Accurate traffic flow forecasting is a crucial component of intelligent transportation systems, playing a pivotal role in enhancing transportation intelligence. The integration of Graph Neural Networks (GNNs) and Transformers in traffic flow forecasting has gained significant adoption for enhancing prediction accuracy. Yet, the complex spatial and temporal dependencies present in traffic data continue to pose substantial challenges: (1) Most GNN-based methods assume that the graph structure reflects the actual dependencies between nodes, overlooking the complex dependencies present in the real-world context. (2) Standard time-series models are unable to effectively model complex temporal dependencies, hindering prediction accuracy. To tackle these challenges, the authors propose a novel Transformer-based Spatiotemporal Graph Diffusion Convolution Network (TSGDC) for Traffic Flow Forecasting, which leverages graph diffusion and transformer to capture the complexity and dynamics of spatial and temporal patterns, thereby enhancing prediction performance. The authors designed an Efficient Channel Attention (ECA) that learns separately from the feature dimensions collected by traffic sensors and the temporal dimensions of traffic data, aiding in spatiotemporal modeling. Chebyshev Graph Diffusion Convolution (GDC) is used to capture the complex dependencies within the spatial distribution. Sequence decomposition blocks, as internal operations of transformers, are employed to gradually extract long-term stable trends from hidden complex variables. Additionally, by integrating multi-scale dependencies, including recent, daily, and weekly patterns, accurate traffic flow predictions are achieved. Experimental results on various public datasets show that TSGDC outperforms conventional traffic forecasting models, particularly in accuracy and robustness.

Recommender systems provide an effective solution to the information overload and have become a research hotspot in both industry and academia. Some existing work on implicit feedback has made great progress. However, there are still the following shortcomings: 1) existing pairwise ranking methods mostly sample unobserved items uniformly to obtain negative samples, which brings a biased solution and insufficient convergence; 2) the recommendation result comes from a complicated process, which makes it less interpretable. Therefore, we put forward a Deep Recommendation with Adversarial Training (DRAT) model, which provides users with personalized recommendations by utilizing an encoder-decoder structure and adversarial training. It consists of two components: one is feature learning module in which the encoder captures the text features of items from user-generated reviews, and the decoder reconstructs the text with the captured features; the other is rating prediction module which utilizes adversarial training to generate personalized negative samples tackling the drawbacks of uniform negative sampling. Extensive experiments on five real-world datasets show that our proposed model significantly outperforms the baseline methods.

Many studies focusing on integrating reviews with ratings to improve recommendation performance have been quite successful. However, these works still face several shortcomings: (1) The importance of dynamically integrating review and interaction data features is typically ignored, yet treating these fusion features equally may lead to an incomplete understanding of user preferences. (2) Some forms of soft attention methods are adopted to model the local semantic information of words. As features thus captured may contain irrelevant information, the generated attention map is neither discriminatory nor detailed. In this paper, we propose a novel A daptive H ierarchical A ttention-enhanced G ated network integrating reviews for item recommendation , named AHAG. AHAG is a unified framework to capture the hidden intentions of users by adaptively incorporating reviews. Specifically, we design a gated network to dynamically fuse the extracted features and select the features that are most relevant to user preferences. To capture distinguishing fine-grained features, we introduce a hierarchical attention mechanism to learn important semantic information features and the dynamic interaction of these features. Besides, the high-order non-linear interaction of neural factorization machines is utilized to derive the rating prediction. Experiments on seven real-world datasets show that the proposed AHAG significantly outperforms state-of-the-art methods. Furthermore, the attention mechanism can highlight the relevant information in reviews to increase the interpretability of the recommendation task. Source codes are available in https://github.com/luojia527/AHAG .