Dynamic graphs serve as a generic abstraction and description of the evolutionary behaviors of various complex systems (e.g., social networks and communication networks). Temporal link prediction (TLP) is a classic yet challenging inference task on dynamic graphs, which predicts possible future linkage based on historical topology. The predicted future topology can be used to support some advanced applications on real-world systems (e.g., resource pre-allocation) for better system performance. This survey provides a comprehensive review of existing TLP methods. Concretely, we first give the formal problem statements and preliminaries regarding data models, task settings, and learning paradigms that are commonly used in related research. A hierarchical fine-grained taxonomy is further introduced to categorize existing methods in terms of their data models, learning paradigms, and techniques. From a generic perspective, we propose a unified encoder-decoder framework to formulate all the methods reviewed, where different approaches only differ in terms of some components of the framework. Moreover, we envision serving the community with an open-source project OpenTLP1 that refactors or implements some representative TLP methods using the proposed unified framework and summarizes other public resources. As a conclusion, we finally discuss advanced topics in recent research and highlight possible future directions.
26 January 2023 in IEEE Transactions on Knowledge and Data Engineering
Temporal link prediction (TLP) is an inference task on dynamic graphs that predicts future topology using historical graph snapshots. Existing TLP methods are usually designed for unweighted graphs with fixed node sets. Some of them cannot be generalized to the prediction of weighted graphs with non-fixed node sets. Although several methods can still be used to predict weighted graphs, they can only derive low-quality prediction snapshots sensitive to large edge weights but fail to distinguish small and zero weights in adjacency matrices. In this study, we consider the challenging high-quality TLP on weighted dynamic graphs and propose a novel inductive dynamic embedding aggregation (IDEA) method, inspired by the high-resolution video prediction. IDEA combines conventional error minimization objectives with a scale difference minimization objective, which can generate high-quality weighted prediction snapshots, distinguishing differences among large, small, and zero weights in adjacency matrices. Since IDEA adopts an inductive dynamic embedding scheme with an attentive node aligning unit and adaptive embedding aggregation module, it can also tackle the TLP on weighted graphs even with non-fixed node sets. Experiments on datasets of various scenarios validate that IDEA can derive high-quality prediction results for weighted dynamic graphs and tackle the variation of node sets.
15 June 2023 in ACM Transactions on Knowledge Discovery From Data
Many network applications can be formulated as NP-hard combinatorial optimization problems of community detection (CD) that partitions nodes of a graph into several groups with dense linkage. Most existing CD methods are transductive , which independently optimized their models for each single graph, and can only ensure either high quality or efficiency of CD by respectively using advanced machine learning techniques or fast heuristic approximation. In this study, we consider the CD task and aims to alleviate its NP-hard challenge. Motivated by the efficient inductive inference of graph neural networks (GNNs), we explore the possibility to achieve a better tradeoff between the quality and efficiency of CD via an inductive embedding scheme across multiple graphs of a system and propose a novel inductive community detection (ICD) method. Concretely, ICD first conducts the offline training of an adversarial dual GNN structure on historical graphs to capture key properties of a system. The trained model is then directly generalized to new graphs of the same system for online CD without additional optimization, where a better tradeoff between quality and efficiency can be achieved. Compared with existing inductive approaches, we develop a novel feature extraction module based on graph coarsening, which can efficiently extract informative feature inputs for GNNs. Moreover, our original designs of adversarial dual GNN and clustering regularization loss further enable ICD to capture permutation-invariant community labels in the offline training and help derive community-preserved embedding to support the high-quality online CD. Experiments on a set of benchmarks demonstrate that ICD can achieve a significant tradeoff between quality and efficiency over various baselines.
The prediction of mobility, topology and traffic is an effective technique to improve the performance of various network systems, which can be generally represented as the temporal link prediction problem. In this paper, we propose a novel adaptive multiple nonnegative matrix factorization (AM-NMF) method from the view of network embedding to cope with such problem. Under the framework of non-negative matrix factorization (NMF), the proposed method embeds the dynamic network into a low-dimensional hidden space, where the characteristics of different network snapshots are comprehensively preserved. Especially, our new method can effectively incorporate the hidden information of different time slices, because we introduce a novel adaptive parameter to automatically adjust the relative contribution of different terms in the uniform model. Accordingly, the prediction result of future network topology can be generated by conducting the inverse process of NMF form the shared hidden space. Moreover, we also derive the corresponding solving strategy whose convergence can be ensured. As an illustration, the new model will be applied to various network datasets such as human mobility networks, vehicle mobility networks, wireless mesh networks and data center networks. Experimental results show that our method outperforms some other state-of-the-art methods for the temporal link prediction of both unweighted and weighted networks.
Community detection (CD) is a classic graph inference task that partitions nodes of a graph into densely connected groups. While many CD methods have been proposed with either impressive quality or efficiency, balancing the two aspects remains a challenge. This study explores the potential of deep graph learning to achieve a better trade-off between the quality and efficiency of K-agnostic CD, where the number of communities K is unknown. We propose PRoCD (Pre-training & Refinement fOr Community Detection), a simple yet effective method that reformulates K-agnostic CD as the binary node pair classification. PRoCD follows a pre-training & refinement paradigm inspired by recent advances in pre-training techniques. We first conduct the offline pre-training of PRoCD on small synthetic graphs covering various topology properties. Based on the inductive inference across graphs, we then generalize the pre-trained model (with frozen parameters) to large real graphs and use the derived CD results as the initialization of an existing efficient CD method (e.g., InfoMap) to further refine the quality of CD results. In addition to benefiting from the transfer ability regarding quality, the online generalization and refinement can also help achieve high inference efficiency, since there is no time-consuming model optimization. Experiments on public datasets with various scales demonstrate that PRoCD can ensure higher efficiency in K-agnostic CD without significant quality degradation.