Knowledge-Embedded Hypergraph Neural Networks

超图 计算机科学 判别式 编码器 人工神经网络 人工智能 顶点(图论) 特征提取 桥接(联网) 模式识别(心理学) 自编码 数据挖掘 编码(内存) 特征(语言学) 知识库 理论计算机科学 机器学习 知识获取 决策树 知识抽取 编码 上下文图像分类 可视化 钥匙(锁) 树形结构
作者
Yifan Feng,Yifan Zhang,Shaoyi Du,Shihui Ying,Zongze Wu,Yue Gao
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:48 (7): 8613-8625 被引量:1
标识
DOI:10.1109/tpami.2026.3674800
摘要

Hypergraph Neural Networks (HGNNs) enhance graph-based modeling by representing complex relationships, with applications in brain network analysis, recommendation systems, and computer vision. However, conventional HGNNs often struggle with effective knowledge extraction and discriminative feature representation, leading to performance limitations. This paper presents Knowledge-Embedded Hypergraph Neural Networks (Knowledge HGNN), a framework that addresses these challenges with two complementary encoders and a multi-dimensional fusion strategy. The High-Order Incidence Encoder (HOI-Encoder) explicitly embeds structural knowledge by capturing permutation-invariant high-order incidence patterns that are typically overlooked by standard HGNNs. In contrast, the Task-Driven Rule Encoder (TDR-Encoder) focuses on feature-level knowledge, extracting task-related rules from vertex attributes through gradient boosted decision tree pre-training and encoding both rule content and positional importance. A Multi-Dimensional Knowledge Fusion module then integrates structural and rule-based embeddings, bridging semantic and dimensional gaps to form enriched vertex representations. The framework includes two implementations: Rule-Driven HGNN, which emphasizes rule-based knowledge, and Dual-Driven HGNN, which jointly leverages structural and rule-based knowledge for comprehensive feature extraction. Extensive experiments on ten datasets, together with ablation studies, demonstrate that Knowledge HGNN significantly improves performance, achieving a 7.3% gain on the Cora dataset and an average improvement of 2.5% across all datasets. These results highlight the effectiveness of explicitly differentiating and fusing structural and rule-based knowledge, setting a new standard for hypergraph applications in complex, data-driven scenarios.
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
vc的应助被冷静的牛青采纳,获得30
刚刚
loquatautumn完成签到 ,获得积分10
刚刚
万万没想到完成签到,获得积分10
1秒前
gong发布了新的文献求助10
1秒前
北徫发布了新的文献求助10
1秒前
哎哟可爱发布了新的文献求助10
2秒前
剑过无声发布了新的文献求助10
3秒前
柯柯完成签到,获得积分10
3秒前
4秒前
4秒前
4秒前
传奇3的应助被溜溜吧采纳,获得10
4秒前
明理含之发布了新的文献求助10
5秒前
6秒前
6秒前
隐形曼青的应助被Katze采纳,获得10
6秒前
6秒前
口农完成签到,获得积分10
6秒前
猴子的应助被深情雅柔采纳,获得10
7秒前
duanzou发布了新的文献求助10
7秒前
9秒前
9秒前
pass发布了新的文献求助15
9秒前
wcychengyou完成签到,获得积分10
9秒前
9秒前
9秒前
完美世界的应助被涤宇采纳,获得10
10秒前
aaaaa发布了新的文献求助10
11秒前
zqy发布了新的文献求助10
11秒前
从容的发布了新的文献求助10
11秒前
溜溜心儿发布了新的文献求助10
11秒前
积极老四完成签到,获得积分10
12秒前
lmg完成签到,获得积分10
14秒前
15秒前
ghr777完成签到 ,获得积分10
15秒前
15秒前
123完成签到,获得积分20
15秒前
huanhuan发布了新的文献求助10
16秒前
SciGPT的应助被董晴采纳,获得10
16秒前
16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 8183204
求助须知:如何正确求助?哪些是违规求助? 9572434
关于积分的说明 21825655
捐赠科研通 7779988
什么是DOI,文献DOI怎么找? 3433852
关于科研通互助平台的介绍 2558060
邀请新用户注册赠送积分活动 2480148