Shanghai Jiao Tong University（上海交通大学）；Australian Artificial Intelligence Institute（澳大利亚人工智能研究所）；University of Technology Sydney（悉尼科技大学）；Mitsubishi Electric Research Laboratories（三菱电机研究实验室）；Alibaba Group（阿里巴巴集团）；Texas University（得克萨斯大学）
Xu Chen, Siheng Chen, Jiangchao Yao, Huangjie Zheng, Ya Zhang, Ivor W Tsang
备注：
This paper is to appear in IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (TPAMI), 2020
Graphs with complete node attributes have been widely explored recently. While in practice, there is a graph where attributes of only partial nodes could be available and those of the others might be entirely missing. This attribute-missing graph is related to numerous real-world applications and there are limited studies investigating the corresponding learning problems. Existing graph learning methods including the popular GNN cannot provide satisfied learning performance since they are not specified for attribute-missing graphs. Thereby, designing a new GNN for these graphs is a burning issue to the graph learning community. In this paper, we make a shared-latent space assumption on graphs and develop a novel distribution matching based GNN called structure-attribute transformer (SAT) for attribute-missing graphs. SAT leverages structures and attributes in a decoupled scheme and achieves the joint distribution modeling of structures and attributes by distribution matching techniques. It could not only perform the link prediction task but also the newly introduced node attribute completion task. Furthermore, practical measures are introduced to quantify the performance of node attribute completion. Extensive experiments on seven real-world datasets indicate SAT shows better performance than other methods on both link prediction and node attribute completion tasks. Codes and data are available online: https://github.com/xuChenSJTU/SAT-master-online
Hong Kong University of Science and Technology（香港科技大学）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）
Missing node attributes is a common problem in real-world graphs. Graph neural networks have been demonstrated power in graph representation learning while their performance is affected by the completeness of graph information. Most of them are not specified for missing-attribute graphs and fail to leverage incomplete attribute information effectively. In this paper, we propose an innovative node representation learning framework, Wasserstein Graph Neural Network (WGNN), to mitigate the problem. To make the most of limited observed attribute information and capture the uncertainty caused by mi…
Graph representation learning (GRL) on attribute-missing graphs, which is a common yet challenging problem, has recently attracted considerable attention. We observe that existing literature: 1) isolates the learning of attribute and structure embedding thus fails to take full advantages of the two types of information; 2) imposes too strict distribution assumption on the latent space variables, leading to less discriminative feature representations. In this paper, based on the idea of introducing intimate information interaction between the two information sources, we propose our Siamese Attr…
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…
AttriReBoost: A Gradient-Free Propagation Optimization Method for Cold Start Mitigation in Attribute Missing Graphs
School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区智能系统工程学院）；School of Transportation Science and Engineering, Harbin Institute of Technology（哈尔滨工业大学交通科学与工程学院）；Yongjiang Laboratory（甬江实验室）；Tongji University（同济大学）
Temporal graph neural network has recently received significant attention due to its wide application scenarios, such as bioinformatics, knowledge graphs, and social networks. There are some temporal graph neural networks that achieve remarkable results. However, these works focus on future event prediction and are performed under the assumption that all historical events are observable. In real-world applications, events are not always observable, and estimating event time is as important as predicting future events. In this paper, we propose MTGN, a missing event-aware temporal graph neural …
Twitter（推特）；Imperial College London（伦敦帝国理工学院）；University of Oxford（牛津大学）
While Graph Neural Networks (GNNs) have recently become the de facto standard for modeling relational data, they impose a strong assumption on the availability of the node or edge features of the graph. In many real-world applications, however, features are only partially available; for example, in social networks, age and gender are available only for a small subset of users. We present a general approach for handling missing features in graph machine learning applications that is based on minimization of the Dirichlet energy and leads to a diffusion-type differential equation on the graph. T…
Enhancing Missing Data Imputation through Combined Bipartite Graph and Complete Directed Graph
School of Statistics, East China Normal University（华东师范大学统计学院）；The University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；School of Global Public Health, New York University（纽约大学全球公共卫生学院）
Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs
Technion – IIT Faculty of Mathematics（技术学院-理工学院数学系）；MIT Dept of EECS and CSAIL（麻省理工学院电子工程与计算机科学系和计算机科学与人工智能实验室）；TUM School of CIT MCML MDSI（技术大学计算机信息科技学院MCML MDSI）
GNNs have been proven to perform highly effective in various node-level, edge-level, and graph-level prediction tasks in several domains. Existing approaches mainly focus on static graphs. However, many graphs change over time with their edge may disappear, or node/edge attribute may alter from one time to the other. It is essential to consider such evolution in representation learning of nodes in time varying graphs. In this paper, we propose a Temporal Multi-layered Position-aware Graph Neural Network (TMP-GNN), a node embedding approach for dynamic graph that incorporates the interdependenc…
Aggregate network properties such as cluster cohesion and the number of bridge nodes can be used to glean insights about a network's community structure, spread of influence and the resilience of the network to faults. Efficiently computing network properties when the network is fully observed has received significant attention (Wasserman and Faust 1994; Cook and Holder 2006), however the problem of computing aggregate network properties when there is missing data attributes has received little attention. Computing these properties for networks with missing attributes involves performing infer…
Heterogeneous Attributed Graph Learning via Neighborhood-Aware Star Kernels
Key Laboratory of System Software (Chinese Academy of Sciences)（系统软件重点实验室（中国科学院））；State Key Laboratory of Computer Science（计算机科学国家重点实验室）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
Traffic forecasting has attracted widespread attention recently. In reality, traffic data usually contains missing values due to sensor or communication errors. The Spatio-temporal feature in traffic data brings more challenges for processing such missing values, for which the classic techniques (e.g., data imputations) are limited: 1) in temporal axis, the values can be randomly or consecutively missing; 2) in spatial axis, the missing values can happen on one single sensor or on multiple sensors simultaneously. Recent models powered by Graph Neural Networks achieved satisfying performance on…
Pavement Missing Condition Data Imputation through Collective Learning-Based Graph Neural Networks
School of Computing and Information（计算与信息学院）；University of Pittsburgh（匹兹堡大学）；Department of Civil & Environmental Engineering（土木与环境工程系）；University of Houston（休斯顿大学）
Most graph neural network models learn embeddings of nodes in static attributed graphs for predictive analysis. Recent attempts have been made to learn temporal proximity of the nodes. We find that real dynamic attributed graphs exhibit complex co-evolution of node attributes and graph structure. Learning node embeddings for forecasting change of node attributes and birth and death of links over time remains an open problem. In this work, we present a novel framework called CoEvoGNN for modeling dynamic attributed graph sequence. It preserves the impact of earlier graphs on the current graph b…
Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling
IDSIA USI-SUPSI（IDSIA USI-SUPSI（瑞士意大利语大学与瑞士应用科学大学联合机构））；Università della Svizzera italiana（瑞士意大利语大学）；Politecnico di Milano（米兰理工大学）；UiT the Arctic University of Norway（挪威北极大学）；NORCE, Norwegian Research Centre AS（NORCE挪威研究中心）
Given a node-attributed graph, how can we efficiently represent it with few numerical features that expressively reflect its topology and attribute information? We propose A-DOGE, for Attributed DOS-based Graph Embedding, based on density of states (DOS, a.k.a. spectral density) to tackle this problem. A-DOGE is designed to fulfill a long desiderata of desirable characteristics. Most notably, it capitalizes on efficient approximation algorithms for DOS, that we extend to blend in node labels and attributes for the first time, making it fast and scalable for large attributed graphs and graph da…
Graph embedding methods transform high-dimensional and complex graph contents into low-dimensional representations. They are useful for a wide range of graph analysis tasks including link prediction, node classification, recommendation and visualization. Most existing approaches represent graph nodes as point vectors in a low-dimensional embedding space, ignoring the uncertainty present in the real-world graphs. Furthermore, many real-world graphs are large-scale and rich in content (e.g. node attributes). In this work, we propose GLACE, a novel, scalable graph embedding method that preserves …
Machine learning with missing data has been approached in two different ways, including feature imputation where missing feature values are estimated based on observed values, and label prediction where downstream labels are learned directly from incomplete data. However, existing imputation models tend to have strong prior assumptions and cannot learn from downstream tasks, while models targeting label prediction often involve heuristics and can encounter scalability issues. Here we propose GRAPE, a graph-based framework for feature imputation as well as label prediction. GRAPE tackles the mi…
Missing data imputation (MDI) is a fundamental problem in many scientific disciplines. Popular methods for MDI use global statistics computed from the entire data set (e.g., the feature-wise medians), or build predictive models operating independently on every instance. In this paper we propose a more general framework for MDI, leveraging recent work in the field of graph neural networks (GNNs). We formulate the MDI task in terms of a graph denoising autoencoder, where each edge of the graph encodes the similarity between two patterns. A GNN encoder learns to build intermediate representations…
The Chinese University of Hong Kong（香港中文大学）；Tencent AI Lab（腾讯人工智能实验室）；Hong Kong Baptist University（香港浸会大学）
Given one or more query vertices, Community Search (CS) aims to find densely intra-connected and loosely inter-connected structures containing query vertices. Attributed Community Search (ACS), a related problem, is more challenging since it finds communities with both cohesive structures and homogeneous vertex attributes. However, most methods for the CS task rely on inflexible pre-defined structures and studies for ACS treat each attribute independently. Moreover, the most popular ACS strategies decompose ACS into two separate sub-problems, i.e., the CS task and subsequent attribute filterin…
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）
This study investigated the problem of fair classification under Covariate Shift and missing protected attribute using a simple approach based on the use of importance-weights to handle covariate-shift and, Related Features arXiv:2104.14537 to handle missing protected attribute.
National University of Defense Technology（国防科技大学）；Chongqing University of Posts and Telecommunications（重庆邮电大学）；Hainan University（海南大学）；Hainan blockchain technology engineering research center（海南区块链技术工程研究中心）
With the development of various applications, such as social networks and knowledge graphs, graph data has been ubiquitous in the real world. Unfortunately, graphs usually suffer from being absent due to privacy-protecting policies or copyright restrictions during data collection. The absence of graph data can be roughly categorized into attribute-incomplete and attribute-missing circumstances. Specifically, attribute-incomplete indicates that a part of the attribute vectors of all nodes are incomplete, while attribute-missing indicates that the whole attribute vectors of partial nodes are mis…
The existing literature on knowledge graph completion mostly focuses on the link prediction task. However, knowledge graphs have an additional incompleteness problem: their nodes possess numerical attributes, whose values are often missing. Our approach, denoted as MrAP, imputes the values of missing attributes by propagating information across the multi-relational structure of a knowledge graph. It employs regression functions for predicting one node attribute from another depending on the relationship between the nodes and the type of the attributes. The propagation mechanism operates iterat…
Divide-Then-Rule: A Cluster-Driven Hierarchical Interpolator for Attribute-Missing Graphs
College of Computer Science and Technology（计算机科学与技术学院）；National University of Defense Technology（国防科技大学）；Xiangjiang Laboratory（湘江实验室）；Hainan University（海南大学）；Changsha University（长沙大学）；Qilu University of Technology（齐鲁工业大学）；North University of China（北方工业大学）
Processed data are insightful, and crude data are obtuse. A serious threat to data reliability is missing values. Such data leads to inaccurate analysis and wrong predictions. We propose an efficient technique to impute the missing value in the dataset based on correlation called FCMI (Feature Correlation based Missing Data Imputation). We have considered the correlation of the attributes of the dataset, and that is our central idea. Our proposed algorithm picks the highly correlated attributes of the dataset and uses these attributes to build a regression model whose parameters are optimized …
National Remote Sensing Centre (ISRO), India（印度国家遥感中心（ISRO））
Decision making from data involves identifying a set of attributes that contribute to effective decision making through computational intelligence. The presence of missing values greatly influences the selection of right set of attributes and this renders degradation in classification accuracies of the classifiers. As missing values are quite common in data collection phase during field experiments or clinical trails appropriate handling would improve the classifier performance. In this paper we present a review of recently developed missing value imputation algorithms and compare their perfor…
St. Pölten University of Applied Sciences（圣珀尔滕应用科学大学）；Kufstein University of Applied Sciences（库夫施泰因应用科学大学）
The assessment and valuation of real estate requires large datasets with real estate information. Unfortunately, real estate databases are usually sparse in practice, i.e., not for each property every important attribute is available. In this paper, we study the potential of predicting high-level real estate attributes from visual data, specifically from two visual modalities, namely indoor (interior) and outdoor (facade) photos. We design three models using different multimodal fusion strategies and evaluate them for three different use cases. Thereby, a particular challenge is to handle miss…
National Research University Higher School of Economics（俄罗斯国立高等经济大学）；Institute of Molecular Genetics of National Research Centre “Kurchatov Institute”（俄罗斯国家研究中心“库尔恰托夫研究所”分子遗传学研究所）；Pirogov Russian National Research Medical University（俄罗斯国家研究型皮罗戈夫医科大学）
Missing genotypes can affect the efficacy of machine learning approaches to identify the risk genetic variants of common diseases and traits. The problem occurs when genotypic data are collected from different experiments with different DNA microarrays, each being characterised by its pattern of uncalled (missing) genotypes. This can prevent the machine learning classifier from assigning the classes correctly. To tackle this issue, we used well-developed notions of object-attribute biclusters and formal concepts that correspond to dense subrelations in the binary relation $\textit{patients} \t…
Bridge the Gaps: Heterogeneous Attributed Graph Clustering via Quaternion Representation Learning
School of Computer Science and Technology, Guangdong University of Technology（广东工业大学计算机科学与技术学院）；Tsinghua University（清华大学）；BH-Energy Technology Co., Ltd.（BH-Energy科技有限公司）；Shenzhen MSU-BIT University（深圳北理莫斯科大学）
Southern University of Science and Technology（南方科技大学）；University of Birmingham（伯明翰大学）
Attributed networks are ubiquitous since a network often comes with auxiliary attribute information e.g. a social network with user profiles. Attributed Network Embedding (ANE) has recently attracted considerable attention, which aims to learn unified low dimensional node embeddings while preserving both structural and attribute information. The resulting node embeddings can then facilitate various network downstream tasks e.g. link prediction. Although there are several ANE methods, most of them cannot deal with incomplete attributed networks with missing links and/or missing node attributes,…
ByteDance（字节跳动）；University of California, Santa Cruz（加州大学圣克鲁兹分校）
Evaluating fairness can be challenging in practice because the sensitive attributes of data are often inaccessible due to privacy constraints. The go-to approach that the industry frequently adopts is using off-the-shelf proxy models to predict the missing sensitive attributes, e.g. Meta [Alao et al., 2021] and Twitter [Belli et al., 2022]. Despite its popularity, there are three important questions unanswered: (1) Is directly using proxies efficacious in measuring fairness? (2) If not, is it possible to accurately evaluate fairness using proxies only? (3) Given the ethical controversy over in…
DPGAN: A Dual-Path Generative Adversarial Network for Missing Data Imputation in Graphs
Hong Kong Polytechnic University（香港理工大学）；National University of Singapore（新加坡国立大学）；Kyushu University（九州大学）；University of Alberta（阿尔伯塔大学）；University of Tokyo（东京大学）
School of Artificial Intelligence, OPtics and ElectroNics (iOPEN)（人工智能学院（iOPEN））；Northwestern Polytechnical University（西北工业大学）；Institute of Artificial Intelligence (TeleAI)（人工智能研究所（TeleAI））
Temple University（天普大学）；University of Belgrade, Faculty of Organizational Sciences（贝尔格莱德大学组织科学学院）
Conditional probabilistic graphical models provide a powerful framework for structured regression in spatio-temporal datasets with complex correlation patterns. However, in real-life applications a large fraction of observations is often missing, which can severely limit the representational power of these models. In this paper we propose a Marginalized Gaussian Conditional Random Fields (m-GCRF) structured regression model for dealing with missing labels in partially observed temporal attributed graphs. This method is aimed at learning with both labeled and unlabeled parts and effectively pre…
