## 图机器学习（ Machine Learning on Graphs）专知荟萃

### 综述

Deep Learning on Graphs: A Survey

Graphs in machine learning: an introduction

Representation Learning on Graphs: Methods and Applications

Attention Models in Graphs: A Survey

A Survey on Network Embedding

Graph Embedding Techniques, Applications, and Performance: A Survey

A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications

Graph Neural Networks: A Review of Methods and Applications

### 入门学习

Machine Learning on Graphs @ NeurIPS 2019

Scalable graph machine learning: a mountain we can climb?

How to get started with machine learning on graphs？

Knowing Your Neighbours: Machine Learning on Graphs

Machine learning with graphs: the next big thing?

AI & Graph Technology: How Graphs Accelerate Machine Learning

### 视频课程

Octavian Machine Learning on Graphs Course Cohort 1

Machine learning on graphs

### 代码

StellarGraph Machine Learning Library

### Tutorial

Machine Learning over graphs

Practical Machine Learning on Graphs course

### VIP内容

【导读】机器学习顶会 NeurIPS 2020, 是人工智能领域全球最具影响力的学术会议之一，因此在该会议上发表论文的研究者也会备受关注。据官方统计，今年NeurIPS 2020 共收到论文投稿 9454 篇，接收 1900 篇（其中 oral 论文 105 篇、spotlight 论文 280 篇），论文接收率为 20.1%。近期，所有Paper List 放出，图机器学习（Graph machine learning）依然十分火热，澳大利亚莫纳什大学潘世瑞（Shirui Pan）老师和其学生（Yixin Liu）整理出NeurIPS 2020图机器学习相关的总结论文《Graph Machine Learning: NeurIPS 2020 Papers》，其中显示大概有80多篇图网络相关论文被大会接收，主要包括：图神经网络(GNNS)的改进、对抗攻击与防御、图自监督学习、可扩展图学习、时空/动态图、图上的应用等方向。

NeurIPS 2020 Accepted Papers : https://neurips.cc/Conferences/2020/AcceptedPapersInitial

1.克服过平滑（Overcoming Over-smoothness） 【3篇】

Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks

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

Towards Deeper Graph Neural Networks with Differentiable Group Normalization

2. 图池化（Graph Pooling）【4篇】

Graph Cross Networks with Vertex Infomax Pooling

Rethinking pooling in graph neural networks

DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multi-grid Pooling

Path Integral Based Convolution and Pooling for Graph Neural Networks

3.图结构学习（Graph Structure Learning）【2篇】

Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings

Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings

4. 对GCN的解释（Explainers for GNNs）【2篇】

Parameterized Explainer for Graph Neural Network

PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks

5. 其他（Others ）【19篇】

Factorizable Graph Convolutional Networks

Factor Graph Neural Networks

Building powerful and equivariant graph neural networks with message-passing

Graphon Neural Networks and the Transferability of Graph Neural Networks

Principal Neighbourhood Aggregation for Graph Nets

Implicit Graph Neural Networks

Natural Graph Networks

Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models

Can Graph Neural Networks Count Substructures?

How hard is to distinguish graphs with graph neural networks?

Graph Random Neural Networks for Semi-Supervised Learning on Graphs

Graph Stochastic Neural Networks for Semi-supervised Learning

Random Walk Graph Neural Networks

Dirichlet Graph Variational Autoencoder

Convergence and Stability of Graph Convolutional Networks on Large Random Graphs

Design Space for Graph Neural Networks

Graph Geometry Interaction Learning

Attribution for Graph Neural Networks

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

（ADVERSARIAL ATTACK & DEFENSE ）

Adversarial Attack on Graph Neural Networks with Limited Node Access

GNNGuard: Defending Graph Neural Networks against Adversarial Attacks

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

Adversarial Attacks on Deep Graph Matching

Reliable Graph Neural Networks via Robust Location Estimation

（GRAPH SELF-SUPERVISED LEARNING）

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

GROVER: Self-Supervised Message Passing Transformer on Large-scale Molecular Graphs

Pre-Training Graph Neural Networks: A Contrastive Learning Framework with Augmentations

（SCALABLE GRAPH LEARNING）

Bandit Samplers for Training Graph Neural Networks

GCOMB: Learning Budget-constrained Combinatorial Algorithms over Billion-sized Graphs

Scalable Graph Neural Networks via Bidirectional Propagation

（SPATIAL-TEMPORAL / DYNAMIC / STREAMING GRAPH）

Pointer Graph Networks

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

Adaptive Shrinkage Estimation for Streaming Graphs

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting

GNNs的应用【15篇】

（APPLICATION OF GNNS）

1. GNNs ×图相关任务（GNNs × Graph-related Tasks）【3篇】

Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning

On the equivalence of molecular graph convolution and molecular wave function with poor basis set

Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous GNNs

2. GNNs × 计算机视觉（GNNs × CV） 【3篇】

Learning Physical Graph Representations from Visual Scenes

Multimodal Graph Networks for Compositional Generalization in Visual Question Answering

GPS-Net: Graph-based Photometric Stereo Network

3. GNNs × 自然语言处理（GNNs × NLP）【4篇】

Learning Graph Structure with A Finite-State Automaton Layer

Strongly Incremental Constituency Parsing with Graph Neural Networks

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks

Deep Relational Topic Modeling via Graph Poisson Gamma Belief Network

4. GNNs ×强化学习（GNNs × RL）【3篇】

Reward Propagation Using Graph Convolutional Networks

Graph Policy Network for Transferable Active Learning on Graphs

Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?

5. GNNs ×其他（GNNs × Others）【2篇】

Generative 3D Part Assembly via Dynamic Graph Learning

Multipole Graph Neural Operator for Parametric Partial Differential Equations

（OTHERS）

1. 图嵌入（Graph Embedding ）【4篇】

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

Curvature Regularization to Prevent Distortion in Graph Embedding

Handling Missing Data with Graph Representation Learning

Manifold structure in graph embeddings

1. 知识图谱（Knowledge Graph ）【3篇】

Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs

Searching Recurrent Architecture for Path-based Knowledge Graph Embedding

Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion

1. 图基准数据集（Graph Benchmark）【1篇】

Open Graph Benchmark: Datasets for Machine Learning on Graphs

1. 图元学习（Graph Meta Learning）【2篇】

Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding

Graph Meta Learning via Local Subgraphs

1. 社区发现（Community Detection ）【2篇】

Provable Overlapping Community Detection in Weighted Graphs

Community detection in sparse time-evolving graphs with a dynamical Bethe-Hessian

1. 图聚类（Graph Clustering）【2篇】

On the Power of Louvain for Graph Clustering

Strongly local p-norm-cut algorithms for semi-supervised learning and local graph clustering

1. 谱聚类（Spectral Clustering）【1篇】

Higher-Order Spectral Clustering of Directed Graphs

Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction

1. 其他（Others indistinguishable）【9篇】

Graph Information Bottleneck

Binary Matrix Completion with Hierarchical Graph Side Information

Universal Function Approximation on Graphs

Less is More: A Deep Graph Metric Learning Perspective Using Few Proxies

COPT: Coordinated Optimal Transport on Graphs

A graph similarity for deep learning

Set2Graph: Learning Graphs From Sets

Stochastic Deep Gaussian Processes over Graphs

Uncertainty Aware Semi-Supervised Learning on Graph Data

https://shiruipan.github.io/post/NIPS_2020_GML.pdf

### 最新论文

Graphs or networks are a very convenient way to represent data with lots of interaction. Recently, Machine Learning on Graph data has gained a lot of traction. In particular, vertex classification and missing edge detection have very interesting applications, ranging from drug discovery to recommender systems. To achieve such tasks, tremendous work has been accomplished to learn embedding of nodes and edges into finite-dimension vector spaces. This task is called Graph Representation Learning. However, Graph Representation Learning techniques often display prohibitive time and memory complexities, preventing their use in real-time with business size graphs. In this paper, we address this issue by leveraging a degeneracy property of Graphs - the K-Core Decomposition. We present two techniques taking advantage of this decomposition to reduce the time and memory consumption of walk-based Graph Representation Learning algorithms. We evaluate the performances, expressed in terms of quality of embedding and computational resources, of the proposed techniques on several academic datasets. Our code is available at https://github.com/SBrandeis/kcore-embedding

Top