Causal Subgraph Learning for Generalizable Inductive Relation Prediction

关系(数据库) 计算机科学 机器学习 人工智能 归纳推理 归纳偏置 归纳逻辑编程 多任务学习 数据挖掘 工程类 任务(项目管理) 系统工程
作者
Li Mei,Xiaoguang Liu,Hua Ji,Shuangjia Zheng
标识
DOI:10.1145/3637528.3671972
摘要

Inductive relation reasoning in knowledge graphs aims at predicting missing triplets involving unseen entities and/or unseen relations. While subgraph-based methods that reason about the local structure surrounding a candidate triplet have shown promise, they often fall short in accurately modeling the causal dependence between a triplet's subgraph and its ground-truth label. This limitation typically results in a susceptibility to spurious correlations caused by confounders, adversely affecting generalization capabilities. Herein, we introduce a novel front-door adjustment-based approach designed to learn the causal relationship between subgraphs and their ground-truth labels, specifically for inductive relation prediction. We conceptualize the semantic information of subgraphs as a mediator and employ a graph data augmentation mechanism to create augmented subgraphs. Furthermore, we integrate a fusion module and a decoder within the front-door adjustment framework, enabling the estimation of the mediator's combination with augmented subgraphs. We also introduce the reparameterization trick in the fusion model to enhance model robustness. Extensive experiments on widely recognized benchmark datasets demonstrate the proposed method's superiority in inductive relation prediction, particularly for tasks involving unseen entities and unseen relations. Additionally, the subgraphs reconstructed by our decoder offer valuable insights into the model's decision-making process, enhancing transparency and interpretability.

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

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
失眠的沛春完成签到,获得积分10
刚刚
星辰大海应助Chloe采纳,获得10
刚刚
BX发布了新的文献求助10
刚刚
WYJie完成签到,获得积分10
1秒前
许子健发布了新的文献求助10
1秒前
xiaozhejia完成签到,获得积分10
1秒前
kkk完成签到,获得积分10
1秒前
1秒前
Ll完成签到,获得积分10
1秒前
爆米花应助xmy采纳,获得10
2秒前
2秒前
程之杭发布了新的文献求助10
2秒前
kmmu0611完成签到 ,获得积分10
3秒前
3秒前
reck应助taster采纳,获得10
3秒前
华仔应助taster采纳,获得10
3秒前
3秒前
幼儿园大大班完成签到,获得积分10
3秒前
汪小楠吖完成签到,获得积分20
4秒前
zerozero发布了新的文献求助10
4秒前
一一完成签到 ,获得积分10
5秒前
小郭完成签到,获得积分10
5秒前
jianjiao完成签到,获得积分10
5秒前
6秒前
斯文败类应助大气丹雪采纳,获得10
6秒前
NexusExplorer应助luvletter采纳,获得10
6秒前
烟花应助程之杭采纳,获得10
7秒前
7秒前
BX完成签到,获得积分10
8秒前
八二年葡萄糖完成签到 ,获得积分10
8秒前
汪小楠吖发布了新的文献求助10
8秒前
8秒前
8秒前
刘闹闹完成签到 ,获得积分10
9秒前
9秒前
CRANE完成签到 ,获得积分10
10秒前
松松包完成签到,获得积分10
11秒前
斯文败类应助liuting采纳,获得20
11秒前
在水一方应助Vera采纳,获得10
11秒前
吴书维完成签到,获得积分10
12秒前
高分求助中
The late Devonian Standard Conodont Zonation 2000
Nickel superalloy market size, share, growth, trends, and forecast 2023-2030 2000
The Lali Section: An Excellent Reference Section for Upper - Devonian in South China 1500
Smart but Scattered: The Revolutionary Executive Skills Approach to Helping Kids Reach Their Potential (第二版) 1000
Very-high-order BVD Schemes Using β-variable THINC Method 850
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 800
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 800
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3249002
求助须知:如何正确求助?哪些是违规求助? 2892380
关于积分的说明 8271185
捐赠科研通 2560658
什么是DOI,文献DOI怎么找? 1389175
科研通“疑难数据库(出版商)”最低求助积分说明 651006
邀请新用户注册赠送积分活动 627869