing. We introduce the Structured Independence via deep Generative Model Approximation ( SIGMA) prior which enables FL for non-factorizable models across clients. We demonstrate the SIGMA prior's effectiveness on synthetic data and showcase its utility in a real-world example of FL for spatial data, using a conditional autoregressive prior to model spatial dependence across Australia.
• Score: 0.6990493129893112
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated learning (FL) allows for collaborative model training across decentralized clients while preserving privacy by avoiding data sharing. However, current FL methods assume conditional independence between client models, limiting the use of priors that capture dependence, such as Gaussian processes (GPs). We introduce the Structured Independence via deep Generative Model Approximation (SIGMA) prior which enables FL for non-factorizable models across clients, expanding the applicability of FL to fields such as spatial statistics, epidemiology, environmental science, and other domains where modeling dependencies is crucial. The SIGMA prior is a pre-trained deep generative model that approximates the desired prior and induces a specified conditional independence structure in the latent variables, creating an approximate model suitable for FL settings. We demonstrate the SIGMA prior's effectiveness on synthetic data and showcase its utility in a real-world example of FL for spatial data, using a conditional autoregressive prior to model spatial dependence across Australia. Our work enables new FL applications in domains where modeling dependent data is essential for accurate predictions and decision-making.

Related papers

• Towards Graph-Based Privacy-Preserving Federated Learning: ModelNet -- A ResNet-based Model Classification Dataset [0.3683202928838613]
  We introduce ModelNet, a novel image classification dataset constructed from the embeddings extracted from a pre-trained ResNet50 model.<n>We train each client-specific subset of all three variants on the pre-trained ResNet50 model to save model parameters.<n>In addition to multi-domain image data, we propose a new hypothesis to define the FL algorithm that can access the anonymized model parameters.
  arXiv  Detail & Related papers  (2025-05-31T08:53:16Z)
• Not All Clients Are Equal: Personalized Federated Learning on Heterogeneous Multi-Modal Clients [52.14230635007546]
  Foundation models have shown remarkable capabilities across diverse multi-modal tasks, but their centralized training raises privacy concerns and induces high transmission costs.<n>For the growing demand for personalizing AI models for different user purposes, personalized federated learning (PFL) has emerged.<n>PFL allows each client to leverage the knowledge of other clients for further adaptation to individual user preferences, again without the need to share data.
  arXiv  Detail & Related papers  (2025-05-20T09:17:07Z)
• FedSKD: Aggregation-free Model-heterogeneous Federated Learning using Multi-dimensional Similarity Knowledge Distillation [7.944298319589845]
  Federated learning (FL) enables privacy-preserving collaborative model training without direct data sharing. Model-heterogeneous FL (MHFL) allows clients to train personalized models with heterogeneous architectures tailored to their computational resources and application-specific needs. While peer-to-peer (P2P) FL removes server dependence, it suffers from model drift and knowledge dilution, limiting its effectiveness in heterogeneous settings. We propose FedSKD, a novel MHFL framework that facilitates direct knowledge exchange through round-robin model circulation.
  arXiv  Detail & Related papers  (2025-03-23T05:33:10Z)
• Federated Dynamic Modeling and Learning for Spatiotemporal Data Forecasting [0.8568432695376288]
  This paper presents an advanced Federated Learning (FL) framework for forecasting complextemporal data, improving upon recent state-of-the-art models. The resulting architecture significantly improves the model's capacity to handle complex temporal patterns in diverse forecasting applications. The efficiency of our approach is demonstrated through extensive experiments on real-world applications, including public datasets for multimodal transport demand forecasting and private datasets for Origin-Destination (OD) matrix forecasting in urban areas.
  arXiv  Detail & Related papers  (2025-03-06T15:16:57Z)
• GeFL: Model-Agnostic Federated Learning with Generative Models [3.4546761246181696]
  Federated learning (FL) is a distributed training paradigm that enables collaborative learning across clients without sharing local data, thereby preserving privacy.<n>We propose Generative Model-Aided Federated Learning (GeFL), a framework that enables cross-client knowledge sharing via a generative model trained in a federated manner.
  arXiv  Detail & Related papers  (2024-12-24T14:39:47Z)
• Federated Learning for Traffic Flow Prediction with Synthetic Data Augmentation [10.751702067716804]
  This work introduces an FL framework, referred to as FedTPS, to generate synthetic data to augment each client's local dataset by training a trajectory generation model through FL. The proposed framework is evaluated on a large-scale real world ride-sharing dataset using various FL methods and Traffic Flow Prediction models.
  arXiv  Detail & Related papers  (2024-12-11T15:25:38Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• Bridging Data Barriers among Participants: Assessing the Potential of Geoenergy through Federated Learning [2.8498944632323755]
  This study introduces a novel federated learning (FL) framework based on XGBoost models. FL models demonstrate superior accuracy and generalization capabilities compared to separate models. This study opens new avenues for assessing unconventional reservoirs through collaborative and privacy-preserving FL techniques.
  arXiv  Detail & Related papers  (2024-04-29T09:12:31Z)
• An Aggregation-Free Federated Learning for Tackling Data Heterogeneity [50.44021981013037]
  Federated Learning (FL) relies on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global model aggregated by the server from the previous training round. We introduce FedAF, a novel aggregation-free FL algorithm.
  arXiv  Detail & Related papers  (2024-04-29T05:55:23Z)
• Federated Bayesian Deep Learning: The Application of Statistical Aggregation Methods to Bayesian Models [0.9940108090221528]
  Aggregation strategies have been developed to pool or fuse the weights and biases of distributed deterministic models. We show that simple application of the aggregation methods associated with FL schemes for deterministic models is either impossible or results in sub-optimal performance.
  arXiv  Detail & Related papers  (2024-03-22T15:02:24Z)
• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)
• PFL-GAN: When Client Heterogeneity Meets Generative Models in Personalized Federated Learning [55.930403371398114]
  We propose a novel generative adversarial network (GAN) sharing and aggregation strategy for personalized learning (PFL) PFL-GAN addresses the client heterogeneity in different scenarios. More specially, we first learn the similarity among clients and then develop an weighted collaborative data aggregation. The empirical results through the rigorous experimentation on several well-known datasets demonstrate the effectiveness of PFL-GAN.
  arXiv  Detail & Related papers  (2023-08-23T22:38:35Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• Knowledge Distillation for Federated Learning: a Practical Guide [8.2791533759453]
  Federated Learning (FL) enables the training of Deep Learning models without centrally collecting possibly sensitive raw data. The most used algorithms for FL are parameter-averaging based schemes (e.g., Federated Averaging) that, however, have well known limits. We provide a review of KD-based algorithms tailored for specific FL issues.
  arXiv  Detail & Related papers  (2022-11-09T08:31:23Z)
• FedDAR: Federated Domain-Aware Representation Learning [14.174833360938806]
  Cross-silo Federated learning (FL) has become a promising tool in machine learning applications for healthcare. We propose a novel method, FedDAR, which learns a domain shared representation and domain-wise personalized prediction heads.
  arXiv  Detail & Related papers  (2022-09-08T19:18:59Z)
• Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning [86.59588262014456]
  Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. We propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG) Our FedFTG significantly outperforms the state-of-the-art (SOTA) FL algorithms and can serve as a strong plugin for enhancing FedAvg, FedProx, FedDyn, and SCAFFOLD.
  arXiv  Detail & Related papers  (2022-03-17T11:18:17Z)
• Prototype Guided Federated Learning of Visual Feature Representations [15.021124010665194]
  Federated Learning (FL) is a framework which enables distributed model training using a large corpus of decentralized training data. Existing methods aggregate models disregarding their internal representations, which are crucial for training models in vision tasks. We introduce FedProto, which computes client deviations using margins of representations learned on distributed data.
  arXiv  Detail & Related papers  (2021-05-19T08:29:12Z)

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.