GNN Survey Weekly Paper Review

Guidelines

• Deadline: Submit paper summaries every Sunday.
• Content:
  • Upload a brief summary of the paper, key insights, and any relevant figures.
  • Focus on the main message of the paper.
• Collaboration:
  • Read and comment on each other's summaries by the following week.
  • Share thoughts, questions, or points of confusion.

Paper List

~10/20

• Network Traffic Modeling and Prediction Using Graph Gaussian Processes
• Graph neural bayesian optimization for virtual screening
• Bayesian optimisation of functions on graphs

~10/27

• Graph neural network-inspired kernels for gaussian processes in semi-supervised learning
• Graph Neural Network Powered Bayesian Optimization for Large Molecular Spaces

~11/3

• Adversarial label-flipping attack and defense for graph neural networks
• Towards self-explainable graph neural network
• Unified robust training for graph neural networks against label noise
• Nrgnn: Learning a label noise resistant graph neural network on sparsely and noisily labeled graphs
• Exact Combinatorial Optimization with Graph Convolutional Neural Network

~11/10

• Strategies for pre-training graph neural networks
• Graph contrastive learning with augmentations
• Graph backdoor
• LightGCN

~11/17

• Generative-Contrastive Graph Learning for Recommendation