Heterogeneous GNNs

GNN: Graph Neural Network

Overview

Heterogeneous GNNs study how to represent and make predictions from graphs whose nodes and edges have different types, such as patients and diagnoses or users and transactions. Common approaches use relation-aware message passing, attention over typed neighbors, meta-paths, temporal encodings, and contrastive or self-supervised pretraining. These models are applied to tasks including recommendation, fraud detection, biomedical prediction, and power-system analysis, with evaluation spanning both established graph benchmarks and domain-specific data. A central challenge is balancing scalable learning and transfer across graphs with preserving type-specific meaning, especially when relations are noisy, sparse, or heterophilous.

Latest papers

CardsList

87 papers7 papers in the last four weeks, down 30% on the four weeks before. 0.1% of all new papers.

  1. BiGSyn: A Bi-Level Heterogeneous Graph Contrastive Learning Framework for Interpretable Drug Synergy Prediction

    Nov 16, 2026Senquan Wang, Hui Fang, Haoran Nan +2Graph SSLHeterogeneous GNNs

  2. MT-RGCN-DTI: A Multi-Task Relational Graph Convolutional Network for Drug-Target Interaction Prediction

    Nov 15, 2026Dheeran Sankaran, R Yadunandan, Daniele Santoni +1Graph Neural NetworksHeterogeneous GNNs

  3. ProtLink: Sequence and Multispecies Graph Context for Protein Interaction Prediction

    Nov 7, 2026Xingyuan ZhangProtein-Protein Interaction PredictionHeterogeneous GNNs

  4. Interpretable Context-Aware Multi-Label Retinal Classification with Dual-Hub Heterogeneous Graph Neural Network

    Nov 6, 2026Proshanto Chanda, Munib Mesinovic, Tingting Zhu +1Retinal Disease ClassificationMultimodal Graph Learning

  5. Efficient and Scalable Multi-View Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning

    Oct 31, 2026Hao Geng, Deqing Wang, Lihao Ge +5Graph SSLMasked Autoencoders

  6. What Carries Architectural Signal? A Code-to-Architecture Mapping Study

    Oct 30, 2026Rakhshanda Jabeen, Morgan Ericsson, Yuyao Duan +1Software EngineeringGraph Representation Learning

  7. LLM-Enhanced Heterogeneous Graph Learning with Business Semantics for Financial Fraud Detection

    Oct 26, 2026Yixuan Chen, Hongyu Zhan, Jie Sheng +5Financial Fraud DetectionHeterogeneous GNNs

  8. RGH-GNN : Risk-Gated Heterogeneous Graph Neural Network for Financial Fraud Detection

    Oct 19, 2026Mythreyee Hari, Subin Sahayam, Vegesna S M SrinivasavarmaFinancial Fraud DetectionGraph Neural Networks

  9. Money-Mule Detection as a Relational Learning Problem: A Study on the RBIH NFPC Dataset

    Oct 15, 2026Owais Ahmad, Anirudh DeodharFinancial Fraud DetectionAnti-Money Laundering Detection

  10. HGRP: Heterogeneous Graph Neural Network for Routability Prediction

    Oct 14, 2026Yule Sheng, Yue Yuan, Shan Shen +1Electronic Design AutomationHeterogeneous GNNs

  11. When Does the Dependency Graph Help Code-to-Architecture Mapping?

    Oct 14, 2026Rakhshanda Jabeen, Morgan Ericsson, Jonas Nordqvist +1Software EngineeringGraph-Based Semi-Supervised Learning

  12. Shared-Roadmap Generation and Evaluator for Multi-Agent Path Planning Using Heterogeneous Graph Neural Network

    Oct 6, 2026Brandon Ho, Nikola Rogers, Seung-Kyum ChoiMulti-Agent PlanningMulti-Agent Path Finding

  13. Dual-Scale Relational Graph Transformers for Ecosystem-Aware Fraud Detection

    Oct 2, 2026Mohsen Nayebi Kerdabadi, Xinrou Li, Yao Xiao +2Financial Fraud DetectionGraph Transformer

  14. RACE: Relation-Level Counterfactual Explanations for Heterogeneous Graph Neural Networks

    Sep 29, 2026Yuxiang Yao, Zijun ZhaoGraph Counterfactual ExplanationsGNN Explainability

  15. Temporal Heterogeneous Graph Pretraining for Relational Deep Learning

    Sep 28, 2026Yixin Peng, Er Jin, Diego Collarana +1Temporal GNNsHeterogeneous GNNs

  16. Mycelium: A Generalizable Cross-Grid Multi-Task Model for Electrical Distribution Systems

    Sep 27, 2026Zhengyang Wei, Shourya Bose, Helgi Hilmarsson +2Power SystemsMulti-Task Learning

  17. Communication-Aware Heterogeneous Graph Learning for Decentralized Multi-Human Multi-Robot Task Allocation

    Sep 26, 2026Ziqin Yuan, Ruiqi Wang, Baijian Yang +1Multi-Robot Task AllocationHuman-Robot Collaboration

  18. Dynamic Heterogeneous Graph Representation Learning: A Survey

    Sep 4, 2026Huan Liu, Pengfei Jiao, Jie Yin +2Graph Representation LearningDynamic Graph Learning

  19. Beyond Similarity: Heterogeneous Graph Learning for Multi-Objective Food Substitution in Charitable Food Agencies

    Aug 22, 2026Naimur Rahman Chowdhury, Limon Bin HossainRecommender SystemsLearning to Rank

  20. FinFraudBench: A Heterogeneous Graph Benchmark for Financial Fraud Detection

    Aug 15, 2026Yixuan Chen, Hongyu Zhan, Jie Sheng +5Financial Fraud DetectionNode Classification

  21. EGRL: Edge generation-guided relation-aware learning for RNA-protein interaction prediction

    Aug 13, 2026Danyu Li, Ling Zhou, Rubing Huang +3Graph Structure LearningHeterogeneous GNNs

  22. MiGHT-EHR: A Multi-task Graph Transformer for Heterogeneous Temporal Electronic Health Records

    Aug 5, 2026Anirudh Rayas, Yuan Wang, Pavan TuragaMedication RecommendationHeterogeneous GNNs

  23. Variable-aware representation, not relation typing, explains the performance of an event-graph model for ICU mortality prediction: temporal and external validation

    Aug 1, 2026Mohammad Nasir Uddin, Eklachur Rahman Bhuiyan, Rahnuma Tabassum OrpitaHeterogeneous GNNsLongitudinal EHR Modeling

  24. TRWH: A Text-Driven Random Walk Heterogeneous GNN for Semantic-Aware Sparse Recommendation

    Jul 28, 2026He Ma, Chen LiuHeterogeneous GNNsRecommender Systems

  25. ParasGB: A Graph Benchmark Suite for Parasitic Estimation on AMS Circuits

    Jul 25, 2026Jiajun Zou, Jiawei Liu, Ao Liu +8Graph Neural NetworksHeterogeneous GNNs

  26. Canopy: A Heterograph Foundation Model for Metabolic Engineering

    Jul 7, 2026Jake Bowden, Laurence Legon, Satnam SuraeHeterogeneous GNNsGraph SSL