Progress in graph neural networks has grown rapidly in recent years, with many new developments in drug discovery, medical diagnosis, and recommender systems. While this progress is significant, many networks are `black boxes' with little understanding of the `what' exactly the network is learning. Many high-stakes applications, such as drug discovery, require human-intelligible explanations from the models so that users can recognize errors and discover new knowledge. Therefore, the development of explainable AI algorithms is essential for us to reap the benefits of AI.
We propose an explainability algorithm for GNNs called eXplainable Insight (XInsight) that generates a distribution of model explanations using GFlowNets. Since GFlowNets generate objects with probabilities proportional to a reward, XInsight can generate a diverse set of explanations, compared to previous methods that only learn the maximum reward sample. We demonstrate XInsight by generating explanations for GNNs trained on two graph classification tasks: classifying mutagenic compounds with the MUTAG dataset and classifying acyclic graphs with a synthetic dataset that we have open-sourced. We show the utility of XInsight's explanations by analyzing the generated compounds using QSAR modeling, and we find that XInsight generates compounds that cluster by lipophilicity, a known correlate of mutagenicity. Our results show that XInsight generates a distribution of explanations that uncovers the underlying relationships demonstrated by the model. They also highlight the importance of generating a diverse set of explanations, as it enables us to discover hidden relationships in the model and provides valuable guidance for further analysis.
GLaDiGAtor: Language-Model-Augmented Multi-Relation Graph Learning for Predicting Disease-Gene Associations
Biological Data Science Lab, Dept. of Computer Engineering, Hacettepe University（生物数据科学实验室，计算机工程系，哈切泰佩大学）；Dept. of Bioinformatics, Graduate School of Health Sciences, Hacettepe University（生物信息学系，健康科学研究生院，哈切泰佩大学）；Dept. of Health Informatics, Institute of Informatics, Hacettepe University（健康信息学系，信息学院，哈切泰佩大学）
Protein Secondary Structure Prediction Using 3D Graphs and Relation-Aware Message Passing Transformers
Banaras Hindu University, Varanasi, India（班纳拉锡大学）；Indiana University, Bloomington（印第安纳大学）；Indian Institute of Technology Jodhpur, India（印度理工学院朱罗尔分校）；Indian Institute of Technology Patna, India（印度理工学院帕坦分校）
CryptoFlowBench: Benchmarking Multi-Hop Reasoning on Blockchains for Cryptocurrency Fund Tracing
State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全全国重点实验室）；Hangzhou City University（杭州城市学院）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术开发区（滨江）区块链与数据安全研究院）；China Mobile Group Zhejiang Co., Ltd（中国移动通信集团浙江有限公司）；China Unicom Digital Technology Co., Ltd（中国联通数字科技有限公司）
Unraveling Privacy Risks of Individual Fairness in Graph Neural Networks
Faculty of IT Monash University（莫纳什大学信息技术学院）；School of CIS The University of Melbourne（墨尔本大学计算机与信息系统学院）；School of ICT Griffith University（格里菲斯大学信息与通信技术学院）
Cooperative Network Learning for Large-Scale and Decentralized Graphs
Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China（电子科技大学基础与前沿研究院）；Yangtze Delta Region Institute (Huzhou), University of Electronic Science and Technology of China（电子科技大学长三角研究院（湖州））；School of Cyber Science and Technology, University of Science and Technology of China（中国科学技术大学网络空间安全学院）
Crossfire: An Elastic Defense Framework for Graph Neural Networks Under Bit Flip Attacks
Faculty of Computer Science, University of Vienna（维也纳大学计算机学院）；Doctoral School Computer Science, University of Vienna（维也纳大学计算机博士学院）；Research Network Data Science University of Vienna（维也纳大学数据科学研究网络）
Graph Neural Network based Hierarchy-Aware Embeddings of Knowledge Graphs: Applications to Yeast Phenotype Prediction
Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg（计算机科学与工程系，查尔姆斯理工大学和哥德堡大学）；Department of Life Sciences, Chalmers University of Technology（生命科学系，查尔姆斯理工大学）；Department of Industrial Biotechnology, KTH Royal Institute of Technology（工业生物技术系，皇家理工学院）；Department of Chemical Engineering and Biotechnology, University of Cambridge（化学工程与生物技术系，剑桥大学）
Interpretable High-order Knowledge Graph Neural Network for Predicting Synthetic Lethality in Human Cancers
Guangdong University of Technology（广东工业大学）；Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；ShanghaiTech University（上海科技大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程技术研究中心）；A*STAR（新加坡科技研究局）
FIGNN: Feature-Specific Interpretability for Graph Neural Network Surrogate Models
Department of Mechanical Engineering, Pennsylvania State University, University Park, 16802, PA, USA（宾夕法尼亚州立大学机械工程系）；College of Information Sciences and Technology, Pennsylvania State University, University Park, 16802, PA, USA（宾夕法尼亚州立大学信息科学与技术学院）；Power Systems Division, Argonne National Laboratory, Lemont, 60439, IL, USA（阿贡国家实验室电力系统分部）
The Bredesen Center, University of Tennessee, Knoxville, TN 37996, USA（田纳西大学布雷德森中心）；Department of Mathematics, Kennesaw State University, Kennesaw, GA 30144, USA（凯尼恩州立大学数学系）；Department of Pharmaceutical Sciences, University of Kentucky, Lexington, KY 40506, USA（肯塔基大学药学系）；Department of Mathematics, University of Tennessee, Knoxville, TN 37996, USA（田纳西大学数学系）
