Hyper-Path-Based Representation Learning for Hyper-Networks

Huang, Jie; Liu, Xin; Song, Yangqiu

doi:10.1145/3357384.3357871

Cited by 19 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent works mainly concentrate on neural network-based scoring functions as they perform better than matrix completion-based techniques and are easier to train. Hyperpath (Huang, Liu, and Song 2019) model's hyperedge as a tuple and uses a neural network-based scoring function to predict links. This method cannot model higher-order interactions as it expects the hyperedge size to be uniform for all edges.…”

Section: Contributionsmentioning

confidence: 99%

Dynamic Representation Learning with Temporal Point Processes for Higher-Order Interaction Forecasting

Gracious

Dukkipati

2023

AAAI

View full text Add to dashboard Cite

The explosion of digital information and the growing involvement of people in social networks led to enormous research activity to develop methods that can extract meaningful information from interaction data. Commonly, interactions are represented by edges in a network or a graph, which implicitly assumes that the interactions are pairwise and static. However, real-world interactions deviate from these assumptions: (i) interactions can be multi-way, involving more than two nodes or individuals (e.g., family relationships, protein interactions), and (ii) interactions can change over a period of time (e.g., change of opinions and friendship status). While pairwise interactions have been studied in a dynamic network setting and multi-way interactions have been studied using hypergraphs in static networks, there exists no method, at present, that can predict multi-way interactions or hyperedges in dynamic settings. Existing related methods cannot answer temporal queries like what type of interaction will occur next and when it will occur. This paper proposes a temporal point process model for hyperedge prediction to address these problems. Our proposed model uses dynamic representation learning techniques for nodes in a neural point process framework to forecast hyperedges. We present several experimental results and set benchmark results. As far as our knowledge, this is the first work that uses the temporal point process to forecast hyperedges in dynamic networks.

show abstract

Section: Contributionsmentioning

confidence: 99%

Dynamic Representation Learning with Temporal Point Processes for Higher-Order Interaction Forecasting

Gracious

Dukkipati

2023

AAAI

View full text Add to dashboard Cite

show abstract

“…Link prediction on hypergraph (hyperlink prediction) has been especially popular for social networks to predict higher-order links such as a user releases a tweet containing a hashtag [21] and to predict metadata information such as tags, groups, labels, users for entities (images from Flickr) [1]. Techniques for hyperlink prediction on social networks include ranking for link proximity information [21], matrix completion on the (incomplete) incidence matrix of the hypergraph [1,28], hyperpath-based method [17], and Laplacian tensor methods for context-aware recommendation [39]. These methods are restricted to uniform hypergraphs in which each hyperlink contains the same number of vertices.…”

Section: Related Workmentioning

confidence: 99%

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

“…After maximizing the proximity, HEBE can preserve the similarity of nodes within the same hyperedge, while reduce the similarity of nodes from different hyperedges. Besides, [67] proposes hyper-path-based random walk to preserve both the structural information and indecomposability of the hyper-graphs.…”

Section: Subgraph-based Hg Embeddingmentioning

confidence: 99%

A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources

Wang¹,

Bo²,

Shi³

et al. 2020

Preprint

View full text Add to dashboard Cite

Heterogeneous graphs (HGs) also known as heterogeneous information networks have become ubiquitous in real-world scenarios; therefore, HG embedding, which aims to learn representations in a lower-dimension space while preserving the heterogeneous structures and semantics for downstream tasks (e.g., node/graph classification, node clustering, link prediction), has drawn considerable attentions in recent years. In this survey, we perform a comprehensive review of the recent development on HG embedding methods and techniques. We first introduce the basic concepts of HG and discuss the unique challenges brought by the heterogeneity for HG embedding in comparison with homogeneous graph representation learning; and then we systemically survey and categorize the state-of-the-art HG embedding methods based on the information they used in the learning process to address the challenges posed by the HG heterogeneity. In particular, for each representative HG embedding method, we provide detailed introduction and further analyze its pros and cons; meanwhile, we also explore the transformativeness and applicability of different types of HG embedding methods in the real-world industrial environments for the first time. In addition, we further present several widely deployed systems that have demonstrated the success of HG embedding techniques in resolving real-world application problems with broader impacts. To facilitate future research and applications in this area, we also summarize the open-source code, existing graph learning platforms and benchmark datasets. Finally, we explore the additional issues and challenges of HG embedding and forecast the future research directions in this field.

show abstract

Hyper-Path-Based Representation Learning for Hyper-Networks

Cited by 19 publications

References 32 publications

Dynamic Representation Learning with Temporal Point Processes for Higher-Order Interaction Forecasting

Dynamic Representation Learning with Temporal Point Processes for Higher-Order Interaction Forecasting

NHP: Neural Hypergraph Link Prediction

A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources

Contact Info

Product

Resources

About