Lichao Sun

Joint Embedding of Meta-Path and Meta-Graph for Heterogeneous Information Networks

2018

Meta-graph is currently the most powerful tool for similarity search on heterogeneous information networks, where a meta-graph is a composition of meta-paths that captures the complex structural information. However, current relevance computing based on meta-graph …

Private Model Compression via Knowledge Distillation

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

The soaring demand for intelligent mobile applications calls for deploying powerful deep neural networks (DNNs) on mobile devices. However, the outstanding performance of DNNs notoriously relies on increasingly complex models, which in turn is associated …

Federated Multi-view Learning for Private Medical Data Integration and Analysis

2022 · ACM Transactions on Intelligent Systems and Technology

Along with the rapid expansion of information technology and digitalization of health data, there is an increasing concern on maintaining data privacy while garnering the benefits in the medical field. Two critical challenges are identified: …

Source Inference Attacks in Federated Learning

2021 · arXiv (Cornell University)

Federated learning (FL) has emerged as a promising privacy-aware paradigm that allows multiple clients to jointly train a model without sharing their private data. Recently, many studies have shown that FL is vulnerable to membership …

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

2022 · arXiv (Cornell University)

Detecting which nodes in graphs are outliers is a relatively new machine learning task with numerous applications. Despite the proliferation of algorithms developed in recent years for this task, there has been no standard comprehensive …

Memory-adaptive Depth-wise Heterogeneous Federated Learning

2023 · arXiv (Cornell University)

Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data. However, the presence of heterogeneous devices in federated learning, such as mobile phones and IoT …

Instructed Diffuser with Temporal Condition Guidance for Offline Reinforcement Learning

2023 · arXiv (Cornell University)

Recent works have shown the potential of diffusion models in computer vision and natural language processing. Apart from the classical supervised learning fields, diffusion models have also shown strong competitiveness in reinforcement learning (RL) by …

Attacking Neural Networks with Neural Networks: Towards Deep Synchronization for Backdoor Attacks

2023

Backdoor attacks inject poisoned samples into training data, where backdoor triggers are embedded into the model trained on the mixture of poisoned and clean samples.An interesting phenomenon can be observed in the training process: the …

Deep Efficient Private Neighbor Generation for Subgraph Federated Learning

2024 · Society for Industrial and Applied Mathematics eBooks

Behemoth graphs are often fragmented and separately stored by multiple data owners as distributed subgraphs in many realistic applications. Without harming data privacy, it is natural to consider the subgraph federated learning (subgraph FL) scenario, …

Variational Bayes for Federated Continual Learning

2024 · arXiv (Cornell University)

Federated continual learning (FCL) has received increasing attention due to its potential in handling real-world streaming data, characterized by evolving data distributions and varying client classes over time. The constraints of storage limitations and privacy …

1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have garnered significant attention due to their remarkable ability to process information across various languages. Despite their capabilities, they exhibit inconsistencies in handling identical queries in different languages, presenting challenges for …

Towards Stable and Explainable Attention Mechanisms

2025 · IEEE Transactions on Knowledge and Data Engineering

Currently, attention mechanism has become a standard fixture in most state-of-the-art natural language processing (NLP) models, not only due to the outstanding performance it could gain but also due to plausible innate explanations for the …

<scp>MetaAgents:</scp> Large Language Model Based Agents for Decision-Making on Teaming

2025 · Proceedings of the ACM on Human-Computer Interaction

Significant advancements have occurred in the application of Large Language Models (LLMs) for social simulations. Despite this, their abilities to perform teaming in task-oriented social events are underexplored. Such capabilities are crucial if LLMs are …