Workshop
New Frontiers in Graph Learning
Jiaxuan You 路 Marinka Zitnik 路 Rex Ying 路 Yizhou Sun 路 Hanjun Dai 路 Stefanie Jegelka
Theater A
Fri 2 Dec, 6:40 a.m. PST
Background. In recent years, graph learning has quickly grown into an established sub-field of machine learning. Researchers have been focusing on developing novel model architectures, theoretical understandings, scalable algorithms and systems, and successful applications across industry and science regarding graph learning. In fact, more than 5000 research papers related to graph learning have been published over the past year alone.
Challenges. Despite the success, existing graph learning paradigms have not captured the full spectrum of relationships in the physical and the virtual worlds. For example, in terms of applicability of graph learning algorithms, current graph learning paradigms are often restricted to datasets with explicit graph representations, whereas recent works have shown promise of graph learning methods for applications without explicit graph representations. In terms of usability, while popular graph learning libraries greatly facilitate the implementation of graph learning techniques, finding the right graph representation and model architecture for a given use case still requires heavy expert knowledge. Furthermore, in terms of generalizability, unlike domains such as computer vision and natural language processing where large-scale pre-trained models generalize across downstream applications with little to no fine-tuning and demonstrate impressive performance, such a paradigm has yet to succeed in the graph learning domain.
Goal. The primary goal of this workshop is to expand the impact of graph learning beyond the current boundaries. We believe that graph, or relation data, is a universal language that can be used to describe the complex world. Ultimately, we hope graph learning will become a generic tool for learning and understanding any type of (structured) data. We aim to present and discuss the new frontiers in graph learning with researchers and practitioners within and outside the graph learning community. New understandings of the current challenges, new perspectives regarding the future directions, and new solutions and applications as proof of concepts are highly welcomed.
Scope and Topics. We welcome submissions regarding the new frontiers of graph learning, including but not limited to:
- Graphs in the wild: Graph learning for datasets and applications without explicit relational structure (e.g., images, text, audios, code). Novel ways of modeling structured/unstructured data as graphs are highly welcomed.
- Graphs in ML: Graph representations in general machine learning problems (e.g., neural architectures as graphs, relations among input data and learning tasks, graphs in large language models, etc.)
- New oasis: Graph learning methods that are significantly different from the current paradigms (e.g., large-scale pre-trained models, multi-task models, super scalable algorithms, etc.)
- New capabilities: Graph representation for knowledge discovery, optimization, causal inference, explainable ML, ML fairness, etc.
- Novel applications: Novel applications of graph learning in real-world industry and scientific domains. (e.g., graph learning for missing data imputation, program synthesis, etc.)
Call for papers
Submission deadline: Thursday, Sept 22, 2022 (16:59 PDT)
Submission site (OpenReview): NeurIPS 2022 GLFrontiers Workshop
Author notification: Thursday, Oct 6, 2022
Camera ready deadline: Thursday, Oct 27, 2022 (16:59 PDT)
Workshop (in person): Friday, Dec 2, 2022
The workshop will be held fully in person at the New Orleans Convention Center, as part of the NeurIPS 2022 conference. We also plan to offer livestream for the event, and more details will come soon.
We welcome both short research papers of up to 4 pages (excluding references and supplementary materials), and full-length research papers of up to 8 pages (excluding references and supplementary materials). All accepted papers will be presented as posters. We plan to select around 6 papers for oral presentations and 2 papers for the outstanding paper awards with potential cash incentives.
All submissions must use the NeurIPS template. We do not require the authors to include the checklist in the template. Submissions should be in .pdf format, and the review process is double-blind鈥攖herefore the papers should be appropriately anonymized. Previously published work (or under-review) is acceptable.
Should you have any questions, please reach out to us via email:
glfrontiers@googlegroups.com
Schedule
Fri 6:40 a.m. - 7:00 a.m.
|
Jiaxuan You
(
Opening remarks
)
>
SlidesLive Video |
Jiaxuan You 馃敆 |
Fri 7:00 a.m. - 7:30 a.m.
|
Invited talk: Kelsey Allen
(
Invited talk
)
>
SlidesLive Video |
Kelsey Allen 馃敆 |
Fri 7:30 a.m. - 8:00 a.m.
|
Invited talk: Azalia Mirhoseini
(
Invited talk
)
>
SlidesLive Video |
Azalia Mirhoseini 馃敆 |
Fri 8:30 a.m. - 9:00 a.m.
|
Oral presenters
(
Contributed talks: Part 1
)
>
SlidesLive Video |
馃敆 |
Fri 9:00 a.m. - 10:00 a.m.
|
All participants
(
Poster sessions: Morning
)
>
|
馃敆 |
Fri 10:00 a.m. - 11:00 a.m.
|
All participants
(
Lunch break
)
>
|
馃敆 |
Fri 11:00 a.m. - 11:30 a.m.
|
Invited talk: Francesco Di Giovanni
(
Invited talk
)
>
SlidesLive Video |
Francesco Di Giovanni 路 Francesco Di Giovanni 馃敆 |
Fri 11:30 a.m. - 12:00 p.m.
|
Invited talk: Matej Balog
(
Invited talk
)
>
SlidesLive Video |
Matej Balog 路 Matej Balog 馃敆 |
Fri 12:00 p.m. - 12:30 p.m.
|
Invited talk: Xavier Bresson
(
Invited talk
)
>
SlidesLive Video |
Xavier Bresson 馃敆 |
Fri 12:30 p.m. - 1:00 p.m.
|
Contributed talks: Part 2
(
Oral presenters
)
>
SlidesLive Video |
馃敆 |
Fri 1:00 p.m. - 1:30 p.m.
|
All participants
(
Coffee break
)
>
|
馃敆 |
Fri 1:30 p.m. - 2:15 p.m.
|
Panelists
(
Panel Discussions: The Future of Graph Learning
)
>
SlidesLive Video |
馃敆 |
Fri 2:15 p.m. - 3:00 p.m.
|
All participants
(
Poster sessions: Afternoon
)
>
|
馃敆 |
-
|
Spectrum Guided Topology Augmentation for Graph Contrastive Learning ( Poster ) > link | Lu Lin 路 Jinghui Chen 路 Hongning Wang 馃敆 |
-
|
Sketch-GNN: Scalable Graph Neural Networks with Sublinear Training Complexity ( Poster ) > link | Mucong Ding 路 Tahseen Rabbani 路 Bang An 路 Evan Wang 路 Furong Huang 馃敆 |
-
|
Graph Neural Networks for Selection of Preconditioners and Krylov Solvers ( Poster ) > link | Ziyuan Tang 路 Hong Zhang 路 Jie Chen 馃敆 |
-
|
Faster Hyperparameter Search on Graphs via Calibrated Dataset Condensation ( Poster ) > link | Mucong Ding 路 Xiaoyu Liu 路 Tahseen Rabbani 路 Furong Huang 馃敆 |
-
|
Sequence-Graph Duality: Unifying User Modeling with Self-Attention for Sequential Recommendation ( Poster ) > link | Zeren Shui 路 Ge Liu 路 Anoop Deoras 路 George Karypis 馃敆 |
-
|
How Powerful is Implicit Denoising in Graph Neural Networks ( Poster ) > link | Songtao Liu 路 Rex Ying 路 Hanze Dong 路 Lu Lin 路 Jinghui Chen 路 Dinghao Wu 馃敆 |
-
|
PolarMOT: How far can geometric relations take us in 3D multi-object tracking? ( Poster ) > link | Aleksandr Kim 路 Guillem Braso 路 Aljosa Osep 路 Laura Leal-Taix茅 馃敆 |
-
|
Agent-based Graph Neural Networks ( Poster ) > link | Karolis Martinkus 路 P谩l Andr谩s Papp 路 Benedikt Schesch 路 Roger Wattenhofer 馃敆 |
-
|
Dissimilar Nodes Improve Graph Active Learning ( Poster ) > link | Zhicheng Ren 路 Yifu Yuan 路 Yuxin Wu 路 Xiaxuan Gao 路 Yewen Wang 路 Yizhou Sun 馃敆 |
-
|
Convolutional Neural Networks on Manifolds: From Graphs and Back ( Poster ) > link | Zhiyang Wang 路 Luana Ruiz 路 Alejandro Ribeiro 馃敆 |
-
|
Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement ( Poster ) > link | Michael Chang 路 Alyssa L Dayan 路 Franziska Meier 路 Tom Griffiths 路 Sergey Levine 路 Amy Zhang 馃敆 |
-
|
Diffusion Models for Graphs Benefit From Discrete State Spaces ( Poster ) > link | Kilian Haefeli 路 Karolis Martinkus 路 Nathanael Perraudin 路 Roger Wattenhofer 馃敆 |
-
|
Multimodal Video Understanding using Graph Convolutional Network ( Poster ) > link | Ayush Singh 路 Vikram Gupta 馃敆 |
-
|
Condensing Graphs via One-Step Gradient Matching ( Poster ) > link | Wei Jin 路 Xianfeng Tang 路 Haoming Jiang 路 Zheng Li 路 Danqing Zhang 路 Jiliang Tang 路 Bing Yin 馃敆 |
-
|
From Local to Global: Spectral-Inspired Graph Neural Networks ( Poster ) > link | Ningyuan Huang 路 Soledad Villar 路 Carey E Priebe 路 Da Zheng 路 Chengyue Huang 路 Lin Yang 路 Vladimir Braverman 馃敆 |
-
|
Provably expressive temporal graph networks ( Poster ) > link | Amauri Souza 路 Diego Mesquita 路 Samuel Kaski 路 Vikas Garg 馃敆 |
-
|
pyGSL: A Graph Structure Learning Toolkit ( Poster ) > link | Max Wasserman 路 Gonzalo Mateos 馃敆 |
-
|
Improving Graph Neural Networks at Scale: Combining Approximate PageRank and CoreRank ( Poster ) > link | Ariel Ramos Vela 路 Johannes Lutzeyer 路 Anastasios Giovanidis 路 Michalis Vazirgiannis 馃敆 |
-
|
GraphWorld: Fake Graphs BringReal Insights for GNNs ( Poster ) > link | John Palowitch 路 Anton Tsitsulin 路 Bryan Perozzi 路 Brandon Mayer 馃敆 |
-
|
GLINKX: A Unified Framework for Large-scale Homophilous and Heterophilous Graphs ( Poster ) > link | Marios Papachristou 路 Rishab Goel 路 Frank Portman 路 Matthew Miller 路 Rong Jin 馃敆 |
-
|
Modular Flows: Differential Molecular Generation ( Poster ) > link | Yogesh Verma 路 Samuel Kaski 路 Markus Heinonen 路 Vikas Garg 馃敆 |
-
|
GIST: Distributed Training for Large-Scale Graph Convolutional Networks ( Poster ) > link | Cameron Wolfe 路 Jingkang Yang 路 Fangshuo Liao 路 Arindam Chowdhury 路 Chen Dun 路 Artun Bayer 路 Santiago Segarra 路 Anastasios Kyrillidis 馃敆 |
-
|
Neural Coarsening Process for Multi-level Graph Combinatorial Optimization ( Poster ) > link | Hyeonah Kim 路 Minsu Kim 路 Changhyun Kwon 路 Jinkyoo Park 馃敆 |
-
|
Graph Contrastive Learning with Cross-view Reconstruction ( Poster ) > link | Qianlong Wen 路 Zhongyu Ouyang 路 Chunhui Zhang 路 Yiyue Qian 路 Yanfang Ye 路 Chuxu Zhang 馃敆 |
-
|
Skeleton Clustering: Graph-Based Approach for Dimension-Free Density-Aided Clustering ( Poster ) > link | Zeyu Wei 路 Yen-Chi Chen 馃敆 |
-
|
AutoTransfer: AutoML with Knowledge Transfer - An Application to Graph Neural Networks ( Poster ) > link | Kaidi Cao 路 Jiaxuan You 路 Jiaju Liu 路 Jure Leskovec 馃敆 |
-
|
Individual Fairness in Dynamic Financial Networks ( Poster ) > link | Zixing Song 路 Yueen Ma 路 Irwin King 馃敆 |
-
|
Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks ( Poster ) > link | Sitao Luan 路 Mingde Zhao 路 Chenqing Hua 路 Xiao-Wen Chang 路 Doina Precup 馃敆 |
-
|
SPGP: Structure Prototype Guided Graph Pooling ( Poster ) > link | Sangseon Lee 路 Dohoon Lee 路 Yinhua Piao 路 Sun Kim 馃敆 |
-
|
ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks ( Poster ) > link | Yuelin Wang 路 Kai Yi 路 Xinliang Liu 路 Yuguang Wang 路 Shi Jin 馃敆 |
-
|
Expander Graph Propagation ( Poster ) > link | Andreea Deac 路 Marc Lackenby 路 Petar Veli膷kovi膰 馃敆 |
-
|
Modeling Hierarchical Topological Structure in Scientific Images with Graph Neural Networks ( Poster ) > link | Samuel Leventhal 路 Attila Gyulassy 路 Valerio Pascucci 路 Mark Heimann 馃敆 |
-
|
Variational Graph Auto-Encoders for Heterogeneous Information Network ( Poster ) > link | Abhishek Dalvi 路 Ayan Acharya 路 Jing Gao 路 Vasant Honavar 馃敆 |
-
|
Contrastive Graph Few-Shot Learning ( Poster ) > link | Chunhui Zhang 路 Hongfu Liu 路 Jundong Li 路 Yanfang Ye 路 Chuxu Zhang 馃敆 |
-
|
Shift-Robust Node Classification via Graph Clustering Co-training ( Poster ) > link | Qi Zhu 路 Chao Zhang 路 Chanyoung Park 路 Carl Yang 路 Jiawei Han 馃敆 |
-
|
Diving into Unified Data-Model Sparsity for Class-Imbalanced Graph Representation Learning ( Poster ) > link | Chunhui Zhang 路 Chao Huang 路 Yijun Tian 路 Qianlong Wen 路 Zhongyu Ouyang 路 Youhuan Li 路 Yanfang Ye 路 Chuxu Zhang 馃敆 |
-
|
Invertible Neural Networks for Graph Prediction ( Poster ) > link | Chen Xu 路 Xiuyuan Cheng 路 Yao Xie 馃敆 |
-
|
Efficient Automatic Machine Learning via Design Graphs ( Poster ) > link | Shirley Wu 路 Jiaxuan You 路 Jure Leskovec 路 Rex Ying 馃敆 |
-
|
Equivariant Graph Hierarchy-based Neural Networks ( Poster ) > link | Jiaqi Han 路 Yu Rong 路 Tingyang Xu 路 Wenbing Huang 馃敆 |
-
|
NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs ( Poster ) > link | Yijun Tian 路 Chuxu Zhang 路 Zhichun Guo 路 Xiangliang Zhang 路 Nitesh Chawla 馃敆 |
-
|
A New Graph Node Classification Benchmark: Learning Structure from Histology Cell Graphs ( Poster ) > link |
11 presentersClaudia Vanea 路 Jonathan Campbell 路 Omri Dodi 路 Liis Salum盲e 路 Karen Meir 路 Drorith Hochner 路 Hagit Hochner 路 Triin Laisk 路 Linda Ernst 路 Cecilia Lindgren 路 Christoffer Nellaker |
-
|
GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks ( Poster ) > link | Kenza Amara 路 Rex Ying 路 Zitao Zhang 路 Zhihao Han 路 Yinan Shan 路 Ulrik Brandes 路 Sebastian Schemm 馃敆 |
-
|
Learning Heterogeneous Interaction Strengths by Trajectory Prediction with Graph Neural Network ( Poster ) > link | Seungwoong Ha 路 Hawoong Jeong 馃敆 |
-
|
A Graph Is More Than Its Nodes: Towards Structured Uncertainty-Aware Learning on Graphs ( Poster ) > link | Hans Hao-Hsun Hsu 路 Yuesong Shen 路 Daniel Cremers 馃敆 |
-
|
Expectation Complete Graph Representations using Graph Homomorphisms ( Poster ) > link | Maximilian Thiessen 路 Pascal Welke 路 Thomas G盲rtner 馃敆 |
-
|
antGLasso: An Efficient Tensor Graphical Lasso Algorithm ( Poster ) > link | Bailey Andrew 路 David Westhead 路 Luisa Cutillo 馃敆 |
-
|
Certified Graph Unlearning ( Poster ) > link | Eli Chien 路 Chao Pan 路 Olgica Milenkovic 馃敆 |
-
|
New Frontiers in Graph Autoencoders: Joint Community Detection and Link Prediction ( Poster ) > link | Guillaume SALHA 路 Johannes Lutzeyer 路 George Dasoulas 路 Romain Hennequin 路 Michalis Vazirgiannis 馃敆 |
-
|
A Simple Hypergraph Kernel Convolution based on Discounted Markov Diffusion Process ( Poster ) > link | Fuyang Li 路 Jiying Zhang 路 Xi Xiao 路 bin zhang 路 Dijun Luo 馃敆 |
-
|
GraphCG: Unsupervised Discovery of Steerable Factors in Graphs ( Poster ) > link | Shengchao Liu 路 Chengpeng Wang 路 Weili Nie 路 Hanchen Wang 路 Jiarui Lu 路 Bolei Zhou 路 Jian Tang 馃敆 |
-
|
Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank ( Poster ) > link | Alessandro Epasto 路 Vahab Mirrokni 路 Bryan Perozzi 路 Anton Tsitsulin 路 Peilin Zhong 馃敆 |
-
|
A deep learning approach to recover conditional independence graphs ( Poster ) > link | Harsh Shrivastava 路 Urszula Chajewska 路 Robin Abraham 路 Xinshi Chen 馃敆 |
-
|
On the Unreasonable Effectiveness of Feature Propagation in Learning on Graphs with Missing Node Features ( Poster ) > link | Emanuele Rossi 路 Henry Kenlay 路 Maria Gorinova 路 Benjamin Chamberlain 路 Xiaowen Dong 路 Michael Bronstein 馃敆 |
-
|
Empowering Language Models with Knowledge Graph Reasoning for Question Answering ( Poster ) > link | Ziniu Hu 路 Yichong Xu 路 Wenhao Yu 路 Shuohang Wang 路 Ziyi Yang 路 Chenguang Zhu 路 Kai-Wei Chang 路 Yizhou Sun 馃敆 |
-
|
COIN: Co-Cluster Infomax for Bipartite Graphs ( Poster ) > link | Baoyu Jing 路 Yuchen Yan 路 Yada Zhu 路 Hanghang Tong 馃敆 |