Skip to content
#federated learning Book Open access

FedCSOT: Model-Heterogeneous Personalized Federated Learning via Channel Semantic Optimal Transport

Nov 2026 · Proceedings of the 35th ACM International Conference on Information and Knowledge Management · 0 citations · 48 references
Privacy-Preserving Technologies in Data

Abstract

Federated Learning (FL) provides a privacy-preserving paradigm for collaborative learning across distributed clients. In practical FL systems, clients often exhibit non-IID data distributions and deploy diverse model architectures under resource constraints. While model heterogeneity improves deployment flexibility under client resource constraints, it prevents direct parameter aggregation and makes cross-architecture knowledge transfer challenging. Existing methods mainly rely on shared structures, coarse-grained distillation, or projection-based feature alignment, which cannot explicitly capture channel-level semantic correspondences across heterogeneous architectures. This paper proposes FedCSOT, a model-heterogeneous personalized FL framework based on channel semantic optimal transport. FedCSOT induces sequence-driven channel semantics from channel responses over a shared unlabeled sequence, establishing a common semantic space for cross-architecture alignment. The framework models cross-architecture semantic alignment through entropy-regularized optimal transport to facilitate knowledge transfer. It further designs a divergence-aware personalized fusion strategy to adaptively balance consensus knowledge and local personalization under non-IID data distributions. Extensive experiments under diverse data and model heterogeneity settings demonstrate that FedCSOT consistently improves average test accuracy, convergence behavior, and robustness over representative baselines. The code is available at https://github.com/greenhead01/FedCSOT.

Read PDF

Similar papers

#machine learning Review Open access Oct 2014

Software development in startup companies: A systematic mapping study

The results indicate that software engineering work practices are chosen opportunistically, adapted and configured to provide value under the constrains imposed by the startup context.

Nicolò Paternoster, Carmine Giardino, M. Unterkalmsteiner et al. · 394 citations · ⚡54
#machine learning Review Open access Jun 2014

Why Early-Stage Software Startups Fail: A Behavioral Framework

This state-of-practice investigation was performed using a literature review followed by a multiple-case study approach and presents how inconsistency between managerial strategies and execution can lead to failure by means of a behavioral framework.

Carmine Giardino, Xiaofeng Wang, P. Abrahamsson · 175 citations · ⚡19
#machine learning Review Open access Oct 2016

“Failures” to be celebrated: an analysis of major pivots of software startups

This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.

Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al. · 127 citations · ⚡15
#machine learning Review Open access May 2016

Key Challenges in Software Startups Across Life Cycle Stages

It is found that what perceived as biggest challenges by software startups do vary across different life cycle stages, even though its significance decreases when the learning focuses of the startups move from problem to solution and their products mature.

Xiaofeng Wang, Henry Edison, Sohaib Shahid Bajwa et al. · 62 citations · ⚡6

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.