FedCKA is proposed, a Centered Kernel Alignment (CKA)-based strategy that dynamically handles the personalization-globalization trade-off, and outperforms established federated baselines, including FedBN, FedRep, and FedSelect, improving average NDS by 7 percentage points over the strongest baseline.
Abstract
Robust perception in intelligent vehicles demands 3D object detectors that remain dependable under domain shifts, such as changes in time of day, location, or weather. However, due to costly annotation and rare shifts, some environments lack sufficient data to train a standalone detector. Federated learning offers a privacy-preserving framework for collaborative model training, enabling clients to benefit from shared learning across diverse environments. Yet, this framework traditionally relies on a single global consensus model, which struggles to perform across heterogeneous local data distributions. Local conditions are better captured by adapting a subset of the model, but many personalization approaches rely on predefined layer partitions or fixed personalization ratios, thereby limiting adaptation to client-specific divergence. To reduce this rigidity, we propose FedCKA, a Centered Kernel Alignment (CKA)-based strategy that dynamically handles the personalization-globalization trade-off. Specifically, FedCKA computes layer-wise feature similarities between local client models and the global consensus model during training. By converting layer-wise similarity scores into client-specific aggregation masks, FedCKA selectively shares representation-consistent layers. Evaluation on a unified multi-domain benchmark based on nuScenes shows that FedCKA outperforms established federated baselines, including FedBN, FedRep, and FedSelect, improving average NDS by 7 percentage points over the strongest baseline. The findings offer both a comparative benchmark and a promising direction for robust federated 3D perception across shifts in location, weather, and illumination. Code is available at https://github.com/j-verhoog/FedCKA.
Federated vision-language models (FedVLMs) represent one of the emerging frontiers of machine learning, aiming to integrate federated learning within the fine-tuning pipelines of vision-language models (VLMs). In this work, we introduce BLEND, a new framework designed to jointly enhance the personalization and generali...
Payam Abdisarabshali, Fardis Nadimi, Kasra Borazjani et al.· 0 citations
MPT is presented, a cross-vehicle FL framework that maintains rare-class recognition by reconstructing its prototype at every round from privacy-preserving class-level statistics and outperforms all baselines in rare class F1, reaching 0.516 on the nuImages dataset.
Han-Ju Jang, Gyeongmin Han, Sung-Min Lee et al.· 0 citations
Multi-scalE Temporal domAin aLignment (METAL), a novel framework that leverages temporal information at multiple resolutions to improve cross-domain video action recognition with only model parameter transfers is proposed.
The proposed Joint Domain-Class Federated Learning (JDFL), a lightweight, optimizer-agnostic extension that makes this latent domain variation usable without sharing raw data, and introduces two complementary supervision strategies based on simple intuitions.
Sina Najafi, Mostafa Tavassolipour, S. P. Shariatpanahi· arXiv.org· 0 citations
This work introduces an input-aware action matrix that weights the adapter update by the second-moment statistics of local layer inputs and proposes Federated Subspace-Guided Action-Informed Learning (FedSAIL), which improves predictive performance over competing federated LoRA methods while reducing communication cost...
A novel personalized FL framework (denoted as FedMAD) for RS image classification problems that allows the global optimization process to suppress conflicting client updates originating from heterogeneous data distributions while enhancing the contribution of clients with consistent adaptation behaviors.
Barış Büyüktaş, B. Demir· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
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.
MIT News · Artificial Intelligence· news.mit.eduNov 9, 2026