SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networks

桥接(联网) 计算机科学 人工神经网络 人工智能 计算机网络
作者
Zhenhua Huang,Kunhao Li,Shaojie Wang,Zhaohong Jia,Wentao Zhu,Sharad Mehrotra
出处
期刊:Proceedings [Institute of Electrical and Electronics Engineers]
卷期号:: 2945-2958 被引量:7
标识
DOI:10.1109/icde60146.2024.00229
摘要

Despite the Graph Neural Networks' (GNNs) pro-ficiency in analyzing graph data, achieving high-accuracy and interpretable predictions remains challenging. Existing GNN interpreters typically provide post-hoc explanations disjointed from GNNs' predictions, resulting in misrepresentations. Self-explainable GNNs offer built-in explanations during the training process. However, they cannot exploit the explanatory outcomes to augment prediction performance, and they fail to provide high-quality explanations of node features and require additional processes to generate explainable subgraphs, which is costly. To address the aforementioned limitations, we propose a self-explained and self-supervised graph neural network (SES) to bridge the gap between explainability and prediction. SES comprises two processes: explainable training and enhanced predictive learning. During explainable training, SES employs a global mask generator co-trained with a graph encoder and directly produces crucial structure and feature masks, reducing time consumption and providing node feature and subgraph explanations. In the enhanced predictive learning phase, mask-based positive-negative pairs are constructed utilizing the ex-planations to compute a triplet loss and enhance the node representations by contrastive learning. Extensive experiments demonstrate the superiority of SES on multiple datasets and tasks. SES outperforms baselines on real-world node classification datasets by notable margins of up to 2.59% and achieves state-of-the-art (SOTA) performance in explanation tasks on synthetic datasets with improvements of up to 3.0%. Moreover, SES delivers more coherent explanations on real-world datasets, has a fourfold increase in Fidelity+ score for explanation quality, and demonstrates faster training and expla-nation generating times. To our knowledge, SES is a pioneering GNN to achieve SOTA performance on both explanation and prediction tasks.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
1秒前
giant_panda发布了新的文献求助10
1秒前
1秒前
hsl完成签到 ,获得积分10
2秒前
俭朴擎汉完成签到,获得积分10
2秒前
3秒前
3秒前
Jasper的应助被危言丶采纳,获得10
3秒前
高静完成签到,获得积分10
3秒前
科研通AI6.3的应助被renn采纳,获得10
3秒前
YYQX完成签到 ,获得积分10
4秒前
陈月亮发布了新的文献求助10
5秒前
唐水之发布了新的文献求助20
5秒前
南枳完成签到 ,获得积分10
6秒前
wanci的应助被科研通管家采纳,获得10
6秒前
上官若男的应助被科研通管家采纳,获得10
6秒前
Ava的应助被科研通管家采纳,获得10
6秒前
科研通AI6.3的应助被故渊丶采纳,获得10
6秒前
丘比特的应助被科研通管家采纳,获得10
6秒前
小蘑菇的应助被科研通管家采纳,获得10
6秒前
null的应助被科研通管家采纳,获得10
6秒前
在水一方的应助被科研通管家采纳,获得10
7秒前
xxu完成签到,获得积分10
7秒前
JamesPei的应助被科研通管家采纳,获得10
7秒前
77的应助被科研通管家采纳,获得10
7秒前
1111的应助被科研通管家采纳,获得30
7秒前
Hello的应助被科研通管家采纳,获得10
7秒前
7秒前
秋风的应助被科研通管家采纳,获得20
7秒前
我要考公完成签到,获得积分10
7秒前
DW的应助被科研通管家采纳,获得10
7秒前
FashionBoy的应助被等待的语海采纳,获得10
8秒前
充电宝的应助被科研通管家采纳,获得10
8秒前
null的应助被科研通管家采纳,获得10
8秒前
Jun的应助被科研通管家采纳,获得10
8秒前
Asha发布了新的文献求助10
8秒前
drizzle发布了新的文献求助10
8秒前
李健的应助被科研通管家采纳,获得10
8秒前
Owen的应助被科研通管家采纳,获得10
8秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8184008
求助须知:如何正确求助?哪些是违规求助? 9573151
关于积分的说明 21829656
捐赠科研通 7781040
什么是DOI,文献DOI怎么找? 3434187
关于科研通互助平台的介绍 2558337
邀请新用户注册赠送积分活动 2480658