All talk recordings are now available. You can find the links in the schedule.
Accepted Papers
All accepted papers will be presented as posters during the workshop. Additionally, a small number of accepted papers was selected to be presented as contributed or spotlight talks.
Poster instructions: Posters should be roughly 24" x 36" in portrait orientation. Papers #1-#20 will be presented in the morning poster session (10:00-11:00AM) and papers #21-#40 will be presented in the afternoon poster session (3:30-4:30PM). Please remove your posters during the lunch break if you are presenting in the morning session.
List of accepted papers:
- Neural Message Passing for Visual Relationship Detection. Yue Hu, Siheng Chen, Xu Chen, Ya Zhang and Xiao Gu. (Spotlight)
- Interpretable node embeddings with mincut loss. Chi Thang Duong, Hung Nguyen Quoc Viet and Karl Aberer.
- Batch Virtual Adversarial Training for Graph Convolutional Networks. Zhijie Deng, Yinpeng Dong and Jun Zhu.
- Supervised Segmentation with Graph-Structured Deep Metric Learning. Loic Landrieu and Mohamed Boussaha.
- IPC: A Benchmark Data Set for Learning with Graph-Structured Data. Patrick Ferber, Tengfei Ma, Siyu Huo, Jie Chen and Michael Katz.
- Decoding Molecular Graph Embeddings with Reinforcement Learning. Steven Kearnes, Li Li and Patrick Riley
- Graph Learning Networks. Vedran J. Hadziosmanovic, Yongbin Li, Xiao Liu, Stuart Kim, David Dynerman and Loic Royer. (Spotlight)
- Evolutionary Representation Learning for Dynamic Graphs. Aynaz Taheri and Tanya Berger-Wolf. (Oral)
- Graph Learning Network: A Structure Learning Algorithm. Darwin D. Saire Pilco and Adín Ramírez Rivera. (Spotlight)
- Parallel Cut Pursuit For Minimization of the Graph Total-Variation. Hugo Raguet and Loic Landrieu.
- Graph Neural Reasoning for 2-Quantified Boolean Formula Solver. Zhanfu Yang, Fei Wang, Ziliang Chen, Guannan Wei and Tiark Rompf.
- Variational inference for neural network matrix factorization and its application to stochastic blockmodeling. Onno P. Kampman and Creighton Heaukulani.
- GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension. Yu Chen, Lingfei Wu and Mohammed Zaki.
- Prototype Propagation Networks for Weakly-supervised Few-shot Learning on Category Graph. Lu Liu, Tianyi Zhou, Guodong Long and Jing Jiang.
- Compositional Structure Learning for Sequential Video Data. Kyoung-Woon On, Eun-Sol Kim, Yu-Jung Heo and Byoung-Tak Zhang.
- Invariant Embedding for Graph Classification. Alexis Galland and Marc Lelarge.
- Towards Graph Pooling by Edge Contraction. Frederik Diehl, Thomas Brunner, Michael Truong Le and Alois Knoll.
- Bayesian Graph Convolutional Neural Networks using Node Copying. Soumyasundar Pal, Florence Regol and Mark Coates.
- End-to-end learning and optimization on graphs. Bryan Wilder, Bistra Dilkina and Milind Tambe.
- Unsupervised extraction of interpretable graph representations from multiple-object scenes. Duo Wang, Mateja Jamnik and Pietro Liò.
- COMBO: Combinatorial Bayesian Optimization using Graph Representations. Changyong Oh, Jakub M. Tomczak, Efstratios Gavves and Max Welling. (Spotlight)
- Structure-informed Graph Auto-encoder for Relational Inference and Simulation. Yaguang Li, Chuizheng Meng, Cyrus Shahabi and Yan Liu.
- Factorised Neural Relational Inference for Multi-Interaction Systems. Ezra Webb, Ben J. Day, Helena Andres Terre and Pietro Lió.
- Are Graph Neural Networks Miscalibrated? Leonardo Teixeira, Brian Jalaian and Bruno Ribeiro. (Spotlight)
- Explainability Techniques for Graph Convolutional Networks. Federico Baldassarre and Hossein Azizpour. (Spotlight)
- Learning to Reason Mathematically. Arash Mehrjou, Ryota Tomioka, Andrew W. Fitzgibbon and Simon Pyton Jones.
- Privacy Preserving Adjacency Spectral Embedding on Stochastic Blockmodels. Li Chen.
- PAN: Path Integral Based Convolution for Deep Graph Neural Networks. Zheng Ma. (Oral)
- Learning Transferable Cooperative Behavior in Multi-Agent Teams. Akshat Agarwal, Sumit Kumar and Katia Sycara. (Spotlight)
- Deep Q-Learning for Directed Acyclic Graph Generation. Laura D'Arcy, Padraig Corcoran and Alun Preece.
- Question Answering by Reasoning Across Documents with Graph Convolutional Networks. Nicola De Cao, Wilker Aziz and Ivan Titov. (Spotlight)
- Multiple instance learning with graph neural networks. Ming Tu, Jing Huang, Xiaodong He and Bowen Zhou.
- Sparse Representation Classification via Screening for Graphs. Cencheng Shen, Li Chen, Yuexiao Dong and Carey E. Priebe.
- Tensor-based Method for Temporal Geopolitical Event Forecasting. Mehrnoosh Mirtaheri, Sami Abu-El-Haija, KSM Tozammel Hossain, Fred Morstatter and Aram Galstyan.
- Latent Adversarial Training of Graph Convolution Networks. Hongwei Jin and Xinhua Zhang.
- Towards Permutation-Invariant Graph Generation. Jenny Liu, Aviral Kumar, Jimmy Ba and Kevin Swersky.
- Path-Augmented Graph Transformer Network. Benson Chen, Regina Barzilay and Tommi Jaakkola. (Spotlight)
- Learning Graphical Structure of Electronic Health Records with Transformer for Predictive Healthcare. Edward Choi, Mike W. Dusenberry, Gerardo Flores, Zhen Xu, Yujia Li, Yuan Xue and Andrew M. Dai.
- On Graph Classification Networks, Datasets and Baselines. Enxhell Luzhnica, Ben Day and Pietro Lió. (Oral)
- Can Neural Networks Learn Symbolic Rewriting? Bartosz Piotrowski.