Time	Title	Authors/Speaker
1:00-1:05pm	Opening Remarks	Jian Pei
1:05-1:35pm	Keynote Talk 1: Graph Neural Networks for Graph Proximity Computation	Yizhou Sun, University of California, Los Angeles
1:35-1:45pm	Contributed Talk 1: An Empirical Study of Graph Neural Networks Based Semantic Parsing	Shucheng Li, Lingfei Wu, Shiwei Feng, Fangli Xu, Fengyuan Xu and Sheng Zhong
1:45-1:55pm	Contributed Talk 2: Exploiting Graph Neural Networks with Context Information for RDF-to-Text Generation	Hanning Gao, Lingfei Wu, Po Hu and Fangli Xu
1:55-2:05pm	Contributed Talk 3: role2vec: Role-based Network Embeddings	Nesreen Ahmed, Ryan Rossi, John Lee, Theodore Willke, Rong Zhou, Xiangnan Kong and Hoda Eldardiry
2:05-2:25pm	Poster Spotlight Talks (2 minutes each): total 10 talks
2:25-3:10pm	Poser Session (overlapped with Coffee Break)
3:10-3:40pm	Keynote Talk 2: Cross-lingual Graph Structure Transfer for Low-resource Relation and Event Extraction	Heng Ji, University of Illinois Urbana-Champaign, USA
3:40-4:10pm	Keynote Talk 3: Deep Generative Models for Graphs: Methods & Applications	Jure Leskovec, Stanford University, USA
4:10-4:40pm	Keynote Talk 4: Perspectives and Outlook on Network Embedding and GCN	Peng Cui, Tsinghua University, China
4:40-4:50pm	Industrial Keynote Talk 5: Graph Deep Learning and Knowledge Graph in Adaptive Learning	Wei Cui, Squirrel AI Learning, USA
4:50-5:00pm	Best Paper Ceremony and Concluding Remarks	Jian Pei, Yinglong Xia, Lingfei Wu, Hongxia Yang

• Deep Graph Translation, Xiaojie Guo, Lingfei Wu and Liang Zhao
• Order Matters at Fanatics Recommending sequentially ordered products by LSTM embedded with Word2Vec, Jing Pan, Weian Sheng and Santanu Dey
• Overlapping Community Detection with Graph Neural Networks, Oleksandr Shchur and Stephan Günnemann
• Learning Dual Graph Representations for AMR-to-Text Generation, Leonardo F. R. Ribeiro, Claire Gardent and Iryna Gurevych
• Logical Graph Deep Learning for Circuit Deobfuscation Runtime Estimation, Zhiqian Chen, Lei Zhang, Gaurav Kolhe, Hadi Mardani Kamali, Setareh Rafatirad, Sai Manoj Pudukotai Dinakarrao, Houman Homayoun, Chang-Tien Lu and Liang Zhao
• role2vec: Role-based Network Embeddings, Nesreen Ahmed, Ryan Rossi, John Lee, Theodore Willke, Rong Zhou, Xiangnan Kong and Hoda Eldardiry
• A High Performance Graph Embedding Platform, Yan Xie, Zhaoxi Zhang and Yinglong Xia
• Towards Incremental Construction of Graph Embeddings, Anton Tsitsulin, Marina Munkhoeva, Davide Mottin, Panagiotis Karras, Ivan Oseledets, Lior Kamma and Emmanuel Müller
• Unsupervised Inductive Whole-Graph Embedding by Preserving Graph Proximity, Yunsheng Bai, Hao Ding, Yang Qiao, Agustin Marinovic, Ken Gu, Ting Chen, Yizhou Sun and Wei Wang
• ncRNA Classification with Graph Convolutional Networks, Emanuele Rossi, Federico Monti, Michael Bronstein and Pietro Liò
• Sparse hierarchical representation learning on molecular graphs, Matthias Bal, Hagen Triendl, Mariana Assmann, Michael Craig, Lawrence Phillips, Jarvist Moore Frost, Usman Bashir, Noor Shaker and Vid Stojevic
• Exploiting Graph Neural Networks with Context Information for RDF-to-Text Generation, Hanning Gao, Lingfei Wu, Po Hu and Fangli Xu
• An Empirical Study of Graph Neural Networks Based Semantic Parsing, Shucheng Li, Lingfei Wu, Shiwei Feng, Fangli Xu, Fengyuan Xu and Sheng Zhong

Deep Learning models are at the core of research in Artificial Intelligence research today. It is well-known that deep learning techniques that were disruptive for Euclidean data such as images or sequence data such as text are not immediately applicable to graph-structured data. This gap has driven a tide in research for deep learning on graphs on various tasks such as graph representation learning, graph generation, and graph classification. New neural network architectures on graph-structured data have achieved remarkable performance in these tasks when applied to domains such as social networks, bioinformatics and medical informatics.

This wave of research at the intersection of graph theory and deep learning has also influenced other fields of science, including computer vision, natural language processing, inductive logic programming, program synthesis and analysis, automated planning, reinforcement learning, and financial security. Despite these successes, graph neural networks (GNNs) still face many challenges namely,

• Modeling highly structured data with time-evolving, multi-relational, and multi-modal nature. Such challenges are profound in applications in social attributed networks, natural language processing, inductive logic programming, and program synthesis and analysis. Joint modeling of text or image content with underlying network structure is a critical topic for these domains.
• Modeling complex data that involves mapping between graph-based inputs and other highly structured output data such as sequences, trees, and relational data with missing values. Natural Language Generation tasks such as SQL-to-Text and Text-to-AMR are emblematic of such challenge.

This workshop aims to bring together both academic researchers and industrial practitioners from different backgrounds and perspectives to above challenges. The workshop will consist of contributed talks, contributed posters, and invited talks on a wide variety of the methods and applications. Work-in-progress papers, demos, and visionary papers are also welcome. This workshop intends to share visions of investigating new approaches and methods at the intersection of Graph Neural Networks and real-world applications.

Topic of interest (including but not limited to)

We invite submission of papers describing innovative research and applications around the following topics. Papers that introduce new theoretical concepts or methods, help to develop a better understanding of new emerging concepts through extensive experiments, or demonstrate a novel application of these methods to a domain are encouraged.

• Graph neural networks on node-level, graph-level embedding
• Graph neural networks on graph matching
• Dynamic/incremental graph-embedding
• Learning representation on heterogeneous networks, knowledge graphs
• Deep generative models for graph generation/semantic-preserving transformation
• Graph2seq, graph2tree, and graph2graph models
• Deep reinforcement learning on graphs
• Adversarial machine learning on graphs

And with particular focuses but not limited to these application domains:

• Learning and reasoning (machine reasoning, inductive logic programming, theory proving)
• Natural language processing (information extraction, semantic parsing (AMR, SQL), text generation, machine comprehension)
• Bioinformatics (drug discovery, protein generation)
• Program synthesis and analysis
• Automated planning
• Reinforcement learning (multi-agent learning, compositional imitation learning)
• Financial security (anti-money laundering)
• Computer vision (object relation, graph-based 3D representations like mesh)

• Paper submission: May 5, 2019.

  Extended to May 15, 2019 (Anywhere on Earth)

• Author notification: June 5, 2019
• Camera-Ready: Jun 20, 2019
• Workshop: August 5, 2019

Submissions are limited to a total of 4 pages for initial submission (up to 5 pages for final camera-ready submission), excluding references or supplementary materials, and authors should only rely on the supplementary material to include minor details that do not fit in the 4 pages. All submissions must be in PDF format and formatted according to the new Standard ACM Conference Proceedings Template. Following this KDD conference submission policy, reviews are double-blind, and author names and affiliations should NOT be listed. Submitted papers will be assessed based on their novelty, technical quality, potential impact, and clarity of writing. For papers that rely heavily on empirical evaluations, the experimental methods and results should be clear, well executed, and repeatable. Authors are strongly encouraged to make data and code publicly available whenever possible. The accepted papers will be posted on the workshop website and will not appear in the KDD proceedings. Special issues in flagship academic journals are under consideration to host the extended versions of best/selected papers in the workshop.

All submissions must be uploaded electronically at https://easychair.org/conferences/?conf=dlg2019

Contact information: DLG.helpinfo@gmail.com.

• Jure Leskovec, Stanford University, USA
• Yizhou Sun, University of California, Los Angeles, USA
• Heng Ji, University of Illinois Urbana-Champaign, USA
• Peng Cui, Tsinghua University, China

• Jian Pei (Simon Fraser University, Canada)
• Lingfei Wu (IBM Research AI, USA)
• Yinglong Xia (Facebook AI, USA)
• Hongxia Yang (Alibaba Group, China)

• Jian Pei, Simon Fraser University, Canada
• Lingfei Wu, IBM Research AI, USA
• Yinglong Xia, Facebook AI, USA
• William L. Hamilton, McGill University, Canada
• Thomas Kipf, University of Amsterdam, Netherlands
• Stephan Günnemann, Technical University of Munich, Germany
• Renjie Liao, University of Toronto, Canada
• Hongxia Yang, Alibaba Group, China
• Jie Tang, Tsinghua University, China
• Le Song, Georgia Institute of Technology, USA
• Xuemin Lin, University of New South Wales, Australia
• Jiebo Luo, University of Rochester, USA

• Ibrahim Abdelaziz, IBM Research AI, USA
• Peng Cui, Tsinghua University, China
• Wei Cui, Squirrel AI Learning, China
• Sutanay Choudhury, Pacific Northwest National Laboratory, USA
• Lingyang Chu, Simon Fraser University, Canada
• Stephan Günnemann, Technical University of Munich, Germany
• Balaji Ganesan, IBM Research AI, USA
• Tian Gao, IBM Research AI, USA
• Jiebo Luo, University of Rochester, USA
• William L. Hamilton, McGill University, Canada
• Zhao Li, Alibaba Group, China
• Tengfei Ma, IBM Research AI, USA
• Thomas Kipf, University of Amsterdam, Netherlands
• Yujia Li, DeepMind, UK
• Renjie Liao, University of Toronto, Canada
• Jian Pei, Simon Fraser University, Canada
• Yizhou Sun, University of California, Los Angeles, USA
• Le Song, Georgia Institute of Technology, USA
• Qingsong Wen, Alibaba DAMO Academy, USA
• Jie Tang, Tsinghua University, China
• Hanghang Tong, Arizona State University, USA
• Richard Tong, Squirrel AI Learning, China
• Lingfei Wu, IBM Research AI, USA
• Yinglong Xia, Facebook AI, USA
• Hongxia Yang, Alibaba Group, China
• Liang Zhao, George Mason University, USA
• Dawei Zhou, Arizona State University, USA
• Zhen Zhang, Washington University in St. Louis, USA