Hi, thanks for maintaining such a comprehensive list of methods for graph-level machine learning. I am an author of the ICDM 2019 paper "Distribution of Node Embeddings as Multiresolution Features for Graphs" and was wondering if it could be included on this list?
Overview: Derives a randomized feature map for a graph based on the distribution of its node embeddings in vector space. As the proposed technique is an explicit feature map, it probably fits in the section on "spectral and statistical fingerprints", but its theoretical underpinnings come from the graph kernel literature and so it might fit in that section instead. Won best student paper at ICDM 2019.
Paper: [https://ieeexplore.ieee.org/document/8970922] Code: [https://github.com/GemsLab/RGM]

You can also add to the list "Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction" from NeurIPS18.

It's a novel graph architecture for mapping images to scene graphs using a permutation invariant property, which achieves a new state-of-the-art results on Visual Genome dataset.

paper: https://arxiv.org/abs/1802.05451 code: https://github.com/shikorab/SceneGraph

Hi!

Thank you for this awesome repository!

Could you please add the following paper, code, and data link to the repository: Paper: Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks Authors: Srijan Kumar, Xikun Zhang, Jure Leskovec Venue: ACM SIGKDD 2019 (Proceedings of the 25th ACM SIGKDD international conference on Knowledge discovery and data mining) Project page: http://snap.stanford.edu/jodie/ Code: https://github.com/srijankr/jodie/ All datasets: http://snap.stanford.edu/jodie/

Many thanks, Srijan

Hi there,

please add our paper “A Persistent Weisfeiler–Lehman Procedure for Graph Classification” as well to this repository:

Paper: http://proceedings.mlr.press/v97/rieck19a/rieck19a.pdf Code: https://github.com/BorgwardtLab/P-WL

Best, Bastian

Hi, I am the author of the library py-graph. Thanks a lot for including our library! Just to inform you that we updated our library and now there are implementations for 8 graph kernels. We also upload our library to PyPI. Thanks!

Attention-based pooling operator without having to learn n^2 cluster-assignment matrix as in DiffPool. paper: https://arxiv.org/abs/1904.08082 code: https://github.com/inyeoplee77/SAGPool

hi, i'm trying to add our paper on semi-supervised heterogenous graph embedding to your awesome repository. it was cited 60+ times. hope you accept the pull request. thanks!

Hi,

in our KDD2020 work we solve a graph classification problem with nice results!

Paper: https://dl.acm.org/doi/10.1145/3394486.3403383 Code: https://github.com/tlancian/contrast-subgraph

Would you add it to the repo?

Thank you, Tommaso

Hi, those are some other graph level classification papers for your information Graph Kernel: "A Graph Kernel Based on the Jensen-Shannon Representation Alignment" IJCAI 2015 Lu Bai, Zhihong Zhang, Chaoyan Wang, Xiao Bai, Edwin R. Hancock paper: http://ijcai.org/Proceedings/15/Papers/468.pdf code: https://github.com/baiuoy/Matlab-code-JS-alignment-kernel-IJCAI-2015

“An Aligned Subtree Kernel for Weighted Graphs” ICML 2015 Lu Bai, Luca Rossi, Zhihong Zhang, Edwin R. Hancock paper: http://proceedings.mlr.press/v37/bai15.pdf code will be released soon

Deep Learning: "Learning Aligned-Spatial Graph Convolutional Networks for Graph Classification" ECML-PKDD 2019 Lu Bai, Yuhang Jiao, Lixin Cui, Edwin R. Hancock paper: https://arxiv.org/abs/1904.04238 code: https://github.com/baiuoy/ASGCN_ECML-PKDD2019 (will be released soon)

Hi, thanks for this awesome repo on graph classification. Please help review the PR. I'd like to add our paper and help clarify 1 workshop paper.

Thanks, Ruochun

Hi,

Thank you for your paper list. I am the author of the paper A Simple Yet Effective Baseline for Non-Attribute Graph Classification. It has been accepted by ICLR 2019 graph representation learning workshop (https://rlgm.github.io/). Would you like to update the record? Thanks!

Best, Chen