Time	Title	Speakers/Authors
8:50-9:00pm	Morning Session: Opening Remarks	Lingfei Wu, Charu Aggarwal
9:00-9:30am	Keynote Talk 1: Geometric Deep Learning for Functional Protein Design	Michael Bronstein, Imperial College London, UK
9:30-10:00am	Keynote Talk 2: Representation Learning on Graphs: From Associative Memory to Hyperbolic Geometry	Maximilian Nickel, Facebook AI, USA
10:00-10:30pm	Poster Spotlight Talks (1 minutes each): total 24 talks
10:30-11:30pm	Poser Session I (overlapped with Coffee Break)
11:30-12:00am	Keynote Talk 3: Learning to Represent, Optimize, and Generate Molecular Graphs	Tommi Jaakkola, Massachusetts Institute of Technology, USA
12:00-12:15pm	Contributed Talk 1: Deep Iterative and Adaptive Learning for Graph Neural Networks	Yu Chen, Lingfei Wu and Mohammed J. Zaki
12:15-12:30pm	Contributed Talk 2: Neural Dynamics on Complex Networks	Chengxi Zang and Fei Wang
12:30-13:55pm	Lunch Break
13:55-14:00pm	Afternoon Session: Opening Remarks	Yinglong Xia, Jian Tang
14:00-14:30pm	Keynote Talk 4: Reasoning in Knowledge Graphs using Deep Learning	Jure Leskovec, Stanford University, USA
14:30-15:00pm	Keynote Talk 5: Robust Logic Reasoning with Graph Neural Networks	Le Song, Georgia Institute of Technology, USA
15:00-15:15pm	Contributed Talk 3: Neural-Symbolic Reasoning over Knowledge Graph for Multi-Stage Explainable Recommendation	Yikun Xian, Zuohui Fu, Qiaoying Huang, S. Muthukrishnan and Yongfeng Zhang
15:15-15:30pm	Contributed Talk 4: Graph Neural Ordinary Differential Equations	Michael Poli, Stefano Massaroli, Junyoung Park, Atsushi Yamashita, Hajime Asama and Jinkyoo Park
15:30-16:30pm	Poser Session II (overlapped with Coffee Break)
16:30-17:00pm	Keynote Talk 6: Meta Learning and Logical Induction on Graphs	Will Hamilton, McGill University, CA
17:00-17:30pm	Keynote Talk 7: Deep Graph Library: Overview, Updates, and Future Directions	George Karypis, University of Minnesota and Amazon AWS, USA
17:30-17:45pm	Best Paper Ceremony and Concluding Remarks	Lingfei Wu, Jian Tang, Yinglong Xia, Charu Aggarwal

• [Poster Spotlight Talk] Neural Dynamics on Complex Networks, Chengxi Zang and Fei Wang
• [Poster Spotlight Talk]Edge Dithering for Robust Adaptive Graph Convolutional Networks, Vassilis N. Ioannidis and Georgios B. Giannakis
• [Poster Spotlight Talk]HDGI: An Unsupervised Graph Neural Network for Representation Learning in Heterogeneous Graph,Yuxiang Ren, Bo Liu, Peng Dai, Jiawei Zhang, Chao Huang and Liefeng Bo
• [Poster Spotlight Talk]Towards Interpretable Adverse Drug Reaction Prediction Using Deep Graph Fusion, Pengwei Hu, Tiantian He, Zhaomeng Niu, Shaochun Li, Bibo Hao and Jing Mei
• [Poster Spotlight Talk]Neural-Symbolic Reasoning over Knowledge Graph for Multi-Stage Explainable Recommendation,Yikun Xian, Zuohui Fu, Qiaoying Huang, S. Muthukrishnan and Yongfeng Zhang
• [Poster Spotlight Talk]Adversarial Attacks on Graphs by Adding Fake Nodes,Yu Chen, Zhiling Luo, Sha Zhao, Ying Li and Jianwei Yin
• [Poster Spotlight Talk]Exploratory Combinatorial Optimization with Reinforcement Learning, Thomas Barrett, William Clements, Jakob Foerster and Alexander Lvovsky
• [Poster Spotlight Talk]An Anatomy of Graph Neural Networks Going Deep via the Lens of Mutual Information: Exponential Decay vs. Full Preservation, Nezihe Merve Gürel, Hansheng Ren, Yujing Wang, Hui Xue, Yaming Yang and Ce Zhang
• [Poster Spotlight Talk]Learning Graph-Based Priors for Generalized Zero-Shot Learning, Colin Samplawski, Jannik Wolff, Tassilo Klein and Moin Nabi
• [Poster Spotlight Talk]Enhancing Attention-based Graph Neural Networks via Cardinality Preservation, Shuo Zhang and Lei Xie
• [Poster Spotlight Talk]Neural Networks for Approximate DNF Counting: An Abridged Report, Ralph Abboud, Ismail Ceylan and Thomas Lukasiewicz
• [Poster Spotlight Talk]Combinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement Learning,Qiang Ma, Suwen Ge, Danyang He, Darshan Thaker and Iddo Drori
• [Poster Spotlight Talk]Adversarial Model Extraction on Graph Neural Networks, David DeFazio and Arti Ramesh
• [Poster Spotlight Talk]Benchmark Tests of Convolutional Neural Network and Graph Convolu-tional Network on HorovodRunner Enabled Spark Clusters, Jing Pan, Wendao Liu and Jing Zhou
• [Poster Spotlight Talk]Explainable Deep RDFS Reasoner,Bassem Makni, Ibrahim Abdelaziz and Jim Hendler
• [Poster Spotlight Talk]Graph Neural Ordinary Differential Equations, Michael Poli, Stefano Massaroli, Junyoung Park, Atsushi Yamashita, Hajime Asama and Jinkyoo Park
• [Poster Spotlight Talk]Zoom in to where it matters: a hierarchical graph based model for mammogram analysis, Hao Du, Jiashi Feng and Mengling Feng
• [Poster Spotlight Talk]Graph Neural Networks for Leveraging Industrial Equipment Structure: An application to Remaining Useful Life Estimation, Jyoti Narwariya, Pankaj Malhotra, Vishnu Tv, Lovekesh Vig and Gautam Shroff
• [Poster Spotlight Talk]Lagrangian Propagation Graph Neural Networks, Matteo Tiezzi, Giuseppe Marra, Stefano Melacci, Marco Maggini and Marco Gori
• [Poster Spotlight Talk]Deep Iterative and Adaptive Learning for Graph Neural Networks, Yu Chen, Lingfei Wu and Mohammed J. Zaki
• [Poster Spotlight Talk]Combining learning and optimization on graphs, Bryan Wilder, Eric Ewing, Bistra Dilkina and Milind Tambe
• [Poster Spotlight Talk]How Robust are Graph Neural Networks to Structural Noise?, James Fox and Sivasankaran Rajamanickam
• [Poster Spotlight Talk]Automatic Quantum Optics experimental design with sequential graph generative models, Daniel Flam-Shepherd

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 one-day 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
• Joint learning of graph neural networks and graph structure
• 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
• Spatial and temporal graph prediction and generation

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, text generation)
• Bioinformatics (drug discovery, protein generation, protein structure prediction)
• Program synthesis and analysis
• Reinforcement learning (multi-agent learning, compositional imitation learning)
• Financial security (anti-money laundering)
• Cybersecurity (authentication graph, Internet of Things, malware propagation)
• Geographical network modeling and prediction (Transportation and mobility networks, social networks)

• Paper submission: November 15, 2019.
• Author notification: December 6, 2019
• Camera-Ready: December 15, 2019
• Workshop: February 8, 2019

Submissions are limited to a total of 5 pages for initial submission (up to 6 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 5 pages. All submissions must be in PDF format and formatted according to the new Standard AAAI Conference Proceedings Template. Following this AAAI 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 AAAI 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=dlgma2020

Contact information: lwu@email.wm.edu

• Tommi S. Jaakkola, Massachusetts Institute of Technology, USA (confirmed)
• Jure Leskovec, Stanford University, USA (confirmed))
• Michael Bronstein, Imperial College London, UK (confirmed))
• Le Song, Georgia Institute of Technology, USA (confirmed)
• William L. Hamilton, McGill University, Canada (confirmed)
• Maximilian Nickel, Facebook AI, USA (confirmed)
• George Karypis, University of Minnesota and Amazon AWS, USA (confirmed)

• Lingfei Wu (IBM Research AI, USA)
• Jian Tang (Mila-Quebec AI Institute, Canada)
• Yinglong Xia (Facebook AI, USA)
• Charu Aggarwal (IBM Research AI, USA)

Sponsorship, Media, and Publicity Co-Chairs

• Jing Pan (eHealth, Inc., USA)

• Ibrahim Abdelaziz, IBM Research AI, USA
• Stephan Günnemann, Technical University of Munich, Germany
• Balaji Ganesan, IBM Research AI, USA
• Tian Gao, IBM Research AI, USA
• William L. Hamilton, McGill University, Canada
• Tengfei Ma, IBM Research AI, USA
• Renjie Liao, University of Toronto, Canada
• Chen (Liana) Lin, IBM Research AI, USA
• Qingsong Wen, Alibaba DAMO Academy, USA
• Qing Wang, IBM Research AI, USA
• Xiaojie Guo, George Mason University, USA
• Yuyang Gao, George Mason University, USA
• Dawei Zhou, Arizona State University, USA
• Zhen Zhang, Washington University in St. Louis, USA
• Yu Chen, Rensselaer Polytechnic Institute, USA
• Xinyi Zhang, Facebook AI, USA
• Shen Wang, University of Illinois at Chicago, USA
• Lingwei Chen, Penn State University
• Clara Paolis, Northeastern University, USA
• Tyler Derr, Michigan State University, USA
• Yao Ma, Michigan State University, USA
• Yunsheng Bai, University of California, Los Angeles, USA
• Liping Liu, Tufts University, USA
• Chuan Lei, IBM Reseach AI, USA