Aiming at better representing multivariate relationships, this paper investigates a motif dimensional framework for higher-order graph learning. The graph learning effectiveness can be improved through OFFER. The proposed framework mainly aims at accelerating and improving higher-order graph learning results. We apply the acceleration procedure from the dimensional of network motifs. Specifically, the refined degree for nodes and edges are conducted in two stages: (1) employ motif degree of nodes to refine the adjacency matrix of the network; and (2) employ motif degree of edges to refine the transition probability matrix in the learning process. In order to assess the efficiency of the proposed framework, four popular network representation algorithms are modified and examined. By evaluating the performance of OFFER, both link prediction results and clustering results demonstrate that the graph representation learning algorithms enhanced with OFFER consistently outperform the original algorithms with higher efficiency.
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Visa Research（Visa研究院）
Recent years have witnessed a surge of interest in machine learning on graphs and networks with applications ranging from vehicular network design to IoT traffic management to social network recommendations. Supervised machine learning tasks in networks such as node classification and link prediction require us to perform feature engineering that is known and agreed to be the key to success in applied machine learning. Research efforts dedicated to representation learning, especially representation learning using deep learning, has shown us ways to automatically learn relevant features from va…
Pre-training Graph Neural Networks (GNN) via self-supervised contrastive learning has recently drawn lots of attention. However, most existing works focus on node-level contrastive learning, which cannot capture global graph structure. The key challenge to conducting subgraph-level contrastive learning is to sample informative subgraphs that are semantically meaningful. To solve it, we propose to learn graph motifs, which are frequently-occurring subgraph patterns (e.g. functional groups of molecules), for better subgraph sampling. Our framework MotIf-driven Contrastive leaRning Of Graph repre…
School of Mathematical Science, Beihang University（北京航空航天大学数学科学学院）；Key Laboratory of Mathematics Informatics Behavioral Semantics, Ministry of Education（教育部数学、信息与行为语义重点实验室）；Peng Cheng Laboratory（鹏城实验室）；Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University（北京航空航天大学大数据与脑机智能北京高精尖创新中心）
The graph structure is a commonly used data storage mode, and it turns out that the low-dimensional embedded representation of nodes in the graph is extremely useful in various typical tasks, such as node classification, link prediction , etc. However, most of the existing approaches start from the binary relationship (i.e., edges) in the graph and have not leveraged the higher order local structure (i.e., motifs) of the graph. Here, we propose mGCMN -- a novel framework which utilizes node feature information and the higher order local structure of the graph to effectively generate node embed…
Ocean University of China（中国海洋大学）；Massachusetts Institute of Technology（麻省理工学院）；The University of Hong Kong（香港大学）
One fundamental problem in temporal graph analysis is to count the occurrences of small connected subgraph patterns (i.e., motifs), which benefits a broad range of real-world applications, such as anomaly detection, structure prediction, and network representation learning. However, existing works focused on exacting temporal motif are not scalable to large-scale temporal graph data, due to their heavy computational costs or inherent inadequacy of parallelism. In this work, we propose a scalable parallel framework for exactly counting temporal motifs in large-scale temporal graphs. We first ca…
ImageDDI: Image-enhanced Molecular Motif Sequence Representation for Drug-Drug Interaction Prediction
College of Computer science and Electronic Engineering, Hunan University（计算机科学与电子工程学院，湖南大学）；Department of Integrative Biotechnology, Yonsei University（整合生物技术系，延世大学）
Temporal networks serve as abstractions of many real-world dynamic systems. These networks typically evolve according to certain laws, such as the law of triadic closure, which is universal in social networks. Inductive representation learning of temporal networks should be able to capture such laws and further be applied to systems that follow the same laws but have not been unseen during the training stage. Previous works in this area depend on either network node identities or rich edge attributes and typically fail to extract these laws. Here, we propose Causal Anonymous Walks (CAWs) to in…
Filtration-Based Representation Learning for Temporal Graphs
Indian Institute of Science Education and Research Tirupati（印度科学教育与研究学院 Tirupati）；Chennai Mathematical Institute（钦奈数学研究所）；Institut Polytechnique de Paris（巴黎高等技术学院）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
We present InfoMotif, a new semi-supervised, motif-regularized, learning framework over graphs. We overcome two key limitations of message passing in popular graph neural networks (GNNs): localization (a k-layer GNN cannot utilize features outside the k-hop neighborhood of the labeled training nodes) and over-smoothed (structurally indistinguishable) representations. We propose the concept of attributed structural roles of nodes based on their occurrence in different network motifs, independent of network proximity. Two nodes share attributed structural roles if they participate in topological…
McGill University（麦吉尔大学）；Montreal Institute for Learning Algorithms (MILA)（蒙特利尔学习算法研究所）；Institut Pasteur（巴斯德研究所）；Mines ParisTech（巴黎高等矿业学院）；Paris-Sciences-et-Lettres Research University（巴黎文理研究大学）
RNA 3D motifs are recurrent substructures, modelled as networks of base pair interactions, which are crucial for understanding structure-function relationships. The task of automatically identifying such motifs is computationally hard, and remains a key challenge in the field of RNA structural biology and network analysis. State of the art methods solve special cases of the motif problem by constraining the structural variability in occurrences of a motif, and narrowing the substructure search space. Here, we relax these constraints by posing the motif finding problem as a graph representation…
ETH Zurich（苏黎世联邦理工学院）；University of Geneva（日内瓦大学）；UIUC（伊利诺伊大学厄巴纳-香槟分校）
Link prediction is one of the central problems in graph mining. However, recent studies highlight the importance of higher-order network analysis, where complex structures called motifs are the first-class citizens. We first show that existing link prediction schemes fail to effectively predict motifs. To alleviate this, we establish a general motif prediction problem and we propose several heuristics that assess the chances for a specified motif to appear. To make the scores realistic, our heuristics consider - among others - correlations between links, i.e., the potential impact of some arri…
Social media mining has become one of the most popular research areas in Big Data with the explosion of social networking information from Facebook, Twitter, LinkedIn, Weibo and so on. Understanding and representing the structure of a social network is a key in social media mining. In this paper, we propose the Motif Iteration Model (MIM) to represent the structure of a social network. As the name suggested, the new model is based on iteration of basic network motifs. In order to better show the properties of the model, a heuristic and greedy algorithm called Vertex Reordering and Arranging (V…
Georgia State University（佐治亚州立大学）；University of Wisconsin–Madison（威斯康星大学麦迪逊分校）
Graph Neural networks (GNNs) have recently become a powerful technique for many graph-related tasks including graph classification. Current GNN models apply different graph pooling methods that reduce the number of nodes and edges to learn the higher-order structure of the graph in a hierarchical way. All these methods primarily rely on the one-hop neighborhood. However, they do not consider the higher- order structure of the graph. In this work, we propose a multi-channel Motif-based Graph Pooling method named (MPool) captures the higher-order graph structure with motif and local and global g…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；IBM UK（IBM英国公司）；Cardiff University（卡迪夫大学）
Network classification has a variety of applications, such as detecting communities within networks and finding similarities between those representing different aspects of the real world. However, most existing work in this area focus on examining static undirected networks without considering directed edges or temporality. In this paper, we propose a new methodology that utilizes feature representation for network classification based on the temporal motif distribution of the network and a null model for comparing against random graphs. Experimental results show that our method improves accu…
Dynamic evolving networks capture temporal relations in domains such as social networks, communication networks, and financial transaction networks. In such networks, temporal motifs, which are repeated sequences of time-stamped edges/transactions, offer valuable information about the networks' evolution and function. However, currently no analytical models for temporal graphs exist and there are no models that would allow for scalable modeling of temporal motif frequencies over time. Here, we develop the Temporal Activity State Block Model (TASBM), to model temporal motifs in temporal graphs.…
Higher-order proximity (HOP) is fundamental for most network embedding methods due to its significant effects on the quality of node embedding and performance on downstream network analysis tasks. Most existing HOP definitions are based on either homophily to place close and highly interconnected nodes tightly in embedding space or heterophily to place distant but structurally similar nodes together after embedding. In real-world networks, both can co-exist, and thus considering only one could limit the prediction performance and interpretability. However, there is no general and universal sol…
This paper uses the reliability polynomial, introduced by Moore and Shannon in 1956, to analyze the effect of network structure on diffusive dynamics such as the spread of infectious disease. We exhibit a representation for the reliability polynomial in terms of what we call {\em structural motifs} that is well suited for reasoning about the effect of a network's structural properties on diffusion across the network. We illustrate by deriving several general results relating graph structure to dynamical phenomena.
Wikipedia serves as a good example of how editors collaborate to form and maintain an article. The relationship between editors, derived from their sequence of editing activity, results in a directed network structure called the revision network, that potentially holds valuable insights into editing activity. In this paper we create revision networks to assess differences between controversial and non-controversial articles, as labelled by Wikipedia. Originating from complex networks, we apply motif analysis, which determines the under or over-representation of induced sub-structures, in this …
Temporal Motifs for Financial Networks: A Study on Mercari, JPMC, and Venmo Platforms
J.P. Morgan Chase AI；Department of Computer Science and Engineering, University at Buffalo（计算机科学与工程系，布法罗大学）；Amazon（亚马逊）；Optum Labs（Optum 实验室）；Mercari, Inc.（Mercari 公司）；Department of Mathematics and Computational, University at Buffalo（数学与计算系，布法罗大学）；Data-Enabled Science and Engineering Program, University at Buffalo（数据赋能科学与工程计划，布法罗大学）
This paper employs a weighted network approach to study the empirical properties of the web of trade relationships among world countries, and its evolution over time. We show that most countries are characterized by weak trade links; yet, there exists a group of countries featuring a large number of strong relationships, thus hinting to a core-periphery structure. The World Trade Web (WTW) is characterized by the following representation: a directed graph connecting world Countries with trade relationships, with the aim of finding its topological characterization in terms of motifs and isolati…
