Identifying influential nodes is an important topic in many diverse applications, such as accelerating information propagation, controlling rumors and diseases. Many methods have been put forward to identify influential nodes in complex networks, ranging from node centrality to diffusion-based processes. However, most of the previous studies do not take into account overlapping communities in networks. In this paper, we propose an effective method based on network representation learning. The method considers not only the overlapping communities in networks, but also the network structure. Experiments on real-world networks show that the proposed method outperforms many benchmark algorithms and can be used in large-scale networks.

Traffic operations depend on forecasts that remain reliable during disruptions such as collisions, lane closures, and signal faults, and that can attribute an observed anomaly to a specific incident. We present STWaveCausal, an intervention-aware spatio-temporal traffic forecasting framework that couples prediction with a reusable counterfactual audit protocol for incident impact assessment. The framework annotates interventions, constructs matched controls, augments inputs with graph context, and learns an explicit effect head on synthetic incident pairs. A separate audit layer checks synthetic recovery, matching diagnostics, structure probes, placebo controls, sensitivity analysis, and external incident records to decide when an output can be interpreted as a causal effect. On four real traffic datasets, STWaveCausal achieves the best mean MAE on the matched-pair intervention benchmark for NYC Taxi, PEMS08, and PEMS04, while matching the accuracy of leading forecasters under the standard single-step protocol. Synthetic effect recovery is near-perfect in distribution and directional under protocol shift, and a PEMS-BAY incident audit shows documented-sensor top-k enrichment after Benjamini--Hochberg correction. The result is an auditable, reproducible forecasting tool for traffic management.

Accurate traffic flow forecasting serves as a cornerstone for intelligent transportation systems, enabling proactive accident prevention and metropolitan mobility optimization. However, existing approaches face fundamental limitations in modeling the spatiotemporal heterogeneity of traffic dynamics, particularly in simultaneously addressing (1) the decaying significance of temporal dependencies across input sequences and prediction horizons, (2) multi-scale spatial interactions spanning local congestion patterns and global functional correlations, and (3) inter-sample temporal variance in evolving traffic states. To address these limitations, this paper proposes MVA-DCNet (Multi-View Attention Dilated Convolutional Network), a novel deep learning architecture incorporating a multidimensional temporal analysis framework that systematically examines temporal influence mechanisms through three complementary perspectives: inter-sample variance, intra-sequence temporal importance, and output sequence temporal propagation. The proposed model systematically addresses temporal data heterogeneity through three innovative mechanisms: variance-aware data augmentation, adaptive temporal attention, and decaying loss weighting. For enhanced spatial correlation modeling, we develop a dilated convolutional architecture with enhanced receptive field coverage and multi-scale spatial pattern recognition capabilities. Empirical validation on two urban traffic datasets demonstrates superior efficacy in capturing complex spatiotemporal evolution patterns, achieving relative reductions of 12.7% and 9.3% in Root Mean Square Error (RMSE) respectively compared with state-of-the-art benchmarks.