Learning on Graphs Conference（LoG）会议，区别于NeurIPS，ICML和ICLR等学术会议，这个新举办的会议接收的投稿都与图&几何机器学习相关。作为第一届举办的会议，Log 2022一共接收了83篇文章，包括12篇spotlight和71篇poster文章。

这是一个致力于图学习的新会议主要是针对图机器学习的研究。会议的组织着和顾问委员会基本上是由图学习领域的权威专家组成的。



完整版
LOG 2022 Conference | OpenReview

Node Classification

• ScatterSample: Diversified Label Sampling for Data Efficient Graph Neural Network Learning
• On the Unreasonable Effectiveness of Feature Propagation in Learning on Graphs with Missing Node Features
• Label-Wise Graph Convolutional Network for Heterophilic Graphs
• AutoGDA: Automated Graph Data Augmentation for Node Classification

Few-shot Learning

• Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification
• Metric Based Few-Shot Graph Classification

Graph Property Prediction

• Shortest Path Networks for Graph Property Prediction
• GEFL: Extended Filtration Learning for Graph Classification
• Towards Efficient and Expressive GNNs for Graph Classification via Subgraph-aware Weisfeiler-Lehman

Expressivity

• PatchGT: Transformer over Non-trainable Clusters for Learning Graph Representations
• Learnable Commutative Monoids for Graph Neural Networks
• Weisfeiler and Leman Go Relational
• Gradual Weisfeiler-Leman: Slow and Steady Wins the Race

Molecules

• Jointly Modelling Uncertainty and Diversity for Active Molecular Property Prediction
• Representation Learning on Biomolecular Structures using Equivariant Graph Attention
• Graph Neural Network with Local Frame for Molecular Potential Energy Surface

Explainability

• GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks
• Towards Training GNNs using Explanation Directed Message Passing

 Oversquashing

• Expander Graph Propagation
• DiffWire: Inductive Graph Rewiring via the Lovasz Bound

Robustness

• You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained Graph Tickets
• A Systematic Evaluation of Node Embedding Robustness
• GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks

 Scalability

• Influence-Based Mini-Batching for Graph Neural Networks
• Flashlight: Scalable Link Prediction with Effective Decoders

Link Prediction

• FakeEdge: Alleviate Dataset Shift in Link Prediction
• Similarity-based Link Prediction from Modular Compression of Network Flows

Dynamic Graphs

• Neighborhood-aware Scalable Temporal Network Representation Learning
• Piecewise-Velocity Model for Learning Continuous-time Dynamic Node Representations
• Well-conditioned Spectral Transforms for Dynamic Graph Representation
• CEP3: Community Event Prediction with Neural Point Process on Graph

Time Series

• Graph-Time Convolutional Autoencoders
• DAMNETS: A Deep Autoregressive Model for Generating Markovian Network Time Series
• De Bruijn goes Neural: Causality-Aware Graph Neural Networks for Time Series Data on Dynamic Graphs
• ISA-Traffic: An Ising-Aided Method for Traffic Congestion Prediction with Uncertainty

Higher-Order Data

• Efficient Representation Learning for Higher-Order Data with Simplicial Complexes
• Sparse and Local Hypergraph Reasoning Networks
• Pruning Edges and Gradients to Learn Hypergraphs from Larger Sets

 Neural Algorithmic Models

• A Generalist Neural Algorithmic Learner
• Continuous Neural Algorithmic Planners

Benchmarks

• Graph Learning Indexer: A Contributor-Friendly Platform for Better Curation of Graph Learning Benchmarks
• Taxonomy of Benchmarks in Graph Representation Learning

Computer Vision

• Neural Graph Modelling of Whole Slide Images for Survival Ranking
• Transfer Learning using Spectral Convolutional Autoencoders on Semi-Regular Surface Meshes

Directed Graphs

• MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian
• DIGRAC: Digraph Clustering Based on Flow Imbalance

Distributed Systems

• Distributed representations of graphs for drug pair scoring
• Learning Distributed Geometric Koopman Operator for Sparse Networked Dynamical Systems

Miscellaneous

• Neural Graph Databases
• TopoImb: Toward Topology-level Imbalance in Learning from Graphs
• Dynamic Network Reconfiguration for Entropy Maximization using Deep Reinforcement Learning
• A Survey on Deep Graph Generation: Methods and Application
• A simple way to learn metrics between attributed graphs
• Learning Graph Search Heuristics
• Combining Graph and Recurrent Networks for Efficient and Effective Segment Tagging
• Reasoning-Modulated Representations