Workshop
New Frontiers in Graph Learning (GLFrontiers)
Jiaxuan You · Rex Ying · Hanjun Dai · Ge Liu · Azalia Mirhoseini · Smita Krishnaswamy · Chaoran Cheng
Hall C2 (level 1 gate 9 south of food court)
Fri 15 Dec, 7 a.m. PST
Overview: Graph learning has grown into an established sub-field of machine learning in recent years. 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. With the success of the New Frontiers in Graph Learning (GLFrontiers) Workshop in NeurIPS 2022, we hope to continue to promote the exchange of discussions and ideas regarding the future of graph learning in NeurIPS 2023.Challenges: Despite the success of graph learning in various applications, the recent machine learning research trends, especially the research towards foundation models and large language models, have posed challenges for the graph learning field. For example, regarding the model architecture, Transformer-based models have been shown to be superior to graph neural networks in certain small graph learning benchmarks. In terms of usability, with language as a generic user interface, it is still a research frontier to explore whether natural language can also interact with ubiquitous graph-structured data and whether it is feasible to build generic foundation models for graphs. Lastly, while graph learning has achieved recent exciting results in molecule and protein design, exploring how graph learning can accelerate scientific discoveries in other disciplines remains an open question.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. In GLFrontiers 2023, we specifically aim to discuss the future of graph learning in the era of foundation models and envision how graph learning can contribute to scientific discoveries.
Schedule
Fri 7:00 a.m. - 7:01 a.m.
|
Opening remarks
(
Opening remarks
)
>
SlidesLive Video |
Jiaxuan You 🔗 |
Fri 7:00 a.m. - 7:30 a.m.
|
Keynote talk: Retrieval Augmentation for LLMs
(
Keynote talk
)
>
SlidesLive Video |
Mohammad Shoeybi 🔗 |
Fri 7:30 a.m. - 8:00 a.m.
|
LLM Scaling: From Power Law to Sparsity
(
Keynote talk
)
>
SlidesLive Video |
Yanqi Zhou 🔗 |
Fri 8:00 a.m. - 8:30 a.m.
|
Coffee Break
(
Coffee Break
)
>
|
🔗 |
Fri 8:30 a.m. - 9:30 a.m.
|
Contributed talks from accepted papers
(
Contributed talks
)
>
SlidesLive Video |
🔗 |
Fri 9:30 a.m. - 11:30 a.m.
|
Poster session 1
(
Poster session
)
>
|
🔗 |
Fri 10:00 a.m. - 11:00 a.m.
|
Lunch break
(
Lunch break
)
>
|
🔗 |
Fri 11:30 a.m. - 12:00 p.m.
|
Keynote talk: Network Construction from Massive Text: Exploring the Power of Language Models
(
Keynote talk
)
>
SlidesLive Video |
Jiawei Han 🔗 |
Fri 12:00 p.m. - 12:30 p.m.
|
Keynote talk
(
Keynote talk
)
>
SlidesLive Video |
Marinka Zitnik 🔗 |
Fri 12:30 p.m. - 1:00 p.m.
|
Keynote talk: Towards Knowledge Foundation Models: Reasoning via Graph Schema Induction
(
Keynote talk
)
>
SlidesLive Video |
Manling Li 🔗 |
Fri 1:00 p.m. - 1:30 p.m.
|
Coffee Break
(
Coffee break
)
>
|
🔗 |
Fri 1:30 p.m. - 2:30 p.m.
|
Panel Discussion: Graphs in the Era of Foundation Models
(
Panel Discussion
)
>
SlidesLive Video |
Jiawei Han · Marinka Zitnik · Manling Li · Yanqi Zhou · Bryan Perozzi · Jiaxuan You · Rex Ying · Hanjun Dai 🔗 |
Fri 2:30 p.m. - 3:00 p.m.
|
Poster session 2
(
Poster session
)
>
|
🔗 |
-
|
Learning Genomic Sequence Representations using Graph Neural Networks over De Bruijn Graphs ( Poster ) > link | Kacper Kapusniak · Manuel Burger · Gunnar Rätsch · Amir Joudaki 🔗 |
-
|
On the Adversarial Robustness of Graph Contrastive Learning Methods ( Poster ) > link | Filippo Guerranti · Zinuo Yi · Anna Starovoit · Rafiq Kamel · Simon Geisler · Stephan Günnemann 🔗 |
-
|
A Simple and Scalable Representation for Graph Generation ( Poster ) > link | Yunhui Jang · Seul Lee · Sungsoo Ahn 🔗 |
-
|
Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Types ( Spotlight ) > link | Jianfei Gao · Yangze Zhou · Jincheng Zhou · Bruno Ribeiro 🔗 |
-
|
Local Differential Privacy in Graph Neural Networks: a Reconstruction Approach ( Poster ) > link | Karuna Bhaila · Wen Huang · Yongkai Wu · Xintao Wu 🔗 |
-
|
GenTKG: Generative Forecasting on Temporal Knowledge Graph ( Poster ) > link | Ruotong Liao · Xu Jia · Yunpu Ma · Volker Tresp 🔗 |
-
|
The Graph Lottery Ticket Hypothesis: Finding Sparse, Informative Graph Structure ( Poster ) > link | Anton Tsitsulin · Bryan Perozzi 🔗 |
-
|
Node Mutual Information: Enhancing Graph Neural Networks for Heterophily ( Poster ) > link | Seongjin Choi · Gahee Kim · Se-Young Yun 🔗 |
-
|
Low-Width Approximations and Sparsification for Scaling Graph Transformers ( Poster ) > link | Hamed Shirzad · Balaji Venkatachalam · Ameya Velingker · Danica J. Sutherland · David Woodruff 🔗 |
-
|
Knowledge Graphs are not Created Equal: Exploring the Properties and Structure of Real KGs ( Poster ) > link | Nedelina Teneva · Estevam Hruschka 🔗 |
-
|
FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks ( Poster ) > link | Qiying Pan · Ruofan Wu · Tengfei LIU · Tianyi Zhang · Yifei Zhu · Weiqiang Wang 🔗 |
-
|
PAN: Expressiveness of GNNs with Paths ( Poster ) > link | Caterina Graziani · Tamara Drucks · Monica Bianchini · Franco Scarselli · Thomas Gärtner 🔗 |
-
|
Poisoning $\times$ Evasion: Symbiotic Adversarial Robustness for Graph Neural Networks ( Poster ) > link | Ege Erdogan · Simon Geisler · Stephan Günnemann 🔗 |
-
|
Order Agnostic Autoregressive Graph Generation ( Poster ) > link | Edo Cohen-Karlik · Eyal Rozenberg · Daniel Freedman 🔗 |
-
|
GraphRNN Revisited: An Ablation Study and Extensions for Directed Acyclic Graphs ( Poster ) > link | Maya Ravichandran · Mark Koch · Taniya Das · Nikhil Khatri 🔗 |
-
|
Knowledge Graph Prompting for Multi-Document Question Answering ( Spotlight ) > link | Yu Wang · Nedim Lipka · Ryan Rossi · Alexa Siu · Ruiyi Zhang · Tyler Derr 🔗 |
-
|
DiP-GNN: Discriminative Pre-Training of Graph Neural Networks ( Poster ) > link | Simiao Zuo · Haoming Jiang · Qingyu Yin · Xianfeng Tang · Bing Yin · Tuo Zhao 🔗 |
-
|
Coupling Graph Neural Networks with Non-Integer Order Dynamics: A Robustness Study ( Poster ) > link | Qiyu Kang · Kai Zhao · Yang Song · Yihang Xie · Yanan Zhao · Sijie Wang · Rui She · Wee Peng Tay 🔗 |
-
|
Graph Pooling Provably Improves Expressivity ( Poster ) > link | Veronica Lachi · Alice Moallemy-Oureh · Andreas Roth · Pascal Welke 🔗 |
-
|
Can LLMs Effectively Leverage Graph Structural Information: When and Why ( Poster ) > link | Jin Huang · Xingjian Zhang · Qiaozhu Mei · Jiaqi Ma 🔗 |
-
|
Semi-Supervised Graph Imbalanced Regression ( Poster ) > link | Gang Liu · Tong Zhao · Eric Inae · Tengfei Luo · Meng Jiang 🔗 |
-
|
Beyond Text: A Deep Dive into Large Language Models' Ability on Understanding Graph Data ( Poster ) > link | Yuntong Hu · Zheng Zhang · Liang Zhao 🔗 |
-
|
Its All Graph To Me: Single-Model Graph Representation Learning on Multiple Domains ( Poster ) > link | Alex O. Davies · Riku Green · Nirav Ajmeri · Telmo Silva Filho 🔗 |
-
|
Long-Range Neural Atom Learning for Molecular Graphs ( Poster ) > link | Xuan Li · Zhanke Zhou · Jiangchao Yao · Yu Rong · Lu Zhang · Bo Han 🔗 |
-
|
Maximally Expressive GNNs for Outerplanar Graphs ( Spotlight ) > link | Franka Bause · Fabian Jogl · Patrick Indri · Tamara Drucks · David Penz · Nils M. Kriege · Thomas Gärtner · Pascal Welke · Maximilian Thiessen 🔗 |
-
|
Privacy-Utility Trade-offs in Neural Networks for Medical Population Graphs: Insights from Differential Privacy and Graph Structure ( Poster ) > link | Tamara Mueller · Maulik Chevli · Ameya Daigavane · Daniel Rueckert · Georgios Kaissis 🔗 |
-
|
Unsupervised Representation Learning of Brain Activity via Bridging Voxel Activity and Functional Connectivity ( Poster ) > link | Ali Behrouz · Parsa Delavari · Farnoosh Hashemi 🔗 |
-
|
HoloNets: Spectral Convolutions do extend to Directed Graphs ( Spotlight ) > link | Christian Koke · Daniel Cremers 🔗 |
-
|
Explaining Drug Repositioning: A Case-Based Reasoning Graph Neural Network Approach ( Poster ) > link | Adriana Carolina Gonzalez Cavazos 🔗 |
-
|
Subgraphormer: Subgraph GNNs meet Graph Transformers ( Poster ) > link | Guy Bar Shalom · Beatrice Bevilacqua · Haggai Maron 🔗 |
-
|
Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts ( Poster ) > link | Jonas Jürß · Lucie Charlotte Magister · Pietro Barbiero · Pietro Lió · Nikola Simidjievski 🔗 |
-
|
ProtoHG: Prototype-Enhanced Hypergraph Learning for Heterogeneous Information Networks ( Poster ) > link | Shuai Wang · Jiayi Shen · Athanasios Efthymiou · Stevan Rudinac · Monika Kackovic · Nachoem Wijnberg · Marcel Worring 🔗 |
-
|
Learning Multiplex Embeddings on Text-rich Networks with One Text Encoder ( Poster ) > link | Bowen Jin · Wentao Zhang · Yu Zhang · Yu Meng · Han Zhao · Jiawei Han 🔗 |
-
|
Non-backtracking Graph Neural Networks ( Spotlight ) > link | Seonghyun Park · Narae Ryu · Gahee Kim · Dongyeop Woo · Se-Young Yun · Sungsoo Ahn 🔗 |
-
|
Large Graph Models: A Perspective ( Poster ) > link | Ziwei Zhang · Haoyang Li · Zeyang Zhang · Yijian Qin · Xin Wang · Wenwu Zhu 🔗 |
-
|
Privacy-preserving design of graph neural networks with applications to vertical federated learning ( Poster ) > link | Ruofan Wu · Mingyang Zhang · Lingjuan Lyu · Xiaolong Xu · Xiuquan Hao · xinyi fu · Tengfei LIU · Tianyi Zhang · Weiqiang Wang 🔗 |
-
|
PowerGraph: A power grid benchmark dataset for graph neural networks ( Poster ) > link | Anna Varbella · Kenza Amara · Blazhe Gjorgiev · Giovanni Sansavini 🔗 |
-
|
Implicit Graph Neural Diffusion Based on Constrained Dirichlet Energy Minimization ( Poster ) > link | Guoji Fu · Mohammed Haroon Dupty · Yanfei Dong · Wee Sun Lee 🔗 |
-
|
RL4CO: a Unified Reinforcement Learning for Combinatorial Optimization Library ( Spotlight ) > link | Federico Berto · Chuanbo Hua · Junyoung Park · Minsu Kim · Hyeonah Kim · Jiwoo SON · HAEYEON KIM · joungho kim · Jinkyoo Park 🔗 |
-
|
Multimodal Graph Learning for Generative Tasks ( Poster ) > link | Minji Yoon · Jing Yu Koh · Bryan Hooi · Ruslan Salakhutdinov 🔗 |
-
|
CuriousWalk: Enhancing Multi-Hop Reasoning in Graphs with Random Network Distillation ( Poster ) > link | Varun Kausika · Saurabh Jha · Adya Jha · Amy Zhang · Michael Sury 🔗 |
-
|
Sparse but Strong: Crafting Adversarially Robust Graph Lottery Tickets ( Poster ) > link | Subhajit Dutta Chowdhury · Zhiyu Ni · Qingyuan Peng · Souvik Kundu · Pierluigi Nuzzo 🔗 |
-
|
ResolvNet: A Graph Convolutional Network with multi-scale Consistency ( Spotlight ) > link | Christian Koke · Abhishek Saroha · Yuesong Shen · Marvin Eisenberger · Daniel Cremers 🔗 |
-
|
On the modelling and impact of negative edges in graph convolutional networks for node classification ( Poster ) > link | Thu Trang Dinh · Julia Handl · Luis Ospina-Forero 🔗 |
-
|
VN-EGNN: Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification ( Spotlight ) > link | Florian Sestak · Lisa Schneckenreiter · Sepp Hochreiter · Andreas Mayr · Günter Klambauer 🔗 |
-
|
Hierarchical Relationships: A New Perspective to Enhance Scene Graph Generation ( Poster ) > link | Bowen Jiang · Camillo Taylor 🔗 |
-
|
Exploring the Potential of Large Language Models (LLMs) in Learning on Graph ( Poster ) > link |
11 presentersZhikai Chen · Haitao Mao · Hang Li · Wei Jin · Hongzhi Wen · Xiaochi Wei · Shuaiqiang Wang · Dawei Yin · Wenqi Fan · Hui Liu · Jiliang Tang |
-
|
One Node Per User: Node-Level Federated Learning for Graph Neural Networks ( Poster ) > link | zhidong gao · Yuanxiong Guo · Yanmin Gong 🔗 |
-
|
GraphRAG: Reasoning on Graphs with Retrieval-Augmented LLMs ( Poster ) > link | Zhen Han · Anand Muralidhar · Aditya Degala 🔗 |
-
|
How does over-squashing affect the power of GNNs? ( Spotlight ) > link | Francesco Di Giovanni · T. Konstantin Rusch · Michael Bronstein · Andreea-Ioana Deac · Marc Lackenby · Siddhartha Mishra · Petar Veličković 🔗 |
-
|
Beyond Erdos-Renyi: Generalization in Algorithmic Reasoning on Graphs ( Poster ) > link | Dobrik Georgiev · Pietro Lió · Jakub Bachurski · Junhua Chen · Tunan Shi 🔗 |
-
|
Graph Neural Networks Go Forward-Forward ( Poster ) > link | Daniele Paliotta · Mathieu Alain · Bálint Máté · François Fleuret 🔗 |
-
|
Towards Particle Flow Event Reconstruction at the Future Circular Collider with GNNs ( Poster ) > link | Dolores Garcia · Gregor Kržmanc · Philipp Zehetner · Jan Kieseler · Michele Selvaggi 🔗 |
-
|
EDGE++: Improved Training and Sampling of EDGE ( Poster ) > link | Xiaohui Chen · Mingyang Wu · Liping Liu 🔗 |
-
|
On the Temperature of Bayesian Graph Neural Networks for Conformal Prediction ( Poster ) > link | Seohyeon Cha · Honggu Kang · Joonhyuk Kang 🔗 |
-
|
Shedding Light on Random Dropping and Oversmoothing ( Poster ) > link | Han Xuanyuan · Tianxiang Zhao · Dongsheng Luo 🔗 |
-
|
Towards Foundation Models for Knowledge Graph Reasoning ( Poster ) > link | Michael Galkin · Xinyu Yuan · Hesham Mostafa · Jian Tang · Zhaocheng Zhu 🔗 |
-
|
A Multi-Task Perspective for Link Prediction with New Relation Types and Nodes ( Poster ) > link | Jincheng Zhou · Beatrice Bevilacqua · Bruno Ribeiro 🔗 |
-
|
Prompt Learning Unlocked for App Promotion in the Wild ( Poster ) > link | Zhongyu Ouyang · Shifu Hou · Shang Ma · Chaoran Chen · Chunhui Zhang · Toby Li · Xusheng Xiao · Xiangchi Yuan · Yanfang Ye 🔗 |
-
|
Uncertainty-Aware Robust Learning on Noisy Graphs ( Poster ) > link | Shuyi Chen · Kaize Ding · Shixiang Zhu 🔗 |
-
|
GAD-EBM: Graph Anomaly Detection using Energy-Based Models ( Poster ) > link | Amit Roy · Juan Shu · Olivier Elshocht · Jeroen Smeets · Ruqi Zhang · Pan Li 🔗 |
-
|
Linear Complexity Framework for Feature-Aware Graph Coarsening via Hashing ( Poster ) > link | Mohit Kataria · Aditi Khandelwal · ROCKTIM DAS · Sandeep Kumar · Jayadeva Dr 🔗 |
-
|
SATG : Structure Aware Transformers on Graphs for Node Classification ( Poster ) > link | Sumedh B G · Sanjay Patnala · Himil Vasava · Akshay Sethi · Sonia Gupta 🔗 |
-
|
What Improves the Generalization of Graph Transformer? A Theoretical Dive into Self-attention and Positional Encoding ( Poster ) > link | Hongkang Li · Meng Wang · Tengfei Ma · Sijia Liu · ZAIXI ZHANG · Pin-Yu Chen 🔗 |
-
|
TOD-Flow: Modeling the Structure of Task-Oriented Dialogues ( Poster ) > link | Sungryull Sohn · Yiwei Lyu · Anthony Liu · Lajanugen Logeswaran · Dong-Ki Kim · Dongsub Shim · Honglak Lee 🔗 |
-
|
Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction ( Spotlight ) > link | Arjun Subramonian · Levent Sagun · Yizhou Sun 🔗 |
-
|
Bridging the Gap: Towards Flexible, Efficient, and Effective Tensor Product Networks ( Poster ) > link | Nanxiang Wang · Chen Lin · Michael Bronstein · Philip Torr 🔗 |
-
|
ChatPathway: Conversational Large Language Models for Biology Pathway Detection ( Spotlight ) > link | Yanjing Li · Hannan Xu · Haiteng Zhao · Hongyu Guo · Shengchao Liu 🔗 |
-
|
Talk like a Graph: Encoding Graphs for Large Language Models ( Poster ) > link | Bahare Fatemi · Jonathan Halcrow · Bryan Perozzi 🔗 |
-
|
Motif-aware Attribute Masking for Molecular Graph Pre-training ( Spotlight ) > link | Eric Inae · Gang Liu · Meng Jiang 🔗 |
-
|
Graph Neural Networks on Discriminative Graphs of Words ( Poster ) > link | Yassine ABBAHADDOU · Johannes Lutzeyer · Michalis Vazirgiannis 🔗 |
-
|
Estimating Epistemic Uncertainty of Graph Neural Networks using Stochastic Centering ( Poster ) > link | Puja Trivedi · Mark Heimann · Rushil Anirudh · Danai Koutra · Jayaraman Thiagarajan 🔗 |
-
|
On the Consistency of GNN Explainability Methods ( Poster ) > link | Ehsan Hajiramezanali · Sepideh Maleki · Alex Tseng · Aicha BenTaieb · Gabriele Scalia · Tommaso Biancalani 🔗 |
-
|
GNN Predictions on k-hop Egonets Boosts Adversarial Robustness ( Poster ) > link | Jian Vora 🔗 |
-
|
GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks ( Poster ) > link | Taraneh Younesian · Thiviyan Thanapalasingam · Emile van Krieken · Daniel Daza · Peter Bloem 🔗 |
-
|
HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation ( Poster ) > link | Ce Zhang · Simon Stepputtis · Joseph Campbell · Katia Sycara · Yaqi Xie 🔗 |
-
|
Higher-Order Expander Graph Propagation ( Poster ) > link | Thomas Christie · Yu He 🔗 |
-
|
MCGC: an MLP-based supervised Contrastive learning framework for Graph Classification ( Poster ) > link | Xiao Yue · Bo Liu · Andrew Meng · Guangzhi Qu 🔗 |