Yichen Li

Yichen Li


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 August 2024 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
YLYichen Li
Yichen Li
WXWenchao Xu
Wenchao Xu
YQYining Qi
Yining Qi
Haozhao WangHaozhao Wang
Haozhao Wang
Ruixuan LiRuixuan Li
Ruixuan Li
SGSong Guo
Song Guo
Federated Learning (FL) is to allow multiple clients to collaboratively train a model while keeping their data locally. However, existing FL approaches typically assume that the data in each client is static and fixed, which cannot account for incremental data with domain shift, leading to catastrophic forgetting on previous domains, particularly when clients are common edge devices that may lack enough storage to retain full samples of each domain. To tackle this challenge, we propose Federated Domain-Incremental Learning via Synergistic Replay (SR-FDIL), which alleviates catastrophic forgetting by coordinating all clients to cache samples and replay them. More specifically, when new data arrives, each client selects the cached samples based not only on their importance in the local dataset but also on their correlation with the global dataset. Moreover, to achieve a balance between learning new data and memorizing old data, we propose a novel client selection mechanism by jointly considering the importance of both old and new data. We conducted extensive experiments on several datasets of which the results demonstrate that SR-FDIL outperforms state-of-theart methods by up to 4.05% in terms of average accuracy of all domains.

9 May 2025 in IEEE Communications Surveys & Tutorials
Verified
Journal Article
Closed access
YLYichen Li
Yichen Li
Haozhao WangHaozhao Wang
Haozhao Wang
WXWenchao Xu
Wenchao Xu
TXTianzhe Xiao
Tianzhe Xiao
HLHong Liu
Hong Liu
Ruixuan LiRuixuan Li
Ruixuan Li
Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high reliability and scalability in deploying this paradigm in distributed systems, it is essential to overcome challenges stemming from both spatial and temporal dimensions, manifesting as distribution shifts, catastrophic forgetting, heterogeneity, and privacy issues. This survey focuses on a comprehensive examination of the development of the non-centralized continual learning algorithms and the real-world deployment across distributed devices. We begin with an introduction to the background and fundamentals of non-centralized learning and continual learning. Then, we review existing solutions from three levels to represent how existing techniques alleviate the catastrophic forgetting and distribution shift. Additionally, we delve into the various types of heterogeneity issues, security, and privacy attributes, as well as real-world applications across three prevalent scenarios. Furthermore, we establish a large-scale benchmark to revisit this problem and analyze the performance of the state-of-the-art NCCL approaches. Finally, we discuss the important challenges and future research directions in NCCL.

17 March 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YLYichen Li
Yichen Li
Haozhao WangHaozhao Wang
Haozhao Wang
YQYining Qi
Yining Qi
WLWei Liu
Wei Liu
Ruixuan LiRuixuan Li
Ruixuan Li
Federated learning (FL) has emerged as a significant distributed machine learning paradigm. It allows the training of a global model through user collaboration without the necessity of sharing their original data. Traditional FL generally assumes that each client’s data remains fixed or static. However, in real-world scenarios, data typically arrives incrementally, leading to a dynamically expanding data domain. In this study, we examine catastrophic forgetting within Federated Incremental Learning (FIL) and focus on the training resources, where edge clients may not have sufficient storage to keep all data or computational budget to implement complex algorithms designed for the server-based environment. We propose a general and low-cost framework for FIL named Re-Fed+, which is designed to help clients cache important samples for replay. Specifically, when a new task arrives, each client initially caches selected previous samples based on their global and local significance. The client then trains the local model using both the cached samples and the new task samples. From a theoretical perspective, we analyze how effectively Re-Fed+ can identify significant samples for replay to alleviate the catastrophic forgetting issue. Empirically, we show that Re-Fed+ achieves competitive performance compared to state-of-the-art methods.

22 April 2025
Verified
Conference Paper
Open access
YLYichen Li
Yichen Li
YSYijing Shan
Yijing Shan
YLYi Liu
Yi Liu
Haozhao WangHaozhao Wang
Haozhao Wang
WWWei Wang
Wei Wang
Ruixuan LiRuixuan Li
Ruixuan Li


19 January 2025 in Journal of Software: Evolution and Process
Verified
Journal Article
Closed access
YWYuying Wang
Yuying Wang
YLYichen Li
Yichen Li
HWHaozhao Wang
Haozhao Wang
LZLei Zhao
Lei Zhao
XZXiaofang Zhang
Xiaofang Zhang