One goal of social recommendation is to utilize social information to alleviate data sparsity and improve recommendation accuracy. User social relationships are inherently graph-structured, graph neural network (GNN) has recently attracted extensive attention in social recommendation because of its capability to integrate structural information and topology. However, current graph neural network (GNN)-based social recommendation models fail to consider context information during user interactions, which hinders more accurate modeling of user interest features. To address this problem, we propose a new social recommendation model based on context-aware graph neural network named CENTRIC (User- C ont E xt Collaboratio N and T enso R Factorization for GNN-based Soc I al Re C ommendation). Specifically, first a multi-channel GNN model with user-context collaboration module is designed, so that context can directly affect user features and participate in the calculation of user interaction probability with items. Then tensor factorization is adopted in output layer to effectively fuse the features extracted from different channels. Experiments on three public datasets show that CENTRIC significantly outperforms other state-of-the-art social recommendation models, further experiments also demonstrate that context information and tensor factorization help improve the accuracy of GNN-based social recommendation.

Multimodal sensors, including vision sensors and wearable sensors, offer valuable complementary information for accurate recognition tasks. Nonetheless, the heterogeneity among sensor data from different modalities presents a formidable challenge in extracting robust multimodal information amidst noise. In this paper, we propose an innovative approach, named semantic-aware multimodal transformer fusion decoupled knowledge distillation method (SMTDKD), which not only guides video data recognition through the information interaction between different wearable-sensor data, but also through the information interaction between visual sensor data and wearable-sensor data, improving the robustness of the model. To preserve the temporal relationship within wearable-sensor data, the SMTDKD method converts them into 2D image data. Furthermore, a transformer-based multimodal fusion module is designed to capture diverse feature information from distinct wearable-sensor modalities. To mitigate modality discrepancies and encourage similar semantic features, graph cross-view attention maps are constructed across various convolutional layers to facilitate feature alignment. Additionally, semantic information is exchanged among the teacher-student network, the student network, and BERT-encoded labels. To obtain more comprehensive knowledge transfer, the decoupled knowledge distillation loss is utilized, thereby enhancing the generalization of the network. Experimental evaluations conducted on three multimodal datasets, namely UTD-MHAD, Berkeley-MHAD, and MMAct, demonstrate the superior performance of the proposed SMTDKD method over the state-of-the-art action human recognition methods.

In recent years, the field of action recognition using spatio-temporal graph convolution models for human skeletal data has made significant progress. However, current methodologies tend to prioritize spatial graph convolution, which leads to an underutilization of valuable information present in skeletal data. It limits the model’s ability to effectively capture complex data patterns, especially in time series data, ultimately impacting recognition accuracy significantly. To address the above issues, this paper introduces an Attention-based Semantic-guided Multi-stream Graph Convolution Network (ASMGCN), which can extract the deep features in skeletal data more fully. Specifically, ASMGCN incorporates a novel temporal convolutional module featuring an attention mechanism and a multiscale residual network, which can dynamically adjust the weights between skeleton graphs at different time points, enabling better capture of relational features. In addition, semantic information is introduced into the loss function, enhancing the model’s ability to distinguish similar actions. Furthermore, the coordinate information of different joints within the same frame is explored to generate new relative position features known as centripetal and centrifugal streams based on the center of gravity. These features are integrated with the original position and motion features of skeleton, including joints and bones, enriching the inputs to the GCN network. Experimental results on the NW-UCLA, NTU RGB+D (NTU60) and NTU RGB+D 120 (NTU120) datasets demonstrate that ASMGCN outperforms other state-of-the-art (SOTA) Human Action Recognition (HAR) methods, signifying its potential in advancing the field of action recognition using skeletal data.

Sequential recommendation has attracted a lot of attention from both academia and industry, however the privacy risks associated with gathering and transferring users’ personal interaction data are often underestimated or ignored. Existing privacy-preserving studies are mainly applied to traditional collaborative filtering or matrix factorization rather than sequential recommendation. Moreover, these studies are mostly based on differential privacy or federated learning, which often lead to significant performance degradation, or have high requirements for communication. In this work, we address privacy-preserving from a different perspective. Unlike existing research, we capture collaborative signals of neighbor interaction sequences and directly inject indistinguishable items into the target sequence before the recommendation process begins, thereby increasing the perplexity of the target sequence. Even if the target interaction sequence is obtained by attackers, it is difficult to discern which ones are the actual user interaction records. To achieve this goal, we introduce a novel sequential recommender system called CoLlaborative-cOnfusion seqUential recommenDer (CLOUD) , which incorporates a collaborative confusion mechanism to modify the raw interaction sequences before conducting recommendation. Specifically, CLOUD first calculates the similarity between the target interaction sequence and other neighbor sequences to find similar sequences. Then, CLOUD considers the shared representation of the target sequence and similar sequences to determine the operation to be performed: keep, delete, or insert. A copy mechanism is designed to make items from similar sequences have a higher probability to be inserted into the target sequence. Finally, the modified sequence is used to train the recommender and predict the next item. We conduct extensive experiments on three benchmark datasets. The experimental results show that CLOUD achieves a maximum modification rate of 66.57% on interaction sequences and obtains over 99% recommendation accuracy compared to the state-of-the-art sequential recommendation methods. This proves that CLOUD can effectively protect user privacy at minimal recommendation performance cost, which provides a new solution for privacy-preserving for sequential recommendation. Our implementation is available at https://github.com/weiwang0927/CLOUD .

This study proposes an efficient method for computing State Vectors in Sequence-to-Sequence (SVSeq2Seq) architecture to improve the performance of sequence data forecasting, which associates each element with other elements instead of relying only on nearby elements. First, the dependency between two elements is adaptively captured by calculating the relative importance between hidden layers. Second, tensor train decomposition is used to address the issue of dimensionality catastrophe. Third, we further select seven instantiated baseline models for data prediction and compare them with our proposed model on six real-world datasets. The results show that the Mean Square Error (MSE) and Mean Absolute Error (MAE) of our SVSeq2Seq model exhibit significant advantages over the other seven baseline models in predicting the three datasets, i.e., weather, electricity, and PEMS, with MSE/MAE values as low as 0.259/0.260, 0.186/0.285 and 0.113/0.222, respectively. Furthermore, the ablation study demonstrates that the SVSeq2Seq model possesses distinct advantages in sequential forecasting tasks. It is observed that replacing SVSeq2Seq with LPRcode and NMTcode resulted in an increase under an MSE of 18.05 and 10.11 times, and an increase under an MAE of 16.54 and 9.8 times, respectively. In comparative experiments with support vector machines (SVM) and random forest (RF), the performance of the SVSeq2Seq model is improved by 56.88 times in the weather dataset and 73.78 times in the electricity dataset under the MSE metric, respectively. The above experimental results demonstrate both the exceptional rationality and versatility of the SVSeq2Seq model for data forecasting.