We invite participation in the Graph Neural Networks and Systems Workshop, to be held in conjunction with MLSys 2021.
Livestream Information
The workshop will be live-streamed on April 9th 7am-4pm PST, from the MLSys conference website. The schedule and live are available at this address:
https://mlsys.org/virtual/2021/workshop/1642
You need to register to MLSys to watch the workshop ($25 for students and $100 for others):
https://mlsys.org/Register/view-registration
Overview
Graph Neural Networks (GNNs) have emerged as one of the hottest areas of research in the field of machine learning and artificial intelligence. The core idea is to explore the relationships among data samples to learn high-quality node, edge, and graph representations. In just the span of a few years, GNNs have expanded from mostly theoretical and small-scale studies to providing state-of-the-art solutions to many problems arising in diverse application domains. This includes domains that traditionally relied on graph learning (e.g., information retrieval, recommendations, fraud detection, knowledge representation), to science and engineering domains whose underlying data can be naturally represented via graphs (e.g., chemistry, bioinformatics, drug discoveries, material science, physics, circuit design), and to areas of science and engineering that have not traditionally been the domain of graph methods (e.g., computer vision, natural language processing, computer graphics, reinforcement learning).
GNN research and application present new and unique challenges to system designs. Industrial users and researchers share the same requirements in some of the requirements, but diverge in others. This landscape also rapidly evolves as new research results appear.
In the same spirit as MLSys, the goal of this workshop is to bring together experts working at the intersection of machine learning research and systems building, with a particular focus on GNN. Topics include, but not limited to:
- Systems for training and serving GNN models at scale
- System-level techniques to deal with complex graphs (heterogeneous, dynamic, temporal, etc.)
- Integration with graph and relational databases
- Distributed GNN training algorithms for large graphs
- Best practices to integrate with existing machine learning pipelines
- Specialized or custom hardware for GNN
- GNN model understanding tools (debugging, visualization, introspection, etc.)
- GNN applications to improve system design and optimizations
Through invited talks as well as oral and poster presentations by the participants, this workshop will showcase the latest advances in GNN systems and address challenges at the intersection of and GNN research and system design.
Dual submissions: The workshop proceedings will be published on the workshop website, but are considered non-archival for the purposes of dual submissions. We welcome work that has already been published or is under submission to a conference, and publishing at the workshop should not preclude you from submitting to conferences in the future. However, please check any conference policies as well.
- Xavier Bresson (NTU, Singapore)
- Michael Bronstein (Imperial College London/Twitter)
- Stefanie Jegelka (MIT)
- George Karypis (University of Minnesota/AWS ML)
- Petar Veličković (DeepMind)
- Zheng Zhang (NYU Shanghai/AWS ML)
- Jonathan Godwin (DeepMind)
- George Karypis (University of Minnesota/AWS ML)
- Nicholas Lane (Cambridge)
- Gianandrea Minneci (Graphcore)
- Azalia Mirhoseini (Google)
- Emanuele Rossi (Imperial/Twitter)
- Savannah Thais (Princeton)
- Marinka Zitnik (Harvard)
- Adam Lerer (Facebook)
- Jonathan Godwin (DeepMind)
- Jinyang Li (NYU)
- Zhihao Jia (CMU)
- Minjie Wang (AWS ML)
- Da Zheng (AWS ML)
- Yibo Zhu (ByteDance)
- Chen Li (USTC)
- Haggai Maron (NVIDIA Research)
- Daniele Grattarola (Università della Svizzera Italiana)
- Emanuele Rossi (Twitter)
- Federico Monti (Twitter)
- Ben Day (University of Cambridge)
- Nikolaos Karalias (EPFL)
- Arian Jamasb (University of Cambridge)
- Cristian Bodnar (University of Cambridge)
- Andreas Loukas (EPFL)
- Fabrizio Frasca (Twitter)
- Vijay Prakash Dwivedi (NTU)
- Ron Levie (TU Berlin)
- Matthias Fey (TU Dortmund University)
- Chi Thang Duong (EPFL)
- Eda Bayram (EPFL)
- Christopher Morris (Polytechnique Montréal)
- Cătălina Cangea (University of Cambridge)
- Clement Vignac (EPFL)
- Andrew Wang (Stanford University)
- Beliz Gunel (Stanford University)
- Xiang Ren (University of Southern California)
- Rex Ying (Stanford University)
- Bryan Perozzi (Google Research)
- Gabriele Corso (University of Cambridge)
- Lovro Vrcek (A-Star)
- Felix Opolka (University of Cambridge)
- Emma Rocheteau (University of Cambridge)
- Boris Knyazev (University of Guelph)
- David Vázquez (Element AI)
- Jakub Kuba Łącki (Google)
- Jonathan Halcrow (Google)
- Perouz Taslakian (Element AI)
- Joey Bose (McGill University)
- Frederic Sala (University of Wisconsin)
- Helena Andrés-Terre (University of Cambridge)
- Jiaxuan You (Stanford University)
- Jun Gao (University of Toronto)
- Vitaly Kurin (University of Oxford)
- Andrei Nicolicioiu (Bitdefender)
- Hanjun Dai (Georgia Institute of Technology)
- Yao Ma (Michigan State University)
- Marc Brockschmidt (Microsoft Research Cambridge)
- Pim de Haan (University of Amsterdam)
- Louis-Pascal Xhonneux (MILA)
- Moshe Eliasof (Ben-Gurion University)
- Michal Valko (DeepMind)
- Weihua Hu (Stanford University)
- Or Litany (NVIDIA)
- Min Jae Song (NYU)
- Simeon Spasov (University of Cambridge)
- Victor Garcia Satorras (University of Amsterdam)
- Gilad Yehudai (Weizmann Institute of Science)
- Tiago Azevedo (Arm ML Research Lab)
- Komal Teru (McGill University)
- Tyler Derr (Vanderbilt University)
- Xiaowen Dong (University of Oxford)
- Paul Scherer (University of Cambridge)
- Zhengdao Chen (NYU)
- David Low Jia Wei (NTU)
- Vikash Singh (Google X)
- Zhaocheng Zhu (MILA)
- Matthew Overlan (DeepMind)
- Momchil Peychev (ETH Zürich)
- Sarah Parisot (Huawei Noah’s Ark Lab)
Submission Instructions
- Submissions can be up to 6 pages (not including references).
- All submissions must be in PDF and follow the the format outlined for MLSys 2021
- Submissions do not have to be anonymized
- Please submit your paper using the EasyChair link
Important Dates
- Submission Deadline:
March 7, 2021March 19, 2021 - Acceptance Notifications:
March 15, 2021March 29, 2021 - Workshop: Friday, April 9, 2021
Accepted Papers
- Chaoyang He, Keshav Balasubramanian, Emir Ceyani, Yu Rong, Peilin Zhao, Junzhou Huang, Murali Annavaram and Salman Avestimehr, FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks, paper, poster.
- David Pujol-Perich, José Suárez-Varela, Miquel Ferriol-Galmés, Shihan Xiao, Bo Wu, Albert Cabellos-Aparicio and Pere Barlet-Ros, IGNNITION: A framework for fast prototyping of Graph Neural Networks, paper, poster.
- Shyam Tailor, Felix Opolka, Pietro Lio and Nicholas Lane, Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions paper, poster.
- David Pujol-Perich, José Suárez-Varela, Shihan Xiao, Bo Wu, Albert Cabellos-Aparicio and Pere Barlet-Ros, NetXplain: Real-time explainability of Graph Neural Networks applied to Computer Networks paper, poster.
- Youhui Bai, Cheng Li, Zhiqi Lin, Yufei Wu, Youshan Miao, Yunxin Liu and Yinlong Xu, Efficient Data Loader for Fast Sampling-based GNN Training on Large Graphs, paper, poster.
- Dominique Beaini, Saro Passaro, Vincent Létourneau, William L. Hamilton, Gabriele Corso and Pietro Lio, Directional Graph Networks, paper, poster.
- Zhiqiang Xie, Zihao Ye, Minjie Wang, Zheng Zhang and Rui Fan, Graphiler: A Compiler for Graph Neural Networks, paper, poster.
- Matthew T. Dearing and Xiaoyan Wang, Analyzing the Performance of Graph Neural Networks with Pipe Parallelism, paper, poster.
- Alok Tripathy, Katherine Yelick and Aydin Buluc, Reducing Communication in Graph Neural Network Training, paper, poster.
- Yao Xiao, Guixiang Ma, Nesreen K. Ahmed, Theodore L. Willke, Shahin Nazarian and Paul Bogdan, Deep Graph Learning for Program Analysis and System Optimization, paper, poster.
- Loc Hoang, Xuhao Chen, Hochan Lee, Roshan Dathathri, Gurbinder Gill and Keshav Pingali, Effiicent Distribution for Deep Learning on Large Graphs, paper, poster.
- Qidong Su, Minjie Wang, Da Zheng and Zheng Zhang, Load Balancing for Parallel GNN Training, paper, poster.
- Gustavo Lima de Oliveira, Ricardo Marcondes Marcacini and Maria da Graça Campos Pimentel, Privacy-Preserving Heterogeneous Network Embedding for Clinical Events, paper, poster.
Contact us at gnnsys21@easychair.org