Deep Graph Learning:

Methodologies and Applications

DGLMA'19 Workshop @ IEEE BigData'19

December 9, Los Angeles, CA, USA


In many scientific fields, many important problems can be best expressed with a complex structure, e.g., graph or manifold structure, such as social networks and drug discovery. On one hand, these graph-structured data can encode complicated pairwise relationships for learning more informative representations; On the other hand, the structural and semantic information in sequence data can be exploited to augment original sequence data by incorporating the domain-specific knowledge.

Deep Learning models are at the core of research in Artificial Intelligence nowadays. In recent years, deep learning on graphs has experienced a fast increase in research on these problems, especially for graph representation learning and graph generation. New neural network architectures on graph-structured data have achieved remarkable performance in some well-known domains such as social networks and bioinformatics . They have also infiltrated other fields of science, including computer vision, natural language processing, inductive logic programming, program synthesis and analysis, automated planning, reinforcement learning, financial security, and adversarial machine learning. Despite these successes, graph neural networks (GNNs) still face many challenges when they are used to model highly structured data that are time-evolving, multi-relational, and multi-modal, and the mapping between graphs and other highly structured data such as sequences, trees and graphs. More importantly, new application domains for GNNs that emerge from real world problems introduce significantly more challenges for GNNs.


We invite the submission of novel research paper, demo paper, and visionary papers. Types of submissions are the following:

  1. Long paper (up to 10 pages)
  2. Short paper (up to 6 pages)
  3. Work in progress paper
Submissions must be in PDF format, written in English, and formatted according to the latest double-column IEEE 2-column format. All papers will be peer reviewed, single-blinded. Submitted papers will be assessed based on their novelty, technical quality, potential impact, insightfulness, depth, clarity, and reproducibility. Accepted papers will be published in the IEEE BigData 2019 conference proceedings with the main conference papers. All the papers are required to be submitted here.

For any inquery please email:

We encourage submissions on a broad range of deep learning on graphs. Topics of interest include, but not limited to:

  • Methods
  • - Graph neural networks on node-level, graph-level embedding
  • - Graph neural networks on graph matching
  • - Scalable methods for large graphs
  • - 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
  •    Applications:
  •    - 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, protein structure prediction)
  •    - Program synthesis and analysis
  •    - Automated planning
  •    - Reinforcement learning (multi-agent learning, compositional imitation learning)
  •    - Financial security (Anti-Money Laundering)
  •    - Computer vision (object relation reasoning, graph-based representations for segmentation/tracking)

Note that at least one author from each accepted paper must register to attend the IEEE Big Data 2019 conference and present their work in DGLMA'19.


Oct 1, 2019: Oct 8, 2019         Workshop paper submission due (23:59, Anywhere on Earth)

Nov 1, 2019:       Workshop paper notifications

Nov 15, 2019:      Workshop paper camera-ready deadline (23:59, Anywhere on Earth)

Dec 9, 2019:  Workshop Date


Opening & Welcome

Lingfei WuIBM Research

Systems Aspects in Graph Learning

Berthold ReinwaldIBM Research

Bio: Dr. Berthold Reinwald is a Principle Research Staff Member and a manager at IBM Research-Almaden. His research interests include scalable machine learning/deep learning platforms and database technologies. He is a committer to Apache SystemML.

Keynote 2

Yang ZhouAuburn University

Coffee Break

Put up posters

Graph-based Rare Category Analysis: Exploration, Exploitation, and Interpretation

Dawei ZhouUIUC

Bio: Dawei Zhou is currently a Ph.D. student at the Department of Computer Science, University of Illinois at Urbana-Champaign. His current research interests include rare category analysis, active learning, and semi-supervised learning, with applications in financial fraud detection, social network analysis. Dawei Zhou has worked on rare category analysis for five years, which results in 10 publications at major conferences (e.g., IJCAI, AAAI, KDD, SDM, ICDM, CIKM) and journals (e.g., TKDD, DMKD).

Learning Interactive Network Summaries

Aditya PrakashVirginia Tech

Bio: B. Aditya Prakash is an Associate Professor in the Computer Science Department at Virginia Tech. He graduated with a Ph.D. from the Computer Science Department at Carnegie Mellon University in 2012, and got his B.Tech (in CS) from the Indian Institute of Technology (IIT) -- Bombay in 2007. He has published one book, more than 80 refereed papers in major venues, holds two U.S. patents and has given five tutorials (SDM 2018, SDM 2017, SIGKDD 2016, VLDB 2012 and ECML/PKDD 2012) at leading conferences. His work has also received a best paper award and four best-of-conference selections (ICDM 2017, ASONAM 2013, CIKM 2012, ICDM 2012, ICDM 2011) and multiple travel awards. His research interests include Data Mining, Applied Machine Learning and Databases, with emphasis on big-data problems in large real-world networks and time-series. His work has been funded through grants/gifts from the National Science Foundation (NSF), the Department of Energy (DoE), the National Security Agency (NSA), the National Endowment for Humanities (NEH) and from companies. Tools developed by his group have been in use in many places including ORNL, Walmart and Facebook. He received a Facebook Faculty Gift Award in 2015, the NSF CAREER award in 2018 and was named as one of ‘2017 AI Ten to Watch’ by IEEE Intelligent Systems. He is also an affiliated faculty member at the Discovery Analytics Center at Virginia Tech. Aditya's homepage is at: and Twitter handle is: @badityap

Poster Session

Accepted Works

Closing Remarks

Tyler DerrMichigan State University


Predicting Alzheimer’s Disease by Hierarchical Graph Convolution from Positron Emission Tomography Imaging
By: Jiaming Guo, Wei Qiu, Xiang Li, Xuandong Zhao, Ning Guo, and Quanzheng Li

Heterogeneous Graph Matching Networks: Application to Unknown Malware Detection
By: Shen Wang and Philip S. Yu

Improved Deep Embeddings for Inferencing with Multi-Layered Graphs
By: Huan Song and Jayaraman J. Thiagarajan

Optimizing Variational Graph Autoencoder for Community Detection
By: Jun Jin Choong, Xin Liu, and Tsuyoshi Murata

Learning Relevant Molecular Representations via Self-Attentive Graph Neural Networks
By: Shoma Kikuchi, Ichigaku Takigawa, Satoshi Oyama, and Masahito Kurihara

Exploiting Graph Convolutional Networks for Representation Learning of Mobile App Usage
By: Keiichi Ochiai, Naoki Yamamoto, Takashi Hamatani, Yusuke Fukazawa, and Takayasu Yamaguchi

Graph classification with the hypernetwork, a molecule interaction based evolutionary architecture
By: Jose Segovia-Juarez, Silvano Colombano, Daniel Hidalgo-Chavez, Alex Flores-Mamani, and Miguel Mejia-Puma

Characterization and graph embedding of weighted social networks through Diffusion Wavelets
By: Zhiliang Chen, Junfeng Wu, Huakang Li, and Guozi Sun

A Dynamic Financial Knowledge Graph Based on Reinforcement Learning and Transfer Learning
By:Rui Miao, Xia Zhang, Hongfei Yan, and Chong Chen

Temporal Neighbourhood Aggregation: Predicting Future Links in Temporal Graphs via Recurrent Variational Graph Convolutions
By: Stephen Bonner, Amir Atapour-Abarghouei, Phillip Jackson, John Brennan, Ibad Kureshi, Georgios Theodoropoulos, Andrew Stephen McGough, and Boguslaw Obara




Lingfei Wu IBM Research AI

Dr. Lingfei Wu is a Research Staff Member in the IBM AI Foundations Labs, Ressoning group at IBM T. J. Watson Research Center. He earned his Ph.D. degree in computer science from the College of William and Mary in 2016. Lingfei Wu is a passionate researcher and responsible team leader, developing novel deep learning/machine learning models for solving real-world challenging problems. He has served as the PI in IBM for several federal agencies such as DARPA and NSF (more than $1.8M), as well as MIT-IBM Watson AI Lab. He has published more than 50 top-ranked conference and journal papers in ML/DL/NLP domains and is a co-inventor of more than 20 filed US patents. He was the recipient of the Best Paper Award and Best Student Paper Award of several conferences such as IEEE ICC'19 and KDD workshop on DLG'19. His research has been featured in numerous media outlets, including NatureNews, YahooNews, Venturebeat, TechTalks, SyncedReview, Leiphone, QbitAI, MIT News, IBM Research News, and SIAM News. He has organized or served as Poster co-chairs of IEEE BigData'19, Tutorial co-chairs of IEEE BigData'18, Workshop co-chairs of Deep Learning on Graphs (with KDD'19, IEEE BigData’19, and AAAI'20), and regularly served as a SPC/TPC member of the following major AI/ML/DL/DM/NLP conferences including NIPS, ICML, ICLR, ACL, IJCAI, AAAI, and KDD.


Jiliang Tang Michigan State University

Jiliang Tang is an assistant professor in the computer science and engineering department at Michigan State University. Before that, he was a research scientist in Yahoo Research and got his PhD from Arizona State University in 2015. He focuses on developing learning, mining and optimization algorithms from the graph perspective . He was the recipients of The NSF Career Award, the Best Paper Award in ASONAM 2018, the Best Student Paper Award in WSDM2018, the Best Paper Award in KDD2016, the runner up of the Best KDD Dissertation Award in 2015, Dean's Dissertation Award and the best paper shortlist of WSDM2013. He is now associate editors of ACM TKDD, ICWSM, and Neurocomputing. He has published his research in highly ranked journals and top conference proceedings, which received thousands of citations and extensive media coverage.


Liang Zhao George Mason University

Dr. Liang Zhao is an assistant professor at Information Science and Technology Department at George Mason University. He got his PhD degree from Computer Science Department at Virginia Tech. His research interests include big data mining, artificial intelligence, and machine learning, with particular emphasis on social network modeling, and deep learning on graphs, and spatiotemporal data mining. He got the NSF CRII award in 2018. He got Jeffress Trust Awards in 2019 for supporting his ongoing research on graph generative deep learning. He is named as one of the “Top 20 Data mining Rising Star” by Microsoft Academic Search in 2016. He won the dissertation award of Computer Science Department at Virginia Tech. He has published over 50 papers in top journals and conferences in data mining, machine learning, and artificial intelligence.

Publicity Chair


Tyler Derr Michigan State University

Tyler Derr is a Ph.D. student in the department of Computer Science and Engineering at Michigan State University (MSU). His main research interest is in network analysis, with particular emphasis on signed networks and graph neural networks. He was the recipient of the Best Reviewer Award at ICWSM2019, the Best Student Poster Award at SDM2019, and the "People's Choice" Award for the 3 Minute Thesis Competition at MSU. He has published several papers in these domains at some of the top international conferences and received travel awards to present his work. He actively serves as a reviewer/program committee member for journals/conferences in his research domain. Tyler is also currently on the job market for a tenure-track Assistant Professor position at a research institution in Computer Science.

Program Committee

Tyler Derr
    (Michigan State University)
Amin Javari
    (University of Illinois at Urbana-Champaign)
Chen Lin
    (IBM Research)

Yue Ning
    (Stevens Insitute of Technology)
Qing Wang
    (IBM T. J. Watson Research Center)
Suhang Wang
    (The Pennsylvania State University)

Zhiwei Wang
    (Michigan State University)
Lingfei Wu
    (IBM T. J. Watson Research Center)
Zhen Zhang
    (Washington University in St. Louis)