The Second International Workshop on Deep Learning on Graphs: Methods and Applications (DLG-KDD’20)

August 24th, 2020
San Diego, CA, USA

In Conjunction with The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
August 23-27, 2020
San Diego Convention Center
San Diego, CA, USA
KDD 2020 logo

Best Paper Award

The Best Paper Award goes to Daheng Wang, Zhihan Zhang, Yihong Ma, Tong Zhao, Tianwen Jiang, Nitesh V. Chawla, Meng Jiang for their paper “Learning Attribute-Structure Co-Evolutions in Dynamic Graphs”


The Best Student Paper Award goes to Yewen Wang, Ziniu Hu, Yusong Ye and Yizhou Sun for their paper “Demystifying Graph Neural Networks with Graph Filter Assessment”


How to attend the workshop remotely?

This year DLG will be held jointly with The 16TH INTERNATIONAL WORKSHOP ON MINING AND LEARNING WITH GRAPHS (KDD-MLG). Due to the COVID-19 pandemic, we will have a fully virtual program. Please register KDD'20 and our workshop for attending the workshop on 08/24/2020! Note that we will be using Pacific Time (3 hours behind Eastern Time) in our program schedule. All talk videos including Keynote, Contributed, and Spotlight will be uploaded to our Youtube DLG Channel after the KDD conference.

Workshop Program

Time Title Speakers/Authors
8:00-8:15pm Morning Session: Opening Remarks Jian Pei, Lingfei Wu, Tim Weninger
8:15-8:45am Keynote Talk 1: Graph Structure of Neural Networks: Good Neural Networks Are Alike [Slides][Video] Jure Leskovec, Stanford University, USA
8:45-9:15am Keynote Talk 2: Broad Learning Via Heterogenous Information Networks [Slides][Video] Philip S. Yu, University of Illinois at Chicago, USA
09:15-09:45pm Parallel Contributed Talks -- DLG Track

Talk 1: Learning Attribute-Structure Co-Evolutions in Dynamic Graphs [Slides][Video]

Daheng Wang, Zhihan Zhang, Yihong Ma, Tong Zhao, Tianwen Jiang, Nitesh V. Chawla, Meng Jiang

Talk 2: Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling [Slides][Video]

Maxwell Crouse, Ibrahim Abdelaziz, Cristina Cornelio, Veronika Thost, Lingfei Wu, Kenneth Forbus and Achille Fokoue

09:15-09:45pm Parallel Contributed Talks -- MLG Track

Talk 1: Understanding and Evaluating Structural Node Embeddings [Slides][Video]

Junchen Jin, et al.

Talk 2: Mining Persistent Activity in Continually Evolving Networks [Slides][Video]

Caleb Belth, et al.

09:45-10:15am Keynote Talk 3: Deep Graph Mining for Healthcare [Slides][Video] Fei Wang, Cornell University, USA
10:15-10:30pm Coffee Break/Social Networking
10:30-11:00am Keynote Talk 4: The Power of Summarization in Network Analysis [Slides][Video] Danai Koutra, University of Michigan, USA
11:00-11:30am Keynote Talk 5: Algorithmic Inductive Biases [Slides][Video] Petar Veličković, Deepmind, UK
11:30-12:00pm Parallel Poster Session (Spotlight Talks + LiveQA ) Breakout Z-rooms for both DLG and MLG
12:00-13:00pm Lunch Break
13:00-13:30am Keynote Talk 6: Deep Learning for Drug Development [Slides][Video] Jimeng Sun, University of Illinois Urbana-Champaign, USA
13:30-14:00pm Parallel Contributed Talks -- DLG Track

Talk 3: Demystifying Graph Neural Networks with Graph FilterAssessment [Slides][Video]

Yewen Wang, Ziniu Hu, Yusong Ye and Yizhou Sun

Talk 4: Early Fraud Detection with Augmented Graph Learning [Slides][Video]

Tong Zhao*, Bo Ni*, Wenhao Yu, Meng Jiang

13:30-14:00pm Parallel Contributed Talks -- MLG Track

Talk 3: BRGAN: Generating Graphs of Bounded Rank [Slides][Video]

William Shiao, et al.

Talk 4: Heterogeneous Threshold Estimation for Linear Threshold Modeling [Slides][Video]

Christopher Tran, et al.

14:00-14:30am Keynote Talk 7: Self-supervised Learning on Graphs: Deep Insights and New Directions [Slides][Video] Tyler Derr, Vanderbilt University, USA
14:30-14:45pm Coffee Break/Social Networking
14:45-15:15am Keynote Talk 8: Learning Graph Strcuture Features for Inductive Link Prediction and Matrix Completion [Slides][Video] Muhan Zhang, Facebook AI, USA
15:15-15:45am Keynote Talk 9: Cybersecurity with Graph Neural Networks [Slides][Video] Le Song, Georgia Institute of Technology, USA
15:45-16:00am Best Paper Award Ceremony + Final Remarks [Video] Jian Pei, Lingfei Wu, Yinglong Xia, Hongxia Yang, Jiezhong Qiu
16:00-17:00pm Parallel Poster Session (Spotlight Talks + LiveQA ) Breakout Z-rooms for both DLG and MLG

Accepted Papers

Call for Papers

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,

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.

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

Awards and Sponsors

  • Best Paper Awards: the program committee will nominate a paper for the Best Paper Award and a paper for the Best Student Paper Award. The Best (Student) Paper Awards will include a cash prize. Stay tuned for this year!
  • Travel Awards: students with accepted papers have a chance to apply for a travel award (up to $500).
  • Sponsorship: TBD

Important Dates

Paper Guidelines

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 KDD 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

This year DLG will be held jointly with The International Workshop on Mining and Learning with Graphs (MLG-KDD'20). DLG and MLG will maintain a separate submission website and program committee.

Contact information:

Keynote Speakers / Invited Panelists

Workshop Co-Chairs

Organizing Committee

Technical Program Committee

Past workshops