activity
20242026
collaborators

5 papers

cs.LG2026

Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy Labels

Yuxin Tian, Mouxing Yang, Yuhao Zhou +5

Conventional federated learning (FL) heavily depends on high-quality labels, which are often impractical in the real world, leading to the federated label-noise (F-LN) problem. Wor…

cs.LG2025

HyperNAS: Enhancing Architecture Representation for NAS Predictor via Hypernetwork

Jindi Lv, Yuhao Zhou, Yuxin Tian +3

Time-intensive performance evaluations significantly impede progress in Neural Architecture Search (NAS). To address this, neural predictors leverage surrogate models trained on pr…

cs.LG2025

Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based Approach

Yuhao Zhou, Jindi Lv, Yuxin Tian +3

Federated Learning (FL) has emerged as a promising paradigm for privacy-preserving collaborative learning, yet data heterogeneity remains a critical challenge. While existing metho…

cs.CV2025

GPS: Distilling Compact Memories via Grid-based Patch Sampling for Efficient Online Class-Incremental Learning

Mingchuan Ma, Yuhao Zhou, Jindi Lv +5

Online class-incremental learning aims to enable models to continuously adapt to new classes with limited access to past data, while mitigating catastrophic forgetting. Replay-base…

cs.LG2024

MSD: A RG Flow-Based Regularization for GAN Training with Limited Data

Jian Wang, Xin Lan, Yuxin Tian +1

Generative adversarial networks (GANs) have made impressive advances in image generation, but they often require large-scale training data to avoid degradation caused by discrimina…