Alysa Ziying Tan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alysa Ziying Tan has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Han Yu
Nanyang technological university, Singapore, Singapore
4 shared publications Feng Wu
School of Computer Science and Technology, Soochow University, Suzhou, China
2 shared publicationsLibang Zhao
School of Computer Science and Technology, Soochow University, Suzhou, China
2 shared publications- Lizhen Cui
Shandong University
2 shared publications - Siwei Feng
Soochow University
2 shared publications - Tao Deng
School of Computer Science and Technology, Soochow University, Suzhou, China
2 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (10) , 6467-6479
Counterfactual Fairness Prediction on Missing Data
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (10) , 6467-6479
Counterfactual Fairness Prediction on Missing Data
- 24 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (12) , 22489-22503
Federated Class-Incremental Learning via Weighted Aggregation and Distillation
Federated Class-Incremental Learning (FCIL) aims to design privacy-preserving collaborative training methods to continuously learn new classes from distributed datasets. In these scenarios, federated clients face the challenge of encountering new classes while being constrained by limited memory capacity, which can lead to catastrophic forgetting in the resulting global model. Existing FCIL approaches tend to overlook the challenges posed by the heterogeneity of dataset label distribution among clients, thereby constraining the generalization capacity of the global model they learn. Some of these methods also suffer from excessive computational burdens when addressing catastrophic forgetting problems. Furthermore, certain approaches are constrained to handling only straightforward data, posing significant difficulties in managing complex datasets and tackling more intricate scenarios. In this paper, we propose the Weighted Aggregation and Distillation-based FCIL (WAD-FCIL) method to address these limitations. To address data heterogeneity arising from class imbalance, we first introduce a task-aware client clustering method to identify clients with extreme class deviations before global model aggregation to eliminate potential impact on the global model. Then, we propose a multi-sampling weighted aggregation approach during the global FL model update that integrates knowledge from different clients and dynamically adjusts the weight of each client model to facilitate model update. To mitigate catastrophic forgetting, we propose a multi-model distillation strategy that involves selecting multiple teacher models for knowledge distillation. Extensive experiments comparing WAD-FCIL with ten state-of-the-art methods demonstrate that it significantly outperforms the baselines by 0.8%~3.2% in terms of average test accuracy on three representative benchmark datasets.
- 24 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (12) , 22489-22503
Federated Class-Incremental Learning via Weighted Aggregation and Distillation
Federated Class-Incremental Learning (FCIL) aims to design privacy-preserving collaborative training methods to continuously learn new classes from distributed datasets. In these scenarios, federated clients face the challenge of encountering new classes while being constrained by limited memory capacity, which can lead to catastrophic forgetting in the resulting global model. Existing FCIL approaches tend to overlook the challenges posed by the heterogeneity of dataset label distribution among clients, thereby constraining the generalization capacity of the global model they learn. Some of these methods also suffer from excessive computational burdens when addressing catastrophic forgetting problems. Furthermore, certain approaches are constrained to handling only straightforward data, posing significant difficulties in managing complex datasets and tackling more intricate scenarios. In this paper, we propose the Weighted Aggregation and Distillation-based FCIL (WAD-FCIL) method to address these limitations. To address data heterogeneity arising from class imbalance, we first introduce a task-aware client clustering method to identify clients with extreme class deviations before global model aggregation to eliminate potential impact on the global model. Then, we propose a multi-sampling weighted aggregation approach during the global FL model update that integrates knowledge from different clients and dynamically adjusts the weight of each client model to facilitate model update. To mitigate catastrophic forgetting, we propose a multi-model distillation strategy that involves selecting multiple teacher models for knowledge distillation. Extensive experiments comparing WAD-FCIL with ten state-of-the-art methods demonstrate that it significantly outperforms the baselines by 0.8%~3.2% in terms of average test accuracy on three representative benchmark datasets.
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (20) , 33927-33939
General Federated Class-Incremental Learning With Lightweight Generative Replay
Federated class-incremental learning (FCIL) aims to allow federated learning (FL) systems to consistently learn new tasks with classes that change dynamically, without forgetting knowledge from previous classes. In FCIL scenarios, both heterogeneity in both label and data distribution across clients and catastrophic forgetting caused by continual emergence of new classes can significantly affect the performance of a FL system. Existing FCIL methods assume only changes in class distribution over time for each single client while ignoring class-specific domain distribution. Furthermore, these methods often rely on storing old class exemplars to mitigate catastrophic forgetting, potentially raising privacy concerns and computational burdens. In this article, we propose a FCIL framework called generative federated class-incremental learning (GenFCIL) that effectively addresses the aforementioned challenges. First, we introduce a lightweight generator that promotes knowledge sharing among clients and preserves the accumulated knowledge from all clients. By collecting classes and their associated data from each client, the generator effectively tackles data heterogeneity, facilitating information transfer across clients, and mitigating catastrophic forgetting in a replay-free manner. Importantly, the lightweight nature of the generator ensures that it does not impose excessive memory and computation requirements. Second, to tackle challenges from shifts in both class distribution and class-specific domain distribution in general FCIL scenarios, which may exacerbate catastrophic forgetting, we incorporate and update multiple logit scores from clients focusing on their old and new overlapping classes to incorporate more intraclass information. Experimental results show that GenFCIL effectively alleviates the impact of catastrophic forgetting and heterogeneity.
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (20) , 33927-33939
General Federated Class-Incremental Learning With Lightweight Generative Replay
Federated class-incremental learning (FCIL) aims to allow federated learning (FL) systems to consistently learn new tasks with classes that change dynamically, without forgetting knowledge from previous classes. In FCIL scenarios, both heterogeneity in both label and data distribution across clients and catastrophic forgetting caused by continual emergence of new classes can significantly affect the performance of a FL system. Existing FCIL methods assume only changes in class distribution over time for each single client while ignoring class-specific domain distribution. Furthermore, these methods often rely on storing old class exemplars to mitigate catastrophic forgetting, potentially raising privacy concerns and computational burdens. In this article, we propose a FCIL framework called generative federated class-incremental learning (GenFCIL) that effectively addresses the aforementioned challenges. First, we introduce a lightweight generator that promotes knowledge sharing among clients and preserves the accumulated knowledge from all clients. By collecting classes and their associated data from each client, the generator effectively tackles data heterogeneity, facilitating information transfer across clients, and mitigating catastrophic forgetting in a replay-free manner. Importantly, the lightweight nature of the generator ensures that it does not impose excessive memory and computation requirements. Second, to tackle challenges from shifts in both class distribution and class-specific domain distribution in general FCIL scenarios, which may exacerbate catastrophic forgetting, we incorporate and update multiple logit scores from clients focusing on their old and new overlapping classes to incorporate more intraclass information. Experimental results show that GenFCIL effectively alleviates the impact of catastrophic forgetting and heterogeneity.
- Top Cited Papers
- 28 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 34 (12) , 9587-9603
Towards Personalized Federated Learning
In parallel with the rapid adoption of artificial intelligence (AI) empowered by advances in AI research, there has been growing awareness and concerns of data privacy. Recent significant developments in the data regulation landscape have prompted a seismic shift in interest toward privacy-preserving AI. This has contributed to the popularity of Federated Learning (FL), the leading paradigm for the training of machine learning models on data silos in a privacy-preserving manner. In this survey, we explore the domain of personalized FL (PFL) to address the fundamental challenges of FL on heterogeneous data, a universal characteristic inherent in all real-world datasets. We analyze the key motivations for PFL and present a unique taxonomy of PFL techniques categorized according to the key challenges and personalization strategies in PFL. We highlight their key ideas, challenges, opportunities, and envision promising future trajectories of research toward a new PFL architectural design, realistic PFL benchmarking, and trustworthy PFL approaches.
- 28 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 34 (12) , 9587-9603
Top Cited PapersTowards Personalized Federated Learning
In parallel with the rapid adoption of artificial intelligence (AI) empowered by advances in AI research, there has been growing awareness and concerns of data privacy. Recent significant developments in the data regulation landscape have prompted a seismic shift in interest toward privacy-preserving AI. This has contributed to the popularity of Federated Learning (FL), the leading paradigm for the training of machine learning models on data silos in a privacy-preserving manner. In this survey, we explore the domain of personalized FL (PFL) to address the fundamental challenges of FL on heterogeneous data, a universal characteristic inherent in all real-world datasets. We analyze the key motivations for PFL and present a unique taxonomy of PFL techniques categorized according to the key challenges and personalization strategies in PFL. We highlight their key ideas, challenges, opportunities, and envision promising future trajectories of research toward a new PFL architectural design, realistic PFL benchmarking, and trustworthy PFL approaches.