Jian Tang

A Foundation Model for Zero-shot Logical Query Reasoning

Mikhail Galkin

Jincheng Zhou

Bruno Ribeiro

Zhaocheng Zhu

Complex logical query answering (CLQA) in knowledge graphs (KGs) goes beyond simple KG completion and aims at answering compositional querie… (see more)s comprised of multiple projections and logical operations. Existing CLQA methods that learn parameters bound to certain entity or relation vocabularies can only be applied to the graph they are trained on which requires substantial training time before being deployed on a new graph. Here we present UltraQuery, the first foundation model for inductive reasoning that can zero-shot answer logical queries on any KG. The core idea of UltraQuery is to derive both projections and logical operations as vocabulary-independent functions which generalize to new entities and relations in any KG. With the projection operation initialized from a pre-trained inductive KG completion model, UltraQuery can solve CLQA on any KG after finetuning on a single dataset. Experimenting on 23 datasets, UltraQuery in the zero-shot inference mode shows competitive or better query answering performance than best available baselines and sets a new state of the art on 15 of them.

2024-09-25

NeurIPS.cc/2024/Conference (poster)

Multi-Scale Representation Learning for Protein Fitness Prediction

Zuobai Zhang

Pascal Notin

Yining Huang

Aurelie Lozano

Vijil Chenthamarakshan

Debora Susan Marks

Payel Das

Designing novel functional proteins crucially depends on accurately modeling their fitness landscape. Given the limited availability of func… (see more)tional annotations from wet-lab experiments, previous methods have primarily relied on self-supervised models trained on vast, unlabeled protein sequence or structure datasets. While initial protein representation learning studies solely focused on either sequence or structural features, recent hybrid architectures have sought to merge these modalities to harness their respective strengths. However, these sequence-structure models have so far achieved only incremental improvements when compared to the leading sequence-only approaches, highlighting unresolved challenges effectively leveraging these modalities together. Moreover, the function of certain proteins is highly dependent on the granular aspects of their surface topology, which have been overlooked by prior models. To address these limitations, we introduce the Sequence-Structure-Surface Fitness (**S3F**) model — a novel multimodal representation learning framework that integrates protein features across several scales. Our approach combines sequence representations from a protein language model with Geometric Vector Perceptron networks encoding protein backbone and detailed surface topology. The proposed method achieves state-of-the-art fitness prediction on the ProteinGym benchmark encompassing 217 substitution deep mutational scanning assays, and provides insights into the determinants of protein function. Our code is at https://github.com/DeepGraphLearning/S3F.

2024-09-25

NeurIPS.cc/2024/Conference (poster)

Are Heterophily-Specific GNNs and Homophily Metrics Really Effective? Evaluation Pitfalls and New Benchmarks

Sitao Luan

Qincheng Lu

Chenqing Hua

Xinyu Wang

Jiaqi Zhu

Xiao-Wen Chang

Guy Wolf

Over the past decade, Graph Neural Networks (GNNs) have achieved great success on machine learning tasks with relational data. However, rece… (see more)nt studies have found that heterophily can cause significant performance degradation of GNNs, especially on node-level tasks. Numerous heterophilic benchmark datasets have been put forward to validate the efficacy of heterophily-specific GNNs and various homophily metrics have been designed to help people recognize these malignant datasets. Nevertheless, there still exist multiple pitfalls that severely hinder the proper evaluation of new models and metrics. In this paper, we point out three most serious pitfalls: 1) a lack of hyperparameter tuning; 2) insufficient model evaluation on the real challenging heterophilic datasets; 3) missing quantitative evaluation benchmark for homophily metrics on synthetic graphs. To overcome these challenges, we first train and fine-tune baseline models on

2024-09-09

ArXiv (preprint)

The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges

Sitao Luan

Chenqing Hua

Qincheng Lu

Liheng Ma

Lirong Wu

Xinyu Wang

Minkai Xu

Xiao-Wen Chang

Doina Precup

Rex Ying

Stan Z. Li

Guy Wolf

Stefanie Jegelka

Homophily principle, \ie{} nodes with the same labels or similar attributes are more likely to be connected, has been commonly believed to b… (see more)e the main reason for the superiority of Graph Neural Networks (GNNs) over traditional Neural Networks (NNs) on graph-structured data, especially on node-level tasks. However, recent work has identified a non-trivial set of datasets where GNN's performance compared to the NN's is not satisfactory. Heterophily, i.e. low homophily, has been considered the main cause of this empirical observation. People have begun to revisit and re-evaluate most existing graph models, including graph transformer and its variants, in the heterophily scenario across various kinds of graphs, e.g. heterogeneous graphs, temporal graphs and hypergraphs. Moreover, numerous graph-related applications are found to be closely related to the heterophily problem. In the past few years, considerable effort has been devoted to studying and addressing the heterophily issue. In this survey, we provide a comprehensive review of the latest progress on heterophilic graph learning, including an extensive summary of benchmark datasets and evaluation of homophily metrics on synthetic graphs, meticulous classification of the most updated supervised and unsupervised learning methods, thorough digestion of the theoretical analysis on homophily/heterophily, and broad exploration of the heterophily-related applications. Notably, through detailed experiments, we are the first to categorize benchmark heterophilic datasets into three sub-categories: malignant, benign and ambiguous heterophily. Malignant and ambiguous datasets are identified as the real challenging datasets to test the effectiveness of new models on the heterophily challenge. Finally, we propose several challenges and future directions for heterophilic graph representation learning.

2024-07-12

ArXiv (preprint)

The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges

Sitao Luan

Chenqing Hua

Qincheng Lu

Liheng Ma

Lirong Wu

Xinyu Wang

Minkai Xu

Xiao-Wen Chang

Doina Precup

Rex Ying

Stan Z. Li

Guy Wolf

Stefanie Jegelka

Homophily principle, \ie{} nodes with the same labels or similar attributes are more likely to be connected, has been commonly believed to b… (see more)e the main reason for the superiority of Graph Neural Networks (GNNs) over traditional Neural Networks (NNs) on graph-structured data, especially on node-level tasks. However, recent work has identified a non-trivial set of datasets where GNN's performance compared to the NN's is not satisfactory. Heterophily, i.e. low homophily, has been considered the main cause of this empirical observation. People have begun to revisit and re-evaluate most existing graph models, including graph transformer and its variants, in the heterophily scenario across various kinds of graphs, e.g. heterogeneous graphs, temporal graphs and hypergraphs. Moreover, numerous graph-related applications are found to be closely related to the heterophily problem. In the past few years, considerable effort has been devoted to studying and addressing the heterophily issue. In this survey, we provide a comprehensive review of the latest progress on heterophilic graph learning, including an extensive summary of benchmark datasets and evaluation of homophily metrics on synthetic graphs, meticulous classification of the most updated supervised and unsupervised learning methods, thorough digestion of the theoretical analysis on homophily/heterophily, and broad exploration of the heterophily-related applications. Notably, through detailed experiments, we are the first to categorize benchmark heterophilic datasets into three sub-categories: malignant, benign and ambiguous heterophily. Malignant and ambiguous datasets are identified as the real challenging datasets to test the effectiveness of new models on the heterophily challenge. Finally, we propose several challenges and future directions for heterophilic graph representation learning.

2024-07-12

ArXiv (preprint)

In-Context Learning, Can It Break Safety?

Sophie Xhonneux

David Dobre

Michael Noukhovitch

Gauthier Gidel

Dhanya Sridhar

2024-06-28

ICML.cc/2024/Workshop/NextGenAISafety (poster)

Augmenting Evolutionary Models with Structure-based Retrieval

Yining Huang

Zuobai Zhang

Debora Susan Marks

Pascal Notin

2024-06-17

ICML.cc/2024/Workshop/ML4LMS (poster)

GraphAny: A Foundation Model for Node Classification on Any Graph

Jianan Zhao

Hesham Mostafa

Mikhail Galkin

Michael M. Bronstein

Zhaocheng Zhu

Foundation models that can perform inference on any new task without requiring specific training have revolutionized machine learning in vis… (see more)ion and language applications. However, applications involving graph-structured data remain a tough nut for foundation models, due to challenges in the unique feature- and label spaces associated with each graph. Traditional graph ML models such as graph neural networks (GNNs) trained on graphs cannot perform inference on a new graph with feature and label spaces different from the training ones. Furthermore, existing models learn functions specific to the training graph and cannot generalize to new graphs. In this work, we tackle these two challenges with a new foundational architecture for inductive node classification named GraphAny. GraphAny models inference on a new graph as an analytical solution to a LinearGNN, thereby solving the first challenge. To solve the second challenge, we learn attention scores for each node to fuse the predictions of multiple LinearGNNs. Specifically, the attention module is carefully parameterized as a function of the entropy-normalized distance-features between multiple LinearGNNs predictions to ensure generalization to new graphs. Empirically, GraphAny trained on the Wisconsin dataset with only 120 labeled nodes can effectively generalize to 30 new graphs with an average accuracy of 67.26\% in an inductive manner, surpassing GCN and GAT trained in the supervised regime, as well as other inductive baselines.

2024-05-30

ArXiv (preprint)

GraphAny: A Foundation Model for Node Classification on Any Graph

Jianan Zhao

Hesham Mostafa

Mikhail Galkin

Michael M. Bronstein

Zhaocheng Zhu

2024-05-30

ArXiv (preprint)

The 1st International Workshop on Graph Foundation Models (GFM)

Haitao Mao

Jianan Zhao

Xiaoxin He

Zhikai Chen

Qian Huang

Zhaocheng Zhu

Micheal Bronstein

Xavier Bresson

Bryan Hooi

Haiyang Zhang

Xianfeng Tang

Luo Chen

Jiliang Tang

2024-05-13

Companion Proceedings of the ACM on Web Conference 2024 (published)

Dynamic System Modeling Using a Multisource Transfer Learning-Based Modular Neural Network for Industrial Application

Haoshan Duan

Xi Meng

JunFei Qiao

Establishing an accurate model of dynamic systems poses a challenge for complex industrial processes. Due to the ability to handle complex t… (see more)asks, modular neural networks (MNN) have been widely applied to industrial process modeling. However, the phenomenon of domain drift caused by operating conditions may lead to a cold start of the model, which affects the performance of MNN. For this reason, a multisource transfer learning-based MNN (MSTL-MNN) is proposed in this study. First, the knowledge-driven transfer learning process is performed with domain similarity evaluation, knowledge extraction, and fusion, aiming to form an initial subnetwork in the target domain. Then, the positive transfer process of effective knowledge can avoid the cold start problem of MNN. Second, during the data-driven fine-tuning process, a regularized self-organizing long short-term memory algorithm is designed to fine-tune the structure and parameters of the initial subnetwork, which can improve the prediction performance of MNN. Meanwhile, relevant theoretical analysis is given to ensure the feasibility of MSTL-MNN. Finally, the effectiveness of the proposed method is confirmed by two benchmark simulations and a real industrial dataset of a municipal solid waste incineration process. Experimental results demonstrate the merits of MSTL-MNN for industrial applications.

2024-05-01

IEEE Transactions on Industrial Informatics (published)