Learning unsupervised node embeddings facilitates several downstream tasks such as node classification and link prediction. A node embedding is universal if it is designed to be used by and benefit various downstream tasks. This work introduces PanRep, a graph neural network (GNN) model, for unsupervised learning of universal node representations for heterogenous graphs. PanRep consists of a GNN encoder that obtains node embeddings and four decoders, each capturing different topological and node feature properties. Abiding to these properties the novel unsupervised framework learns universal embeddings applicable to different downstream tasks. PanRep can be furthered fine-tuned to account for possible limited labels. In this operational setting PanRep is considered as a pretrained model for extracting node embeddings of heterogenous graph data. PanRep outperforms all unsupervised and certain supervised methods in node classification and link prediction, especially when the labeled data for the supervised methods is small. PanRep-FT (with fine-tuning) outperforms all other supervised approaches, which corroborates the merits of pretraining models. Finally, we apply PanRep-FT for discovering novel drugs for Covid-19. We showcase the advantage of universal embeddings in drug repurposing and identify several drugs used in clinical trials as possible drug candidates.
To enable heterogeneous computing systems with autonomous programming and optimization capabilities, we propose a unified, end-to-end, programmable graph representation learning (PGL) framework that is capable of mining the complexity of high-level programs down to the universal intermediate representation, extracting the specific computational patterns and predicting which code segments would run best on a specific core in heterogeneous hardware platforms. The proposed framework extracts multi-fractal topological features from code graphs, utilizes graph autoencoders to learn how to partition…
Heterogeneous graphs have multiple node and edge types and are semantically richer than homogeneous graphs. To learn such complex semantics, many graph neural network approaches for heterogeneous graphs use metapaths to capture multi-hop interactions between nodes. Typically, features from non-target nodes are not incorporated into the learning procedure. However, there can be nonlinear, high-order interactions involving multiple nodes or edges. In this paper, we present Simplicial Graph Attention Network (SGAT), a simplicial complex approach to represent such high-order interactions by placin…
DSHGT: Dual-Supervisors Heterogeneous Graph Transformer -- A pioneer study of using heterogeneous graph learning for detecting software vulnerabilities
Tongji University（同济大学）；Ping An Technology（平安科技）；Fudan University（复旦大学）；Ant Group（蚂蚁集团）；Macquarie University（麦考瑞大学）
Heterogeneous Graph Alignment for Joint Reasoning and Interpretability
Department of Statistics, University of California, Irvine（统计学系，加州大学伊维特分校）；Department of Neurobiology and Behavior, University of California, Irvine（神经生物学与行为系，加州大学伊维特分校）
Multi-Granular Attention based Heterogeneous Hypergraph Neural Network
School of Computer Science, Hubei University（湖北大学计算机学院）；Hubei Key Laboratory of Big Data Intelligent Analysis and Application (Hubei University)（湖北大学大数据智能分析与应用重点实验室）；Discipline of Business Analytics, The University of Sydney（悉尼大学商业分析学科）；Key Laboratory of Intelligent Sensing System and Security (Hubei University), Ministry of Education（智能感知系统与安全重点实验室（湖北大学），教育部）
Istanbul Technical University（伊斯坦布尔理工大学）；University of Dundee（邓迪大学）
With the recent technological advances, biological datasets, often represented by networks (i.e., graphs) of interacting entities, proliferate with unprecedented complexity and heterogeneity. Although modern network science opens new frontiers of analyzing connectivity patterns in such datasets, we still lack data-driven methods for extracting an integral connectional fingerprint of a multi-view graph population, let alone disentangling the typical from the atypical variations across the population samples. We present the multi-view graph normalizer network (MGN-Net; https://github.com/basiral…
The University of Queensland（昆士兰大学）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Alibaba AI Labs（阿里巴巴人工智能实验室）
With the ubiquitous graph-structured data in various applications, models that can learn compact but expressive vector representations of nodes have become highly desirable. Recently, bearing the message passing paradigm, graph neural networks (GNNs) have greatly advanced the performance of node representation learning on graphs. However, a majority class of GNNs are only designed for homogeneous graphs, leading to inferior adaptivity to the more informative heterogeneous graphs with various types of nodes and edges. Also, despite the necessity of inductively producing representations for comp…
Epidemiology-informed Graph Neural Network for Heterogeneity-aware Epidemic Forecasting
University of Canberra（堪培拉大学）；University of Queensland（昆士兰大学）；Hong Kong Polytechnic University（香港理工大学）；Griffith University（格里菲斯大学）；South China Normal University（华南师范大学）
Perturbation Ontology based Graph Attention Networks
Institute of Data and Information（数据与信息研究所）；Tsinghua University（清华大学）；Tongji University（同济大学）；School of Mathematics and Statistics（数学与统计学院）；Shandong University（山东大学）；Department of Electrical and Computer Engineering（电气与计算机工程系）；Carnegie Mellon University（卡内基梅隆大学）；Language Technologies Institute（语言技术研究所）
University of California, Berkeley（加州大学伯克利分校）；LinkedIn（领英）
As a special field in deep learning, Graph Neural Networks (GNNs) focus on extracting intrinsic network features and have drawn unprecedented popularity in both academia and industry. Most of the state-of-the-art GNN models offer expressive, robust, scalable and inductive solutions empowering social network recommender systems with rich network features that are computationally difficult to leverage with graph traversal based methods. Most recent GNNs follow an encoder-decoder paradigm to encode high dimensional heterogeneous information from a subgraph onto one low dimensional embedding space…
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. However, current SGRL approaches suffer from scalability issues since they require extracting subgraphs for each training or test query. Recent solutions that scale up canonical GNNs may not apply to SGRL. Here, we propose a novel framework SUREL for scalable SGRL by co-designing the learning algorithm …
Tsinghua University（清华大学）；Khoury College of Computer Sciences, Northeastern University（东北大学库利计算机科学学院）
Web and artificial intelligence technologies, especially semantic web and knowledge graph (KG), have recently raised significant attention in educational scenarios. Nevertheless, subject-specific KGs for K-12 education still lack sufficiency and sustainability from knowledge and data perspectives. To tackle these issues, we propose EDUKG, a heterogeneous sustainable K-12 Educational Knowledge Graph. We first design an interdisciplinary and fine-grained ontology for uniformly modeling knowledge and resource in K-12 education, where we define 635 classes, 445 object properties, and 1314 datatype…
Out-of-Distribution Detection in Heterogeneous Graphs via Energy Propagation
School of New Media and Communication, Tianjin University（天津大学新媒体与传播学院）；Department of Computer Science, Baylor University（贝勒大学计算机科学系）；School of Qiyue Media and Communication, Cangzhou Normal University（沧州市庆云传媒学院）
While deep neural networks (DNNs) have been increasingly applied to choice analysis showing high predictive power, it is unclear to what extent researchers can interpret economic information from DNNs. This paper demonstrates that DNNs can provide economic information as complete as classical discrete choice models (DCMs). The economic information includes choice predictions, choice probabilities, market shares, substitution patterns of alternatives, social welfare, probability derivatives, elasticities, marginal rates of substitution (MRS), and heterogeneous values of time (VOT). Unlike DCMs,…
Jointly Learning Representations for Map Entities via Heterogeneous Graph Contrastive Learning
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；School of Economics and Management, Beihang University（北京航空航天大学经济管理学院）
