Haiyang Yu

On Explainability of Graph Neural Networks via Subgraph Explorations

2021 · arXiv (Cornell University)

We consider the problem of explaining the predictions of graph neural networks (GNNs), which otherwise are considered as black boxes. Existing methods invariably focus on explaining the importance of graph nodes or edges but ignore …

SVFLC: Secure and Verifiable Federated Learning With Chain Aggregation

2023 · IEEE Internet of Things Journal

As many countries have promulgated laws to protect users’ data privacy, how to legally use users’ data has become a hot topic. With the emergence of federated learning (FL) (also known as collaborative learning), multiple …

USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task

2024

Cross-lingual semantic textual relatedness task is an important research task that addresses challenges in cross-lingual communication and text understanding.It helps establish semantic connections between different languages, crucial for downstream tasks like machine translation, multilingual information …

Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement

2024 · arXiv (Cornell University)

Merging Large Language Models (LLMs) aims to amalgamate multiple homologous LLMs into one with all the capabilities. Ideally, any LLMs sharing the same backbone should be mergeable, irrespective of whether they are Fine-Tuned (FT) with …

Investigating the Effects of Self-Focus in Competitive Learning Environments: A Study for High School Students

2024 · Korean Journal of Youth Studies

본 연구는 자기집중, 탄력성, 능력기반 사회비교경향성, 부정적 학업자아상, 주관적 안녕감 간의 구조적 관계를 검증하는 것을 목적으로 하였다. 일반계 고등학교 2학년 학생 273명(여학생 121명, 남학생 152명)을 대상으로 설문조사를 실시하였으며 구조모형방정식을 사용하여 제안된 연구모형을 검증하였다. 연구결과, 자기집중은 …