33 citations · 162 across the 52 of their papers we have counts for
32 papers · 1 filter
Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching
Zhuoyi Peng, Hanlin Gu, Lixin Fan +1
Text-attributed graphs (TAGs) underlie real-world applications such as citation networks, social media, and e-commerce. Few-shot graph learning on TAGs is hard: with only a handful…
GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs
Zhuoyi Peng, Jingzhou Jiang, Hanlin Gu +2
Graph analysis underlies many applications whose answers cannot be looked up in a single record or retrieved along a path: laundering rings, drug repurposing, user preference, and…
FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion
Tao Fan, Guoqiang Ma, Yuanfeng Song +3
Federated fine-tuning of Large Language Models (LLMs) is obstructed by a trilemma of challenges: protecting LLMs intellectual property (IP), ensuring client privacy, and mitigating…
FedGRPO: Privately Optimizing Foundation Models with Group-Relative Rewards from Domain Client
Gongxi Zhu, Hanlin Gu, Lixin Fan +2
One important direction of Federated Foundation Models (FedFMs) is leveraging data from small client models to enhance the performance of a large server-side foundation model. Exis…
Large-Small Model Collaborative Framework for Federated Continual Learning
Hao Yu, Xin Yang, Boyang Fan +4
Continual learning (CL) for Foundation Models (FMs) is an essential yet underexplored challenge, especially in Federated Continual Learning (FCL), where each client learns from a p…
Ten Challenging Problems in Federated Foundation Models
Tao Fan, Hanlin Gu, Xuemei Cao +30
Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of fed…
Vertical Federated Learning in Practice: The Good, the Bad, and the Ugly
Zhaomin Wu, Zhen Qin, Junyi Hou +4
Vertical Federated Learning (VFL) is a privacy-preserving collaborative learning paradigm that enables multiple parties with distinct feature sets to jointly train machine learning…
Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure
Hanlin Gu, Hong Xi Tae, Lixin Fan +1
This paper addresses the critical challenge of unlearning in Vertical Federated Learning (VFL), a setting that has received far less attention than its horizontal counterpart. Spec…
Model-based Large Language Model Customization as Service
Zhaomin Wu, Jizhou Guo, Junyi Hou +3
Prominent Large Language Model (LLM) services from providers like OpenAI and Google excel at general tasks but often underperform on domain-specific applications. Current customiza…
Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning
Jinglin Liang, Jin Zhong, Hanlin Gu +6
Federated Class Continual Learning (FCCL) merges the challenges of distributed client learning with the need for seamless adaptation to new classes without forgetting old ones. The…
A Survey on Contribution Evaluation in Vertical Federated Learning
Yue Cui, Chung-ju Huang, Yuzhu Zhang +4
Vertical Federated Learning (VFL) has emerged as a critical approach in machine learning to address privacy concerns associated with centralized data storage and processing. VFL fa…
Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
Hanlin Gu, Win Kent Ong, Chee Seng Chan +1
The advent of Federated Learning (FL) highlights the practical necessity for the right to be forgotten for all clients, allowing them to request data deletion from the machine lear…
Unlearning during Learning: An Efficient Federated Machine Unlearning Method
Hanlin Gu, Gongxi Zhu, Jie Zhang +4
In recent years, Federated Learning (FL) has garnered significant attention as a distributed machine learning paradigm. To facilitate the implementation of the right to be forgotte…
Hyperparameter Optimization for SecureBoost via Constrained Multi-Objective Federated Learning
Yan Kang, Ziyao Ren, Lixin Fan +3
SecureBoost is a tree-boosting algorithm that leverages homomorphic encryption (HE) to protect data privacy in vertical federated learning. SecureBoost and its variants have been w…
FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning
Gongxi Zhu, Donghao Li, Hanlin Gu +3
Federated Learning (FL) is a promising approach for training machine learning models on decentralized data while preserving privacy. However, privacy risks, particularly Membership…
A Theoretical Analysis of Efficiency Constrained Utility-Privacy Bi-Objective Optimization in Federated Learning
Hanlin Gu, Xinyuan Zhao, Gongxi Zhu +4
Federated learning (FL) enables multiple clients to collaboratively learn a shared model without sharing their individual data. Concerns about utility, privacy, and training effici…
Grounding Foundation Models through Federated Transfer Learning: A General Framework
Yan Kang, Tao Fan, Hanlin Gu +3
Foundation Models (FMs) such as GPT-4 encoded with vast knowledge and powerful emergent abilities have achieved remarkable success in various natural language processing and comput…
FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models
Tao Fan, Yan Kang, Guoqiang Ma +4
Large Language Models (LLMs), such as ChatGPT, LLaMA, GLM, and PaLM, have exhibited remarkable performances across various tasks in recent years. However, LLMs face two main challe…
SecureBoost Hyperparameter Tuning via Multi-Objective Federated Learning
Ziyao Ren, Yan Kang, Lixin Fan +3
SecureBoost is a tree-boosting algorithm leveraging homomorphic encryption to protect data privacy in vertical federated learning setting. It is widely used in fields such as finan…
Temporal Gradient Inversion Attacks with Robust Optimization
Bowen Li, Hanlin Gu, Ruoxin Chen +5
Federated Learning (FL) has emerged as a promising approach for collaborative model training without sharing private data. However, privacy concerns regarding information exchanged…
Probably Approximately Correct Federated Learning
Xiaojin Zhang, Anbu Huang, Lixin Fan +2
Federated learning (FL) is a new distributed learning paradigm, with privacy, utility, and efficiency as its primary pillars. Existing research indicates that it is unlikely to sim…
Optimizing Privacy, Utility and Efficiency in Constrained Multi-Objective Federated Learning
Yan Kang, Hanlin Gu, Xingxing Tang +7
Conventionally, federated learning aims to optimize a single objective, typically the utility. However, for a federated learning system to be trustworthy, it needs to simultaneousl…
A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learning
Xiaojin Zhang, Yan Kang, Lixin Fan +2
Trustworthy Federated Learning (TFL) typically leverages protection mechanisms to guarantee privacy. However, protection mechanisms inevitably introduce utility loss or efficiency…
A Game-theoretic Framework for Privacy-preserving Federated Learning
Xiaojin Zhang, Lixin Fan, Siwei Wang +3
In federated learning, benign participants aim to optimize a global model collaboratively. However, the risk of \textit{privacy leakage} cannot be ignored in the presence of \texti…