Going beyond xai: A systematic survey for explanation-guided learning

Y Gao, S Gu, J Jiang, SR Hong, D Yu, L Zhao - ACM Computing Surveys, 2024 - dl.acm.org
As the societal impact of Deep Neural Networks (DNNs) grows, the goals for advancing
DNNs become more complex and diverse, ranging from improving a conventional model …

Due: Dynamic uncertainty-aware explanation supervision via 3d imputation

Q Zhao, Y Zhang, M Zhu, S Gu, Y Gao, X Yang… - Proceedings of the 30th …, 2024 - dl.acm.org
Explanation supervision aims to enhance deep learning models by integrating additional
signals to guide the generation of model explanations, showcasing notable improvements in …

MEGL: Multimodal Explanation-Guided Learning

Y Zhang, T Jiang, B Pan, J Wang, G Bai… - arXiv preprint arXiv …, 2024 - arxiv.org
Explaining the decision-making processes of Artificial Intelligence (AI) models is crucial for
addressing their" black box" nature, particularly in tasks like image classification. Traditional …

Helper Recommendation with seniority control in Online Health Community

J Gao, C Ling, C Yang, L Zhao - Proceedings of the 2024 SIAM International …, 2024 - SIAM
Online health communities (OHCs) provide an essential platform for patients with similar
health conditions to share experiences and offer moral support. However, many time …

STES: A Spatiotemporal Explanation Supervision Framework

D Yu, B Chen, Y Li, S Dhakal, Y Zhang, Z Liu… - Proceedings of the 2024 …, 2024 - SIAM
Explanation supervision is a technique that guides a deep learning model to have correct
attention during training and thus improve both the interpretability and predictability of the …

Low-cost Enhancer for Text Attributed Graph Learning via Graph Alignment

L Hu, H Xie, L Yu, T Huang, L Li, M Li, JUN ZHOU… - openreview.net
Many graphs can be represented as Text-attributed Graphs (TAGs). Due to the rich textual
information present in each node of TAGs, traditional graph neural networks (GNNs) often …