Graph Neural Networks (GNNs) have emerged as powerful tools for analyzing and learning representations from graph-structured data. A crucial prerequisite for the outstanding performance of GNNs is the availability of complete graph information, i.e., node features and graph structure, which is frequently unmet in real-world scenarios since graphs are often incomplete due to various uncontrollable factors. Existing approaches only focus on dealing with either incomplete features or incomplete structure, which leads to performance loss inevitably. To address this issue, this study proposes a mutual dual-stream graph neural network (MDS-GNN), which implements a mutual benefit learning between features and structure. Its main ideas are as follows: a) reconstructing the missing node features based on the initial incomplete graph structure; b) generating an augmented global graph based on the reconstructed node features, and propagating the incomplete node features on this global graph; and c) utilizing contrastive learning to make the dual-stream process mutually benefit from each other. Extensive experiments on six real-world datasets demonstrate the effectiveness of our proposed MDS-GNN on incomplete graphs.
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；School of Economics and Management, Beijing University of Posts and Telecommunications（北京邮电大学经济管理学院）；Pinterest
Graph Neural Networks (GNNs) have been a prevailing technique for tackling various analysis tasks on graph data. A key premise for the remarkable performance of GNNs relies on complete and trustworthy initial graph descriptions (i.e., node features and graph structure), which is often not satisfied since real-world graphs are often incomplete due to various unavoidable factors. In particular, GNNs face greater challenges when both node features and graph structure are incomplete at the same time. The existing methods either focus on feature completion or structure completion. They usually rely…
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in node classification, regression, and recommendation tasks. GNNs work well when rich and high-quality connections are available. However, their effectiveness is often jeopardized in many real-world graphs in which node degrees have power-law distributions. The extreme case of this situation, where a node may have no neighbors, is called Strict Cold Start (SCS). SCS forces the prediction to rely completely on the node's own features. We propose Cold Brew, a teacher-student distillation approach to address the SCS and nois…
Graph Neural Networks (GNNs) are gaining increasing attention on graph data learning tasks in recent years. However, in many applications, graph may be coming in an incomplete form where attributes of graph nodes are partially unknown/missing. Existing GNNs are generally designed on complete graphs which can not deal with attribute-incomplete graph data directly. To address this problem, we develop a novel partial aggregation based GNNs, named Partial Graph Neural Networks (PaGNNs), for attribute-incomplete graph representation and learning. Our work is motivated by the observation that the ne…
Federated Incomplete Multi-View Clustering with Heterogeneous Graph Neural Networks
Guangdong University of Foreign Studies（广东外语外贸大学）；School of Engineering, Westlake University（西湖大学工程学院）；East China University of Science and Technology（华东理工大学）
Graph neural networks (GNNs) have been applied into a variety of graph tasks. Most existing work of GNNs is based on the assumption that the given graph data is optimal, while it is inevitable that there exists missing or incomplete edges in the graph data for training, leading to degraded performance. In this paper, we propose Generative Predictive Network (GPN), a GNN-based joint learning framework that simultaneously learns the graph structure and the downstream task. Specifically, we develop a bilevel optimization framework for this joint learning task, in which the upper optimization (gen…
Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum
Snir Hordan Faculty of Mathematics Department of Applied Mathematics Technion - Israel Institute of Technology（技术学院-以色列理工学院数学系应用数学系）；Maya Bechler-Speicher Meta（Meta公司）；Gur Lifshitz Blavatnik School of Computer Science Tel-Aviv University（特拉维夫大学Blavatnik计算机科学学院）；Nadav Dym Faculty of Mathematics Faculty of Computer Science Technion - Israel Institute of Technology（技术学院-以色列理工学院数学系计算机科学系）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua University（清华大学）
Conversations have become a critical data format on social media platforms. Understanding conversation from emotion, content and other aspects also attracts increasing attention from researchers due to its widespread application in human-computer interaction. In real-world environments, we often encounter the problem of incomplete modalities, which has become a core issue of conversation understanding. To address this problem, researchers propose various methods. However, existing approaches are mainly designed for individual utterances rather than conversational data, which cannot fully explo…
Ecole Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Graph neural networks (GNN) are very popular methods in machine learning and have been applied very successfully to the prediction of the properties of molecules and materials. First-order GNNs are well known to be incomplete, i.e., there exist graphs that are distinct but appear identical when seen through the lens of the GNN. More complicated schemes have thus been designed to increase their resolving power. Applications to molecules (and more generally, point clouds), however, add a geometric dimension to the problem. The most straightforward and prevalent approach to construct graph repres…
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）；AI Lab, Tencent（腾讯AI实验室）
Graph neural networks (GNNs) are popular weapons for modeling relational data. Existing GNNs are not specified for attribute-incomplete graphs, making missing attribute imputation a burning issue. Until recently, many works notice that GNNs are coupled with spectral concentration, which means the spectrum obtained by GNNs concentrates on a local part in spectral domain, e.g., low-frequency due to oversmoothing issue. As a consequence, GNNs may be seriously flawed for reconstructing graph attributes as graph spectral concentration tends to cause a low imputation precision. In this work, we pres…
Istituto Italiano di Tecnologia（意大利技术研究院）；University College London（伦敦大学学院）；NEC Labs Europe（NEC欧洲实验室）
Graph neural networks (GNNs) are a popular class of machine learning models whose major advantage is their ability to incorporate a sparse and discrete dependency structure between data points. Unfortunately, GNNs can only be used when such a graph-structure is available. In practice, however, real-world graphs are often noisy and incomplete or might not be available at all. With this work, we propose to jointly learn the graph structure and the parameters of graph convolutional networks (GCNs) by approximately solving a bilevel program that learns a discrete probability distribution on the ed…
Mila - Québec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）；HEC Montréal（蒙特利尔高等商学院）；CIFAR AI Chair（加拿大高等研究院人工智能讲席）
Answering complex first-order logic (FOL) queries on knowledge graphs is a fundamental task for multi-hop reasoning. Traditional symbolic methods traverse a complete knowledge graph to extract the answers, which provides good interpretation for each step. Recent neural methods learn geometric embeddings for complex queries. These methods can generalize to incomplete knowledge graphs, but their reasoning process is hard to interpret. In this paper, we propose Graph Neural Network Query Executor (GNN-QE), a neural-symbolic model that enjoys the advantages of both worlds. GNN-QE decomposes a comp…
Enhancing Knowledge Graph Completion with GNN Distillation and Probabilistic Interaction Modeling
Shandong Key Laboratory of Industrial Network Security（山东工业网络安全重点实验室）；School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）
A Graph Neural Network with Auxiliary Task Learning for Missing PMU Data Reconstruction
Guangxi University（广西大学）；Tsinghua University（清华大学）；University of Electronic Science and Technology of China（电子科技大学）；Massachusetts Institute of Technology（麻省理工学院）
Harvard T.H. Chan School of Public Health（哈佛大学陈曾熙公共卫生学院）；IQVIA（艾昆纬）；Harvard University（哈佛大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Molecular interaction networks are powerful resources for the discovery. They are increasingly used with machine learning methods to predict biologically meaningful interactions. While deep learning on graphs has dramatically advanced the prediction prowess, current graph neural network (GNN) methods are optimized for prediction on the basis of direct similarity between interacting nodes. In biological networks, however, similarity between nodes that do not directly interact has proved incredibly useful in the last decade across a variety of interaction networks. Here, we present SkipGNN, a gr…
Future Directions in the Theory of Graph Machine Learning
RWTH Aachen University（亚琛工业大学）；Technion - Israel Institute of Technology（以色列理工学院）；NVIDIA Research（英伟达研究院）；University of Oxford（牛津大学）；MIT（麻省理工学院）；TU Munich（慕尼黑工业大学）
Beihang University（北京航空航天大学）；Macquarie University（麦考瑞大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
Graph Neural Networks (GNNs) have shown promising results on a broad spectrum of applications. Most empirical studies of GNNs directly take the observed graph as input, assuming the observed structure perfectly depicts the accurate and complete relations between nodes. However, graphs in the real world are inevitably noisy or incomplete, which could even exacerbate the quality of graph representations. In this work, we propose a novel Variational Information Bottleneck guided Graph Structure Learning framework, namely VIB-GSL, in the perspective of information theory. VIB-GSL advances the Info…
Sampling Transferable Graph Neural Networks with Limited Graph Information
Department of Applied Mathematics and Statistics, Johns Hopkins University（应用数学与统计学系，约翰霍普金斯大学）；Department of Statistics and Data Science, Yale University（统计与数据科学系，耶鲁大学）；Department of Electrical and Computer Engineering, University of Rochester（电气与计算机工程系，罗切斯特大学）
School of Engineering, Computing and Mathematics（工程、计算与数学学院）；Oxford Brookes University（奥克斯福德布鲁克斯大学）；Department of Computer Science（计算机科学系）；University of Pisa（比萨大学）；Oxford Brookes Institute for Artificial Intelligence, Data Analysis and Systems (AIDAS)（奥克斯福德布鲁克斯人工智能、数据分析与系统研究所（AIDAS））
Global Health Drug Discovery Institute（全球健康药物研发中心）
Multi-scale biomedical knowledge networks are expanding with emerging experimental technologies that generates multi-scale biomedical big data. Link prediction is increasingly used especially in bipartite biomedical networks to identify hidden biological interactions and relationshipts between key entities such as compounds, targets, gene and diseases. We propose a Graph Neural Networks (GNN) method, namely Graph Pair based Link Prediction model (GPLP), for predicting biomedical network links simply based on their topological interaction information. In GPLP, 1-hop subgraphs extracted from kno…
Tsinghua University（清华大学）；Central South University（中南大学）
Large-scale data missing is a challenging problem in Intelligent Transportation Systems (ITS). Many studies have been carried out to impute large-scale traffic data by considering their spatiotemporal correlations at a network level. In existing traffic data imputations, however, rich semantic information of a road network has been largely ignored when capturing network-wide spatiotemporal correlations. This study proposes a Graph Transformer for Traffic Data Imputation (GT-TDI) model to impute large-scale traffic data with spatiotemporal semantic understanding of a road network. Specifically,…
Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network
Institute of Computing Technology, University of Chinese Academy of Sciences（中国科学院大学计算技术研究所）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Accurate traffic forecasting, the foundation of intelligent transportation systems (ITS), has never been more significant than nowadays due to the prosperity of smart cities and urban computing. Recently, Graph Neural Network truly outperforms the traditional methods. Nevertheless, the most conventional GNN-based model works well while given a pre-defined graph structure. And the existing methods of defining the graph structures focus purely on spatial dependencies and ignore the temporal correlation. Besides, the semantics of the static pre-defined graph adjacency applied during the whole tra…
Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?
Operations Research, Université de Montréal（运营研究，蒙特利尔大学）；Mila – Quebec AI Institute（魁北克人工智能研究所）；Valence Labs（Valence实验室）；Dept. of Mathematics, Boise State University（数学系，博伊州立大学）
Mila（米拉研究所）；McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）；Stanford University（斯坦福大学）；HEC Montréal（蒙特利尔高等商学院）
Formulating and answering logical queries is a standard communication interface for knowledge graphs (KGs). Alleviating the notorious incompleteness of real-world KGs, neural methods achieved impressive results in link prediction and complex query answering tasks by learning representations of entities, relations, and queries. Still, most existing query answering methods rely on transductive entity embeddings and cannot generalize to KGs containing new entities without retraining the entity embeddings. In this work, we study the inductive query answering task where inference is performed on a …
Center for Research on Intelligent Perception and Computing（智能感知与计算研究中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Department of Computer Science, George Mason University（乔治梅森大学计算机科学系）；The Paul G. Allen School of Computer Science and Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；Department of Computer Science, Emory University（埃默里大学计算机科学系）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Graphs are widely used to describe real-world objects and their interactions. Graph Neural Networks (GNNs) as a de facto model for analyzing graphstructured data, are highly sensitive to the quality of the given graph structures. Therefore, noisy or incomplete graphs often lead to unsatisfactory representations and prevent us from fully understanding the mechanism underlying the system. In pursuit of an optimal graph structure for downstream tasks, recent studies have sparked an effort around the central theme of Graph Structure Learning (GSL), which aims to jointly learn an optimized graph st…
Graph Neural Networks Based Analog Circuit Link Prediction
HDU-ITMO Joint Institute, Hangzhou Dianzi University（杭州电子科技大学信息处理联合研究所）；Intelligent Information Processing Laboratory, Hangzhou Dianzi University（杭州电子科技大学智能信息处理实验室）；Innovation Center for Electronic Design Automation Technology, Hangzhou Dianzi University（杭州电子科技大学电子设计自动化技术创新中心）；School of Computer Science and Technology, South China Business College, Guangdong University of Foreign Studies（广东外语外贸大学南方商学院计算机科学与技术学院）；Department of Computer Science and Technology, University of Cambridge（剑桥大学计算机科学与技术系）
Bi-Level Graph Structure Learning for Next POI Recommendation
Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；University of California, Los Angeles（加州大学洛杉矶分校）；Meituan（美团）
