Dissecting Multiplication in Transformers: Insights into LLMs

1 code implementation • 22 Jul 2024 • Luyu Qiu, Jianing Li, Chi Su, Chen Jason Zhang, Lei Chen

This work underscores the importance of explainable AI, helping to build trust in large language models and promoting their adoption in critical applications.

XPose: eXplainable Human Pose Estimation

no code implementations • 19 Mar 2024 • Luyu Qiu, Jianing Li, Lei Wen, Chi Su, Fei Hao, Chen Jason Zhang, Lei Chen

In this paper, we propose XPose, a novel framework that incorporates Explainable AI (XAI) principles into pose estimation.

Computational Efficiency Data Augmentation +1

Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network

1 code implementation • 23 Dec 2023 • Tong Li, Jiale Deng, Yanyan Shen, Luyu Qiu, Yongxiang Huang, Caleb Chen Cao

Heterogeneous graph neural networks (HGNs) are prominent approaches to node classification tasks on heterogeneous graphs.

Graph Neural Network Node Classification

Resisting Out-of-Distribution Data Problem in Perturbation of XAI

no code implementations • 27 Jul 2021 • Luyu Qiu, Yi Yang, Caleb Chen Cao, Jing Liu, Yueyuan Zheng, Hilary Hei Ting Ngai, Janet Hsiao, Lei Chen

Besides, our solution also resolves a fundamental problem with the faithfulness indicator, a commonly used evaluation metric of XAI algorithms that appears to be sensitive to the OoD issue.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI)