Papers with hypergraph neural networks

3 papers
HyperIDP: Customizing Temporal Hypergraph Neural Networks for Multi-Scale Information Diffusion Prediction (2025.coling-main)

Copied to clipboard

Challenge: Existing studies on information diffusion prediction have focused on both macroscopic and microscopic scales.
Approach: They propose a hypergraph-based model that manages both macroscopic and microscopic diffusion predictions.
Outcome: The proposed model outperforms baseline models on both macroscopic and microscopic tasks.
Hypergraph-Based Session Modeling: A Multi-Collaborative Self-Supervised Approach for Enhanced Recommender Systems (2024.lrec-main)

Copied to clipboard

Challenge: Presently, graph-based recommendations are limited by session dependencies and data sparsity in real-world scenarios.
Approach: They propose a method which uses multi-collaborative self-supervised learning in hypergraph neural networks to model item transitions and to mitigate the challenges of data sparsity.
Outcome: The proposed method outperforms existing methods in a number of domains and consistently outperformed existing methods.
HGAdapter: Hypergraph-based Adapters in Language Models for Code Summarization and Clone Detection (2025.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) are increasingly being applied to code-related tasks.
Approach: They propose a hypergraph-based adapter to capture high-order data correlations in code tokens . they improve hypergraph neural networks and combine it with adapter tuning to propose adapter .
Outcome: The proposed adapter can encode high-order data correlations and be inserted into PLMs to enhance performance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations