Hypergraph Neural Networks

Feng, Yifan; You, Haoxuan; Zhang, Zizhao; Ji, Rongrong; Gao, Yue

doi:10.1609/aaai.v33i01.33013558

Cited by 988 publications

(570 citation statements)

References 2 publications

Supporting

Mentioning

569

Contrasting

Order By: Relevance

“…The category of using hypergraphs without modification includes star expansion [3] that connects each node in a hyperedge to a new node that represents a hyperedge. There are works that directly use hypergraphs with the idea of two resilient distributed datasets (RDDs) [20] and deep learning approaches [13,47]. Representation in hyperedge prediction.…”

Section: Related Workmentioning

confidence: 99%

How Much and When Do We Need Higher-order Information in Hypergraphs? A Case Study on Hyperedge Prediction

Yoon¹,

Song²,

Shin³

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

Hypergraphs provide a natural way of representing group relations, whose complexity motivates an extensive array of prior work to adopt some form of abstraction and simplification of higher-order interactions. However, the following question has yet to be addressed: How much abstraction of group interactions is sufficient in solving a hypergraph task, and how different such results become across datasets? This question, if properly answered, provides a useful engineering guideline on how to trade off between complexity and accuracy of solving a downstream task. To this end, we propose a method of incrementally representing group interactions using a notion of n-projected graph whose accumulation contains information on up to n-way interactions, and quantify the accuracy of solving a task as n grows for various datasets. As a downstream task, we consider hyperedge prediction, an extension of link prediction, which is a canonical task for evaluating graph models. Through experiments on 15 real-world datasets, we draw the following messages: (a) Diminishing returns: small n is enough to achieve accuracy comparable with near-perfect approximations, (b) Troubleshooter: as the task becomes more challenging, larger n brings more benefit, and (c) Irreducibility: datasets whose pairwise interactions do not tell much about higher-order interactions lose much accuracy when reduced to pairwise abstractions. CCS CONCEPTS• Information systems → Data mining.

show abstract

Section: Related Workmentioning

confidence: 99%

How Much and When Do We Need Higher-order Information in Hypergraphs? A Case Study on Hyperedge Prediction

Yoon¹,

Song²,

Shin³

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

show abstract

“…while vertices still map to systems. For brevity, we note that the methods proposed for hypergraphs [2], [33], [31], [32] are similar to those proposed for graphs, and the above discussion applies here as well. In this case we can perform classification or regression tasks to find, for instance, the probability that a subnet has been infected by malware, or the exploitability score of a specific library given the hypergraph topology and features of the systems within the hyperedge (using the library).…”

Section: B Level Ii: the Cloud: Network And Malware Pathsmentioning

confidence: 91%

Towards Deep Federated Defenses Against Malware in Cloud Ecosystems

Payne

Kundu

2019

2019 First IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)

View full text Add to dashboard Cite

In cloud computing environments with many virtual machines, containers, and other systems, an epidemic of malware can be highly threatening to business processes. In this vision paper, we introduce a hierarchical approach to performing malware detection and analysis using several recent advances in machine learning on graphs, hypergraphs, and natural language. We analyze individual systems and their logs, inspecting and understanding their behavior with attentional sequence models. Given a feature representation of each system's logs using this procedure, we construct an attributed network of the cloud with systems and other components as vertices and propose an analysis of malware with inductive graph and hypergraph learning models. With this foundation, we consider the multicloud case, in which multiple clouds with differing privacy requirements cooperate against the spread of malware, proposing the use of federated learning to perform inference and training while preserving privacy. Finally, we discuss several open problems that remain in defending cloud computing environments against malware related to designing robust ecosystems, identifying cloud-specific optimization problems for response strategy, action spaces for malware containment and eradication, and developing priors and transfer learning tasks for machine learning models in this area.

show abstract

“…The reader is referred to a comprehensive literature review [5] and extensive surveys [3,16,37] on this topic of deep learning on graphs. Recently, GCNs have been extended to hypergraphs [10,38]. Below, we give an overview of related research in link prediction on hypergraphs where relationships go beyond pairwise.…”

Section: Related Workmentioning

confidence: 99%

“…vertices. This challenge is typically handled by approximating the hypergraph by its clique expansion in which pairwise edges are introduced between all vertex pairs in the hyperlink [4,10]. Because of the pairwise connections, each hyperlink may not be considered as a unit (in which vertex connections go beyond pairwise).…”

Section: Nhp-umentioning

confidence: 99%

“…We used DBLP 2 for co-authorship data. We used a dataset → iAF1260b iJO1366 USPTO model ↓ AUC Recall@k AUC Recall@k AUC Recall@k HGNN [10] 0.62 ± 0.02 0.27 ± 0.04 0.61 ± 0.03 0.32 ± 0.02 0.69 ± 0.02 0.26 ± 0.01 HyperGCN [38] 0.62 ± 0.02 0.28 ± 0.02 0.60 ± 0.02 0.32 ± 0.02 0.70 ± 0.03 0.29 ± 0.03 Hyper-SAGNN [43] Table 5: Mean (± std) Recall@k values on the DBLP dataset. NA: not applicable.…”

Section: Collaborations In a Co-authorship Networkmentioning

confidence: 99%

See 1 more Smart Citation

NHP: Neural Hypergraph Link Prediction

Yadati

Ray

Nimishakavi

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Link prediction in simple graphs is a fundamental problem in which new links between vertices are predicted based on the observed structure of the graph. However, in many real-world applications, there is need to model relationships among vertices which go beyond pairwise associations. For example, in a chemical reaction, relationship among the reactants and products is inherently higherorder. Additionally, there is need to represent the direction from reactants to products. Hypergraphs provide a natural way to represent such complex higher-order relationships. Graph Convolutional Networks (GCN) have recently emerged as a powerful deep learning-based approach for link prediction over simple graphs. However, their suitability for link prediction in hypergraphs is underexplored-we fill this gap in this paper and propose Neural Hyperlink Predictor (NHP). NHP adapts GCNs for link prediction in hypergraphs. We propose two variants of NHP-NHP-U and NHP-D-for link prediction over undirected and directed hypergraphs, respectively. To the best of our knowledge, NHP-D is the first ever method for link prediction over directed hypergraphs. An important feature of NHP is that it can also be used for hyperlinks in which dissimilar vertices interact (e.g. acids reacting with bases). Another attractive feature of NHP is that it can be used to predict unseen hyperlinks at test time (inductive hyperlink prediction). Through extensive experiments on multiple real-world datasets, we show NHP's effectiveness. CCS CONCEPTS • Computing methodologies → Neural networks; Unsupervised learning.

show abstract

Hypergraph Neural Networks

Cited by 988 publications

References 2 publications

How Much and When Do We Need Higher-order Information in Hypergraphs? A Case Study on Hyperedge Prediction

How Much and When Do We Need Higher-order Information in Hypergraphs? A Case Study on Hyperedge Prediction

Towards Deep Federated Defenses Against Malware in Cloud Ecosystems

NHP: Neural Hypergraph Link Prediction

Contact Info

Product

Resources

About