Hyperedge Prediction
9 papers with code • 0 benchmarks • 0 datasets
Hyperlink/hyperedge prediction, targets to find missing hyperedges in a hypergraph.
Benchmarks
These leaderboards are used to track progress in Hyperedge Prediction
Most implemented papers
Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs
We present a generalization of Transformers to any-order permutation invariant data (sets, graphs, and hypergraphs).
Hyperedge Prediction using Tensor Eigenvalue Decomposition
This is further used to propose a hyperedge prediction algorithm.
Inference of hyperedges and overlapping communities in hypergraphs
Hypergraphs, encoding structured interactions among any number of system units, have recently proven a successful tool to describe many real-world biological and social networks.
AHP: Learning to Negative Sample for Hyperedge Prediction
Since it is prohibitive to use all of them as negative examples for model training, it is inevitable to sample a very small portion of them, and to this end, heuristic sampling schemes have been employed.
CAT-Walk: Inductive Hypergraph Learning via Set Walks
ubc-systopia/CATWalk
•
•
NeurIPS 2023
Our evaluation on 10 hypergraph benchmark datasets shows that CAT-Walk attains outstanding performance on temporal hyperedge prediction benchmarks in both inductive and transductive settings.
Enhancing Hyperedge Prediction with Context-Aware Self-Supervised Learning
yy-ko/cash
•
•
To tackle both challenges together, in this paper, we propose a novel hyperedge prediction framework (CASH) that employs (1) context-aware node aggregation to precisely capture complex relations among nodes in each hyperedge for (C1) and (2) self-supervised contrastive learning in the context of hyperedge prediction to enhance hypergraph representations for (C2).
Unified Pretraining for Recommendation via Task Hypergraphs
mdyfrank/uprth
•
•
On the other hand, pretraining and finetuning on the same dataset leads to a high risk of overfitting.
Hypergraphs with node attributes: structure and inference
Many networked datasets with units interacting in groups of two or more, encoded with hypergraphs, are accompanied by extra information about nodes, such as the role of an individual in a workplace.
Interpretable Subgraph Feature Extraction for Hyperlink Prediction
KXDY233/SSF
•
•
ICDM 2023
In this study, we present SSF, an innovative hyperlink prediction methodology based on Subgraph Structural Features.
