Graph Neural Network

Graph Neural Networks (GNNs) are a class of machine learning models designed to analyze and learn from data represented as graphs, focusing on capturing relationships between nodes and their impact on downstream tasks like node classification and link prediction. Current research emphasizes improving GNN performance by addressing limitations such as oversmoothing and oversquashing through architectural innovations (e.g., incorporating residual connections, Cayley graph propagation) and novel training techniques (e.g., contrastive learning, Laplacian regularization). GNNs are proving valuable across diverse fields, including social network analysis, drug discovery, and financial modeling, offering powerful tools for analyzing complex relational data where traditional methods fall short.

Papers

September 12, 2024

September 11, 2024

Learning Personalized Scoping for Graph Neural Networks under Heterophily
Gangda Deng, Hongkuan Zhou, Rajgopal Kannan, Viktor Prasanna
Graph Neural Network Heterophilic Graph Depth Network Node Similarity GNN Inference

September 10, 2024

September 9, 2024

Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting
Lirong Wu, Haitao Lin, Guojiang Zhao, Cheng Tan, Stan Z. Li
LeArning Abstract Graph Neural Network Graph Convolution Graph Structure Node Representation Multi Layer Perceptron Training Graph

September 8, 2024

September 7, 2024

Up-sampling-only and Adaptive Mesh-based GNN for Simulating Physical Systems
Fu Lin, Jiasheng Shi, Shijie Luo, Qinpei Zhao, Weixiong Rao, Lei Chen
Graph Neural Network Physical Simulation Complex Physical System

September 6, 2024

CUQ-GNN: Committee-based Graph Uncertainty Quantification using Posterior Networks
Clemens Damke, Eyke Hüllermeier
Graph Neural Network Predictive Uncertainty Uncertainty Aware Graph Posterior Network

September 5, 2024

Characterizing Massive Activations of Attention Mechanism in Graph Neural Networks
Lorenzo Bini, Marco Sorbi, Stephane Marchand-Maillet
Graph Neural Network Attention Mechanism Graph Transformer Attention Layer Targeted Activation Penalty

September 4, 2024

Global Context Enhanced Anomaly Detection of Cyber Attacks via Decoupled Graph Neural Networks
Ahmad Hafez
Graph Neural Network Anomaly Detection Node Representation GNN Architecture Cyber Attack Node Representation Learning Deep Learning Based Anomaly Detection

September 3, 2024

A Lesion-aware Edge-based Graph Neural Network for Predicting Language Ability in Patients with Post-stroke Aphasia
Zijian Chen, Maria Varkanitsa, Prakash Ishwar, Janusz Konrad, Margrit Betke, Swathi Kiran, Archana Venkataraman
Graph Neural Network Patient Friendly Language Functional Connectivity Linguistic Capability Human Connectome Project Resting State fMRI Aphasia Type

September 2, 2024

VLSI Hypergraph Partitioning with Deep Learning
Muhammad Hadir Khan, Bugra Onal, Eren Dogan, Matthew R. Guthaus
Deep Learning Graph Neural Network Chip Design

September 1, 2024

August 30, 2024

August 29, 2024

Graph Neural Network

Papers

CliquePH: Higher-Order Information for Graph Neural Networks through Persistent Homology on Clique Graphs

Graph Neural Networks for Parkinsons Disease Detection

Learning Personalized Scoping for Graph Neural Networks under Heterophily

Learn2Aggregate: Supervised Generation of Chvátal-Gomory Cuts Using Graph Neural Networks

D3-GNN: Dynamic Distributed Dataflow for Streaming Graph Neural Networks

Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting

Stress Predictions in Polycrystal Plasticity using Graph Neural Networks with Subgraph Training

MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks

Up-sampling-only and Adaptive Mesh-based GNN for Simulating Physical Systems

CUQ-GNN: Committee-based Graph Uncertainty Quantification using Posterior Networks

Characterizing Massive Activations of Attention Mechanism in Graph Neural Networks

Global Context Enhanced Anomaly Detection of Cyber Attacks via Decoupled Graph Neural Networks

A Lesion-aware Edge-based Graph Neural Network for Predicting Language Ability in Patients with Post-stroke Aphasia

VLSI Hypergraph Partitioning with Deep Learning

Detecting Homeomorphic 3-manifolds via Graph Neural Networks

Roundabout Dilemma Zone Data Mining and Forecasting with Trajectory Prediction and Graph Neural Networks

Leveraging Graph Neural Networks to Forecast Electricity Consumption

Controllable Edge-Type-Specific Interpretation in Multi-Relational Graph Neural Networks for Drug Response Prediction

SFR-GNN: Simple and Fast Robust GNNs against Structural Attacks

TG-PhyNN: An Enhanced Physically-Aware Graph Neural Network framework for forecasting Spatio-Temporal Data