神经网络代码解读_NeurIPS2020上图神经网络好文

今年的Neurips正在进行，图神经网络也是今年的一大热点，这里总结一下GNN的文章，贴个链接和概述备忘，如果有错误的或者遗漏的文章请大家一定指出来。

整理不易，点个赞呗再走呗，欢迎关注我们的新专栏图神经网络实战，里面会更新一些图神经网络代码解读和最新的进展。如果大家有什么需要分享的，也欢迎投稿本专栏，感激不尽。

GNN的测试：

Design Space for Graph Neural Networks
Open Graph Benchmark: Datasets for Machine Learning on Graphs
Rethinking pooling in graph neural networks

GNN理论：
Can Graph Neural Networks Count Substructures?

Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks

Building powerful and equivariant graph neural networks with structural message-passing

A graph similarity for deep learning

Universal Function Approximation on Graphs

How hard is to distinguish graphs with graph neural networks?

Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings

Graphon Neural Networks and the Transferability of Graph Neural Networks
Manifold structure in graph embeddings
Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning

Convergence and Stability of Graph Convolutional Networks on Large Random Graphs

如何训练更好的GNN：

Graph Random Neural Networks for Semi-Supervised Learning on Graphs

Graph Contrastive Learning with Augmentations

Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings
Self-Supervised Graph Transformer on Large-Scale Molecular Data

Bandit Samplers for Training Graph Neural Networks
Towards Deeper Graph Neural Networks with Differentiable Group Normalization (video missing)
Graph Policy Network for Transferable Active Learning on Graphs

Graph Meta Learning via Local Subgraphs

新GNN结构：
Graph Geometry Interaction Learning (hyperbolic geometries)

Digraph Inception Convolutional Networks (graph convolution on directed graphs; refer to PageRank)

Graph Cross Networks with Vertex Infomax Pooling

Graph Stochastic Neural Networks for Semi-supervised Learning

Subgraph Neural Networks
Reliable Graph Neural Networks via Robust Aggregation (Medoid Aggregation)
Self-Supervised Graph Transformer on Large-Scale Molecular Data
Path Integral Based Convolution and Pooling for Graph Neural Networks
Uncertainty Aware Semi-Supervised Learning on Graph Data
GNNGuard: Defending Graph Neural Networks against Adversarial Attacks

Natural Graph Networks (Scalable "equivariant" GNN)
Stochastic Deep Gaussian Processes over Graphs

Random Walk Graph Neural Networks
DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling

GNN与图优化：
Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous GNNs

Pointer Graph Networks

Implicit Graph Neural Networks (solve recurrent GNNs to equilibrium state)

GCOMB: Learning Budget-constrained Combinatorial Algorithms over Billion-sized Graphs
Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver? (learn branch policy with GNN)
Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs

超大图上GNN：
Scalable Graph Neural Networks via Bidirectional Propagation
GCOMB: Learning Budget-constrained Combinatorial Algorithms over Billion-sized Graphs

可解释GNN：
Parameterized Explainer for Graph Neural Network

Graph Cross Networks with Vertex Infomax Pooling

Graph Information Bottleneck

PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks
Evaluating Attribution for Graph Neural Networks
Factorizable Graph Convolutional Networks (Disentanglement in graph domain)

图生成：

Set2Graph: Learning Graphs From Sets

Dirichlet Graph Variational Autoencoder

Unsupervised relational graph generation:

Learning Physical Graph Representations from Visual Scenes

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings
Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning

GNN与PDE：

Multipole Graph Neural Operator for Parametric Partial Differential Equations
DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling

Causal graph：

A polynomial-time algorithm for learning nonparametric causal graphs
CASTLE: Regularization via Auxiliary Causal Graph Discovery

谱GNN：

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting

Graphon Neural Networks and the Transferability of Graph Neural Networks

一些新的应用：

Handling Missing Data with Graph Representation Learning Learning Physical Graph Representations from Visual Scenes

Cross-Scale Internal Graph Neural Network for Image Super-Resolution Factor Graph Neural Networks
On the equivalence of molecular graph convolution and molecular wave function with poor basis set

Reward Propagation Using Graph Convolutional Networks
Sparse Graphical Memory for Robust Planning

AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity

GNN与LDPC CODE：
Factor Graph Neural Networks

Learning to Decode: Reinforcement Learning for Decoding of Sparse Graph-Based Channel Codes

GNN与自动编程：
Learning Graph Structure With A Finite-State Automaton Layer

Transferable Graph Optimizers for ML Compilers
Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks

还没看abstract的：

UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging

Towards More Practical Adversarial Attacks on Graph Neural Networks

Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs

Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs

Learning Dynamic Belief Graphs to Generalize on Text-Based Games

Dense Correspondences between Human Bodies via Learning Transformation Synchronization on Graphs
Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning

Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks

Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs
GPS-Net: Graph-based Photometric Stereo Network
Language and Visual Entity Relationship Graph for Agent Navigation
Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies

Multimodal Graph Networks for Compositional Generalization in Visual Question Answering
Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding

Generative 3D Part Assembly via Dynamic Graph Learning
Strongly Incremental Constituency Parsing with Graph Neural Networks