Awesome-Graph-level-Neural-Networks (Awesome GLNNs)

4. GLNNs - Deep Neural Networks (DNNs)

4.1 Convolution Neural Networks (CNN)-based Approaches

paper title	venue	yeas	authors	Materials
Learning convolutional neural networks for graphs	ICML	2016	M. Niepert et al.	paper
Diffusion- convolutional neural networks	NeurIPs	2016	J. Atwood et al.	paper
Dynamic edge-conditioned filters in convolutional neural networks on graphs	CVPR	2017	M. Simonovsky et al.	paper

4.2 Capsule Neural Networks (CapsNet)-based Approaches

paper title	venue	yeas	authors	Materials
Graph Capsule Convolutional Neural Networks	ICML&IJCAI Workshop	2018	S. Verma et al.	paper
Capsule graph neural network	ICLR	2018	X. Zhang et al.	paper

4.3 Recurrent Neural Networks (RNN)-based Approaches

paper title	venue	yeas	authors	Materials
Graphrnn: Gener-ating realistic graphs with deep auto-regressive models	ICML	2018	J. You et al.	paper
Graph classification using structural attention	KDD	2018	J. B. Lee et al.	paper
Janossy pooling: Learning deep permutation-invariant functions for variable-size inputs	ICLR	2019	R. L. Murphy et al.	paper

5. GLNNs - Graph Nueral Networks (GNNs)

5.1 The expressivity of GLNNs-GNNs

paper title	venue	yeas	authors	Materials
Neural message passing for quantum chemistry	ICML	2017	J. Gilmer et al.	paper
How Powerful are Graph Neural Networks?	NeurIPS	2018	K. Xu et al.	paper
On weisfeiler-leman invariance: subgraph counts and related graph properties	J Comput Syst Sci	2020	V.Arvind et al.	paper
Can graph neural networks count substructures	NeurIPS	2020	Z. Chen et al.	paper
Weisfeiler and leman go neural: Higher-order graph neural networks	AAAI	2019	C. Morris et al.	paper
Provably powerful graph networks	NeurIPS	2019	H.Maron et al.	paper
Improving graph neural network expressivity via subgraph isomorphism counting	arXiv	2020	G.Bouristas et al.	paper
Relational pooling for graph representations	ICML	2019	R.Murphy et al.	paper
A survey on the expressive power of graph neural networks	arXiv	2020	R. Sato	paper
Breaking the limits of message passing graph neural networks	ICML	2021	M. Balcilar	paper
Weisfeiler and lehman go topological: Message passing simplicial networks	ICML	2021	C. Bodnar	paper
Expressiveness and approxima- tion properties of graph neural networks	ICLR	2022	Anonymous	paper
An- alyzing the expressive power of graph neural networks in a spec- tral perspective	ICLR	2021	M. Balcilar	paper

5.2 Spectral GLNNs-GNNs

paper title	venue	yeas	authors	Materials
How framelets enhance graph neural networks	ICML	2021	X. Zheng et al.	paper
Fast attributed graph embedding via density of states	ICDM	2021	S. Sawlani et al.	paper
Bridging the gap between spectral and spatial domains in graph neural networks	arXiv	2020	M. Balcilar et al.	paper

5.3 The Generalization of GLNNs-GNNs

paper title	venue	yeas	authors	Materials
How neural networks extrapolate: From feedforward to graph neural networks	ICLR	2021	W. Xu et al.	paper
From local structures to size generalization in graph neural networks	ICML	2021	G. Yehudai et al.	paper
Adaptive-step graph meta-learner for few-shot graph classification	CIKM	2020	N. Ma et al.	paper
Few- shot learning on graphs via super-classes based on graph spectral measures	ICLR	2021	J. Chauhan et al	paper
On the bottleneck of graph neural networks and its practical implications	ICLR	2021	U. Alon et al.	paper

5.4 Explaining GLNNs-GNNs’ Predictions

paper title	venue	yeas	authors	Materials
Xgnn:towards model-level explanations of graph neural networks	KDD	2020	H. Yuan et al.	paper
Parameterized explainer for graph neural network	NeurIPS	2020	D. Luo et al.	paper
Gnnex- plainer: Generating explanations for graph neural networks	NeurIPS	2019	R. Ying et al.	paper
Graphlime: Local interpretable model explanations for graph neural networks	arXiv	2020	Q. Huang et al.	paper
Ex- plainability methods for graph convolutional neural networks	CVPR	2020	P. E. Pope	paper

5.5 GLNNs-GNNs Combined with Other Methods

Combining GLNNs-GNNs with Contrastive Learning

paper title	venue	yeas	authors	Materials
Info- graph: Unsupervised and semi-supervised graph-level represen- tation learning via mutual information maximization	ICLR	2020	F. Sun et al.	paper
Graph contrastive learning with augmentations	NeurIPS	2020	Y. You et al.	paper
Gcc: Graph con- trastive coding for graph neural network pre-training	KDD	2020	J. Qiu et al.	paper

Combining GLNNs-GNNs with GKs

paper title	venue	yeas	authors	Materials
Convolutional kernel networks for graph-structured data	ICLR	2020	D. Chen et al.	paper
Graph neural tangent kernel: Fusing graph neural networks with graph kernels	NeurIPS	2019	S. S. Du et al.	paper
Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels	WWW	2021	Q. Long et al.	paper

6. GLNNS: Graph Pooling

6.1 Global Pooling

paper title	venue	yeas	authors	Materials
An end-to-end deep learning architecture for graph classification	AAAI	2018	M. Zhang et al.	paper
Learnable structural semantic readout for graph classification	ICDM	2021	D. Lee et al.	paper

6.2 Hierarchical Pooling

paper title	venue	yeas	authors	Materials
Hierarchical graph representation learning with differentiable pooling	NeurIPS	2018	R. Ying et al.	paper
Spectral clustering with graph neural networks for graph pooling	ICML	2020	F. M. Bianchi et al.	paper
Memory-based graph networks	ICLR	2020	A. H. Khasahmadi et al.	paper
Self-attention graph pooling	ICML	2019	J. Lee et al.	paper
Graph u-nets	ICML	2019	H. Gao et al.	paper
Towards sparse hierarchical graph classifiers	NeurIPS	2018	C. Cangea et al.	paper
Graph convolutional networks with eigenpooling	KDD	2019	Y. Ma	paper
Structpool: Structured graph pooling via conditional random fields	ICLR	2020	H. Yuan	paper
Asap: Adaptive structure aware pooling for learning hierarchical graph representations	AAAI	2020	E. Ranjan et al.	paper

6.3 Emerging Graph Pooling Techniques

paper title	venue	yeas	authors	Materials
Rethinking pooling in graph neural networks	NeurIPS	2020	D. Mesquita et al.	paper
Pooling architecture search for graph classification	CIKM	2021	L. Wei et al.	paper

7. Reproducibility, Benchmarks, and Datasets

Benchmarks

paper title	venue	yeas	authors	Materials
A faircomparison of graph neural networks for graph classification	ICLR	2020	F. Errica et al.	paper
Benchmarking graph neural networks	arXiv	2020	V.P. Dwivedi et al.	paper

Datasets

paper title	venue	yeas	authors	Materials
Benchmark data sets for graph kernels	ICML Workshop	2020	C. Morris et al.	paper
Understanding isomorphism bias in graph data sets	arXiv	2019	S. Ivanov et al.	paper
A large-scale database for graph representation learning	NeurIPS	2021	S. Freitas et al.	paper
Open graph benchmark: Datasets for machine learning on graphs	NeurIPS	2020	W. Hu et al.	paper

8. Future Directions

8.1 Graph Transformation-equivariance

paper title	venue	yeas	authors	Materials
Covariant compositional networks for learning graphs	ICLR	2018	R. Kondor et al.	paper
new perspective on “how graph neurla networks go beyond weisfeiler-lehman?”	ICLR	2022	Anonymous	paper
Natural graph networks	NeurIPS	2020	P. Hann et al.	paper
GemNet: Universal Directional Graph Neural Networks for Molecules	NeurIPS	2021	J. Klicpera et al.	paper
E(n) equivariant graph neural networks	ICML	2021	V. G. Satorras et al.	paper

8.2 Graph Pooling with Difference Awareness

/

8.3 Imbalanced Graph-level Learning

paper title	venue	yeas	authors	Materials
Imbalanced Graph Classification via Graph-of-Graph Neural Networks	arXiv	2021	Y. Wang et al.	paper

8.4 Out-of-Distribution Generalization of GLNNs

paper title	venue	yeas	authors	Materials
Size-invariant graph representations for graph classification extrapolations	ICML	2021	B. Bevilacqua et al.	paper

8.5 Performant Parameters of GLNNs

paper title	venue	yeas	authors	Materials
Parameter Prediction for Unseen Deep Architectures	NeurIPS	2021	B. Knyazev et al.	paper

8.6 Applying GLNNs to Classify Brain Networks

paper title	venue	yeas	authors	Materials
Explainable classification of brain networks via contrast subgraphs	KDD	2020	T. Lanciano et al.	paper

8.7 Encoding Relations among Graphs

paper title	venue	yeas	authors	Materials
Gognn: Graph of graphs neural network for predicting structured entity interactions	IJCAI	2020	H. Wang et al.	paper