Search Results for author: Muhan Zhang

Found 54 papers, 39 papers with code

Highly Accurate Disease Diagnosis and Highly Reproducible Biomarker Identification with PathFormer

no code implementations11 Feb 2024 Zehao Dong, Qihang Zhao, Philip R. O. Payne, Michael A Province, Carlos Cruchaga, Muhan Zhang, Tianyu Zhao, Yixin Chen, Fuhai Li

However, we found two major limitations of existing GNNs in omics data analysis, i. e., limited-prediction (diagnosis) accuracy and limited-reproducible biomarker identification capacity across multiple datasets.

On the Completeness of Invariant Geometric Deep Learning Models

no code implementations7 Feb 2024 Zian Li, Xiyuan Wang, Shijia Kang, Muhan Zhang

Our results fill the gap in the theoretical power of invariant models, contributing to a rigorous and comprehensive understanding of their capabilities.

Computational Efficiency Inductive Bias

Latent Graph Diffusion: A Unified Framework for Generation and Prediction on Graphs

no code implementations4 Feb 2024 Zhou Cai, Xiyuan Wang, Muhan Zhang

We first propose Latent Graph Diffusion (LGD), a generative model that can generate node, edge, and graph-level features of all categories simultaneously.

Graph Learning regression

PyTorch Geometric High Order: A Unified Library for High Order Graph Neural Network

1 code implementation28 Nov 2023 Xiyuan Wang, Muhan Zhang

We introduce PyTorch Geometric High Order (PyGHO), a library for High Order Graph Neural Networks (HOGNNs) that extends PyTorch Geometric (PyG).

Chain of Images for Intuitively Reasoning

1 code implementation9 Nov 2023 Fanxu Meng, Haotong Yang, Yiding Wang, Muhan Zhang

The human brain is naturally equipped to comprehend and interpret visual information rapidly.

Common Sense Reasoning Language Modelling +2

LooGLE: Can Long-Context Language Models Understand Long Contexts?

1 code implementation8 Nov 2023 Jiaqi Li, Mengmeng Wang, Zilong Zheng, Muhan Zhang

In this paper, we present LooGLE, a Long Context Generic Language Evaluation benchmark for LLMs' long context understanding.

In-Context Learning Question Answering

Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes

1 code implementation NeurIPS 2023 Cai Zhou, Xiyuan Wang, Muhan Zhang

Second, on $1$-simplices or edge level, we bridge edge-level random walk and Hodge $1$-Laplacians and design corresponding edge PE respectively.

Neural Attention: Enhancing QKV Calculation in Self-Attention Mechanism with Neural Networks

1 code implementation17 Oct 2023 Muhan Zhang

In the realm of deep learning, the self-attention mechanism has substantiated its pivotal role across a myriad of tasks, encompassing natural language processing and computer vision.

Explaining the Complex Task Reasoning of Large Language Models with Template-Content Structure

no code implementations9 Oct 2023 Haotong Yang, Fanxu Meng, Zhouchen Lin, Muhan Zhang

Our framework offers an explanatory tool for the complex reasoning abilities of large language models from the perspective of modeling autoregressive generation tasks.

Answer Generation Language Modelling

One for All: Towards Training One Graph Model for All Classification Tasks

1 code implementation29 Sep 2023 Hao liu, Jiarui Feng, Lecheng Kong, Ningyue Liang, DaCheng Tao, Yixin Chen, Muhan Zhang

For in-context learning on graphs, OFA introduces a novel graph prompting paradigm that appends prompting substructures to the input graph, which enables it to address varied tasks without fine-tuning.

Graph Classification Graph Learning +3

Graph Contrastive Learning Meets Graph Meta Learning: A Unified Method for Few-shot Node Tasks

1 code implementation19 Sep 2023 Hao liu, Jiarui Feng, Lecheng Kong, DaCheng Tao, Yixin Chen, Muhan Zhang

In our study, we first identify two crucial advantages of contrastive learning compared to meta learning, including (1) the comprehensive utilization of graph nodes and (2) the power of graph augmentations.

CoLA Contrastive Learning +3

Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power

1 code implementation NeurIPS 2023 Junru Zhou, Jiarui Feng, Xiyuan Wang, Muhan Zhang

Many of the proposed GNN models with provable cycle counting power are based on subgraph GNNs, i. e., extracting a bag of subgraphs from the input graph, generating representations for each subgraph, and using them to augment the representation of the input graph.

CktGNN: Circuit Graph Neural Network for Electronic Design Automation

1 code implementation31 Aug 2023 Zehao Dong, Weidong Cao, Muhan Zhang, DaCheng Tao, Yixin Chen, Xuan Zhang

The electronic design automation of analog circuits has been a longstanding challenge in the integrated circuit field due to the huge design space and complex design trade-offs among circuit specifications.

Bayesian Optimization Graph Learning

VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs

1 code implementation4 Aug 2023 Ling Yang, Ye Tian, Minkai Xu, Zhongyi Liu, Shenda Hong, Wei Qu, Wentao Zhang, Bin Cui, Muhan Zhang, Jure Leskovec

To address this issue, we propose to learn a new powerful graph representation space by directly labeling nodes' diverse local structures for GNN-to-MLP distillation.

Knowledge Distillation Quantization +1

Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman

1 code implementation NeurIPS 2023 Jiarui Feng, Lecheng Kong, Hao liu, DaCheng Tao, Fuhai Li, Muhan Zhang, Yixin Chen

We theoretically prove that even if we fix the space complexity to $O(n^k)$ (for any $k\geq 2$) in $(k, t)$-FWL, we can construct an expressiveness hierarchy up to solving the graph isomorphism problem.

Graph Regression

Code Prompting: a Neural Symbolic Method for Complex Reasoning in Large Language Models

no code implementations29 May 2023 Yi Hu, Haotong Yang, Zhouchen Lin, Muhan Zhang

We also consider the ensemble of code prompting and CoT prompting to combine the strengths of both.

Arithmetic Reasoning

Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners

1 code implementation24 May 2023 Xiaojuan Tang, Zilong Zheng, Jiaqi Li, Fanxu Meng, Song-Chun Zhu, Yitao Liang, Muhan Zhang

On the whole, our analysis provides a novel perspective on the role of semantics in developing and evaluating language models' reasoning abilities.

From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks

1 code implementation8 May 2023 Cai Zhou, Xiyuan Wang, Muhan Zhang

Relational pooling is a framework for building more expressive and permutation-invariant graph neural networks.

Improving Graph Neural Networks on Multi-node Tasks with Labeling Tricks

no code implementations20 Apr 2023 Xiyuan Wang, Pan Li, Muhan Zhang

When we want to learn a node-set representation involving multiple nodes, a common practice in previous works is to directly aggregate the single-node representations obtained by a GNN.

Hyperedge Prediction Link Prediction +1

Towards Better Evaluation of GNN Expressiveness with BREC Dataset

2 code implementations16 Apr 2023 Yanbo Wang, Muhan Zhang

Research on the theoretical expressiveness of Graph Neural Networks (GNNs) has developed rapidly, and many methods have been proposed to enhance the expressiveness.

Efficiently Counting Substructures by Subgraph GNNs without Running GNN on Subgraphs

1 code implementation19 Mar 2023 Zuoyu Yan, Junru Zhou, Liangcai Gao, Zhi Tang, Muhan Zhang

Among these works, a popular way is to use subgraph GNNs, which decompose the input graph into a collection of subgraphs and enhance the representation of the graph by applying GNN to individual subgraphs.

Graph Learning

SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning

1 code implementation6 Mar 2023 Haoteng Yin, Muhan Zhang, Jianguo Wang, Pan Li

Subgraph-based graph representation learning (SGRL) has recently emerged as a powerful tool in many prediction tasks on graphs due to its advantages in model expressiveness and generalization ability.

Graph Representation Learning

Neural Common Neighbor with Completion for Link Prediction

1 code implementation2 Feb 2023 Xiyuan Wang, Haotong Yang, Muhan Zhang

Despite its outstanding performance in various graph tasks, vanilla Message Passing Neural Network (MPNN) usually fails in link prediction tasks, as it only uses representations of two individual target nodes and ignores the pairwise relation between them.

Link Prediction

RulE: Neural-Symbolic Knowledge Graph Reasoning with Rule Embedding

1 code implementation24 Oct 2022 Xiaojuan Tang, Song-Chun Zhu, Yitao Liang, Muhan Zhang

In this paper, we propose a novel and principled framework called \textbf{RulE} (stands for {Rul}e {E}mbedding) to effectively leverage logical rules to enhance KG reasoning.

Knowledge Graph Embedding Knowledge Graphs +1

Boosting the Cycle Counting Power of Graph Neural Networks with I$^2$-GNNs

2 code implementations22 Oct 2022 Yinan Huang, Xingang Peng, Jianzhu Ma, Muhan Zhang

To the best of our knowledge, it is the first linear-time GNN model that can count 6-cycles with theoretical guarantees.

1st ICLR International Workshop on Privacy, Accountability, Interpretability, Robustness, Reasoning on Structured Data (PAIR^2Struct)

no code implementations7 Oct 2022 Hao Wang, WanYu Lin, Hao He, Di Wang, Chengzhi Mao, Muhan Zhang

Recent years have seen advances on principles and guidance relating to accountable and ethical use of artificial intelligence (AI) spring up around the globe.

Rethinking Knowledge Graph Evaluation Under the Open-World Assumption

1 code implementation19 Sep 2022 Haotong Yang, Zhouchen Lin, Muhan Zhang

However, evaluation of knowledge graph completion (KGC) models often ignores the incompleteness -- facts in the test set are ranked against all unknown triplets which may contain a large number of missing facts not included in the KG yet.

Fairness

Graph Neural Network with Local Frame for Molecular Potential Energy Surface

1 code implementation1 Aug 2022 Xiyuan Wang, Muhan Zhang

Projected onto a frame, equivariant features like 3D coordinates are converted to invariant features, so that we can capture geometric information with these projections and decouple the symmetry requirement from GNN design.

Representation Learning

Two-Dimensional Weisfeiler-Lehman Graph Neural Networks for Link Prediction

1 code implementation20 Jun 2022 Yang Hu, Xiyuan Wang, Zhouchen Lin, Pan Li, Muhan Zhang

As pointed out by previous works, this two-step procedure results in low discriminating power, as 1-WL-GNNs by nature learn node-level representations instead of link-level.

Link Prediction Vocal Bursts Valence Prediction

How Powerful are K-hop Message Passing Graph Neural Networks

1 code implementation26 May 2022 Jiarui Feng, Yixin Chen, Fuhai Li, Anindya Sarkar, Muhan Zhang

Recently, researchers extended 1-hop message passing to K-hop message passing by aggregating information from K-hop neighbors of nodes simultaneously.

How Powerful are Spectral Graph Neural Networks

2 code implementations23 May 2022 Xiyuan Wang, Muhan Zhang

We also establish a connection between the expressive power of spectral GNNs and Graph Isomorphism (GI) testing, the latter of which is often used to characterize spatial GNNs' expressive power.

3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design

1 code implementation15 May 2022 Yinan Huang, Xingang Peng, Jianzhu Ma, Muhan Zhang

The main computational challenges include: 1) the generation of linkers is conditional on the two given molecules, in contrast to generating full molecules from scratch in previous works; 2) linkers heavily depend on the anchor atoms of the two molecules to be connected, which are not known beforehand; 3) 3D structures and orientations of the molecules need to be considered to avoid atom clashes, for which equivariance to E(3) group are necessary.

PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs

1 code implementation19 Mar 2022 Zehao Dong, Muhan Zhang, Fuhai Li, Yixin Chen

In this work, we propose a Parallelizable Attention-based Computation structure Encoder (PACE) that processes nodes simultaneously and encodes DAGs in parallel.

Neural Architecture Search

Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks

1 code implementation ICLR 2022 Haorui Wang, Haoteng Yin, Muhan Zhang, Pan Li

Graph neural networks (GNN) have shown great advantages in many graph-based learning tasks but often fail to predict accurately for a task-based on sets of nodes such as link/motif prediction and so on.

Link Prediction

Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning

3 code implementations28 Feb 2022 Haoteng Yin, Muhan Zhang, Yanbang Wang, Jianguo Wang, Pan Li

Subgraph-based graph representation learning (SGRL) has been recently proposed to deal with some fundamental challenges encountered by canonical graph neural networks (GNNs), and has demonstrated advantages in many important data science applications such as link, relation and motif prediction.

Graph Representation Learning

Decoupling the Depth and Scope of Graph Neural Networks

1 code implementation NeurIPS 2021 Hanqing Zeng, Muhan Zhang, Yinglong Xia, Ajitesh Srivastava, Andrey Malevich, Rajgopal Kannan, Viktor Prasanna, Long Jin, Ren Chen

We propose a design principle to decouple the depth and scope of GNNs -- to generate representation of a target entity (i. e., a node or an edge), we first extract a localized subgraph as the bounded-size scope, and then apply a GNN of arbitrary depth on top of the subgraph.

Link Prediction Node Classification +1

Network In Graph Neural Network

no code implementations23 Nov 2021 Xiang Song, Runjie Ma, Jiahang Li, Muhan Zhang, David Paul Wipf

However, wider hidden layers can easily lead to overfitting, and incrementally adding more GNN layers can potentially result in over-smoothing. In this paper, we present a model-agnostic methodology, namely Network In Graph Neural Network (NGNN ), that allows arbitrary GNN models to increase their model capacity by making the model deeper.

Fraud Detection Link Prediction +1

Principled Hyperedge Prediction with Structural Spectral Features and Neural Networks

no code implementations8 Jun 2021 Changlin Wan, Muhan Zhang, Wei Hao, Sha Cao, Pan Li, Chi Zhang

SNALS captures the joint interactions of a hyperedge by its local environment, which is retrieved by collecting the spectrum information of their connections.

Hyperedge Prediction

Learning Two-Time-Scale Representations For Large Scale Recommendations

no code implementations1 Jan 2021 Xinshi Chen, Yan Zhu, Haowen Xu, Muhan Zhang, Liang Xiong, Le Song

We propose a surprisingly simple but effective two-time-scale (2TS) model for learning user representations for recommendation.

Vocal Bursts Valence Prediction

Deep Graph Neural Networks with Shallow Subgraph Samplers

2 code implementations2 Dec 2020 Hanqing Zeng, Muhan Zhang, Yinglong Xia, Ajitesh Srivastava, Andrey Malevich, Rajgopal Kannan, Viktor Prasanna, Long Jin, Ren Chen

We propose a simple "deep GNN, shallow sampler" design principle to improve both the GNN accuracy and efficiency -- to generate representation of a target node, we use a deep GNN to pass messages only within a shallow, localized subgraph.

Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning

2 code implementations NeurIPS 2021 Muhan Zhang, Pan Li, Yinglong Xia, Kai Wang, Long Jin

In this paper, we provide a theory of using graph neural networks (GNNs) for multi-node representation learning (where we are interested in learning a representation for a set of more than one node, such as link).

General Classification Graph Classification +4

Pooling Regularized Graph Neural Network for fMRI Biomarker Analysis

no code implementations29 Jul 2020 Xiaoxiao Li, Yuan Zhou, Nicha C. Dvornek, Muhan Zhang, Juntang Zhuang, Pamela Ventola, James S. Duncan

We propose an interpretable GNN framework with a novel salient region selection mechanism to determine neurological brain biomarkers associated with disorders.

Inductive Matrix Completion Based on Graph Neural Networks

3 code implementations ICLR 2020 Muhan Zhang, Yixin Chen

Under the extreme setting where not any side information is available other than the matrix to complete, can we still learn an inductive matrix completion model?

Matrix Completion Recommendation Systems +1

Link Prediction Based on Graph Neural Networks

9 code implementations NeurIPS 2018 Muhan Zhang, Yixin Chen

The theory unifies a wide range of heuristics in a single framework, and proves that all these heuristics can be well approximated from local subgraphs.

Link Prediction

Weisfeiler-lehman neural machine for link prediction

1 code implementation KDD 2017 Muhan Zhang, Yixin Chen

Compared with traditional link prediction methods, Wlnm does not assume a particular link formation mechanism (such as common neighbors), but learns this mechanism from the graph itself.

Link Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.