Detecting a community in a network is a matter of discerning the distinct features and connections of a group of members that are different from those in other communities. The ability to do this is of great significance in network analysis. However, beyond the classic spectral clustering and statistical inference methods, there have been significant developments with deep learning techniques for community detection in recent years--particularly when it comes to handling high-dimensional network data. Hence, a comprehensive review of the latest progress in community detection through deep learning is timely. To frame the survey, we have devised a new taxonomy covering different state-of-the-art methods, including deep learning models based on deep neural networks (DNNs), deep nonnegative matrix factorization, and deep sparse filtering. The main category, i.e., DNNs, is further divided into convolutional networks, graph attention networks, generative adversarial networks, and autoencoders. The popular benchmark datasets, evaluation metrics, and open-source implementations to address experimentation settings are also summarized. This is followed by a discussion on the practical applications of community detection in various domains. The survey concludes with suggestions of challenging topics that would make for fruitful future research directions in this fast-growing deep learning field.

Graph neural networks (GNNs) tend to suffer from high computation costs due to the exponentially increasing scale of graph data and a large number of model parameters, which restricts their utility in practical applications. To this end, some recent works focus on sparsifying GNNs (including graph structures and model parameters) with the lottery ticket hypothesis (LTH) to reduce inference costs while maintaining performance levels. However, the LTH-based methods suffer from two major drawbacks: 1) they require exhaustive and iterative training of dense models, resulting in an extremely large training computation cost, and 2) they only trim graph structures and model parameters but ignore the node feature dimension, where vast redundancy exists. To overcome the above limitations, we propose a comprehensive graph gradual pruning framework termed CGP. This is achieved by designing a during-training graph pruning paradigm to dynamically prune GNNs within one training process. Unlike LTH-based methods, the proposed CGP approach requires no retraining, which significantly reduces the computation costs. Furthermore, we design a cosparsifying strategy to comprehensively trim all the three core elements of GNNs: graph structures, node features, and model parameters. Next, to refine the pruning operation, we introduce a regrowth process into our CGP framework, to reestablish the pruned but important connections. The proposed CGP is evaluated over a node classification task across six GNN architectures, including shallow models graph convolutional network (GCN) and graph attention network (GAT), shallow-but-deep-propagation models simple graph convolution (SGC) and approximate personalized propagation of neural predictions (APPNP), and deep models GCN via initial residual and identity mapping (GCNII) and residual GCN (ResGCN), on a total of 14 real-world graph datasets, including large-scale graph datasets from the challenging Open Graph Benchmark (OGB). Experiments reveal that the proposed strategy greatly improves both training and inference efficiency while matching or even exceeding the accuracy of the existing methods.

State-of-the-art heuristic algorithms to solve the vehicle routing problem with time windows (VRPTW) usually present slow speeds during the early iterations and easily fall into local optimal solutions. Focusing on solving the above problems, this paper analyzes the particle encoding and decoding strategy of the particle swarm optimization algorithm, the construction of the vehicle route and the judgment of the local optimal solution. Based on these, a hybrid chaos-particle swarm optimization algorithm (HPSO) is proposed to solve VRPTW. The chaos algorithm is employed to re-initialize the particle swarm. An efficient insertion heuristic algorithm is also proposed to build the valid vehicle route in the particle decoding process. A particle swarm premature convergence judgment mechanism is formulated and combined with the chaos algorithm and Gaussian mutation into HPSO when the particle swarm falls into the local convergence. Extensive experiments are carried out to test the parameter settings in the insertion heuristic algorithm and to evaluate that they are corresponding to the data’s real-distribution in the concrete problem. It is also revealed that the HPSO achieves a better performance than the other state-of-the-art algorithms on solving VRPTW.

With the rapid development of urbanization, the problem of urban traffic congestion has become increasingly prominent. Dynamic route guidance promises to improve the capacity of urban traffic management and mitigate traffic congestion in big cities. In the design of simulation-based experiments for most dynamic route guidance methods, the simulation data is generally estimated from a specific traffic scenario in the real-world. However, highly dynamic traffic in the city implies that traffic scenarios in real systems are diverse. Therefore, if a route guidance method cannot adjust its strategy according to the spatial and temporal characteristics of different traffic scenarios, then it cannot guarantee optimal results under all traffic scenarios. Thus, ideal dynamic route guidance methods should have a highly adaptive learning ability under diverse traffic scenarios so as to have extensive improvement capabilities for different traffic scenarios. In this study, an A* trajectory rejection method based on multi-agent reinforcement learning (A*R²) is proposed; the method integrates both system and user perspectives to mitigate traffic congestion and reduce travel time (TT) and travel distance (TD). First, owing to its adaptive learning ability, the A*R² can comprehensively analyze the traffic conditions for different traffic scenarios and intelligently evaluate the road congestion index from a system perspective. Then, the A*R² determines the routes for all vehicles from user perspective according to the road network congestion index. An extensive set of simulation experiments reveal that, under various traffic scenarios, the A*R² can rely on its adaptive learning ability to achieve better traffic efficiency. Moreover, even in cases where many drivers are not fully compliant with the route guidance, the traffic efficiency can still be improved significantly by A*R².