Session-based recommendation systems focus on capturing users’ evolving intents from short interaction sequences, yet they persistently face three key challenges: the difficulty in dynamically discriminating between short-term and long-term interests, the inherent tradeoff between sequential modeling and relational dependency learning, and the pervasive noise and sparsity in real-world session data. To tackle these issues, we propose Multivariate Relationship Graph Embedding (MRGE), a novel framework that synergizes enhanced recurrent modeling with graph-structured representations. Specifically, MRGE leverages a self-attention–enhanced RNN to concurrently model short-term intents and long-term preferences within sessions, while constructing a heterogeneous session graph that captures multi-relational item dependencies without compromising temporal fidelity. In addition, we introduce an auxiliary edge augmentation mechanism based on neighbor similarity to mitigate data sparsity and noise, thereby facilitating more robust information propagation. Extensive experiments on three public benchmarks— Delicious , Gowalla , and Foursquare —show that MRGE consistently surpasses state-of-the-art baselines and achieves significant improvements in top- \(K\) recommendation accuracy. Our implementation is available at: https://github.com/July-jz/MRGEcode .

Spatiotemporal fusion strategies are a crucial direction in traffic flow prediction. However, studies often emphasize the learning of local dynamic spatiotemporal dependencies from historical data while neglecting the potential impacts of label sequence autocorrelation, nonstationary signals, and temporal pattern changes on spatiotemporal dependency modeling. For example, the delayed propagation of abnormal traffic conditions, such as sudden traffic congestion, and abnormal weather between nodes and within sequences may trigger signal shifts, which in turn lead to changes in local flow patterns. Such changes can produce locally dependent misleading learning, making it difficult for spatiotemporal fusion strategies to accurately reflect the true relationships between signals. We propose a framework for traffic flow prediction, which first enhances the original signals in a targeted manner using knowledge of the autocorrelation of sequences through a multiform feature enhancement module, to obtain a more representative and enriched feature representation for model training. The framework processes features by decoupling multi-granularity in temporal patterns, comprehensively identifying complex traffic patterns, and eliminating the impact of nonstationary noise. A dual-channel spatiotemporal fusion network models local spatiotemporal dependencies and global seasonal dependencies to reasonably predict traffic. Experimental results on four real-world datasets show that the original method improves the Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) metrics by an average of 5.47%, 4.27%, and 7.05%, respectively, compared to all the metrics of the baseline model over the last two years. We also evaluated the performance of each module through ablation studies.

A common paradigm is followed by several current click-through rate (CTR) prediction models based on user behavior sequences. They first apply embedding technology to map users’ past behavior to low-dimensional dense vectors and then utilize an attention technique to acquire user interest representation from behavior sequences, using current candidates as queries. However, these approaches overemphasize the role of items similar to the candidate items in the historical sequence and ignore the learning of other contextual features as well as the sequential behavior patterns of users. In this article, we present a deep click-through prediction model that incorporates a multigranularity interest activation and implicit feature interactions. Our model first incorporates the nonlinearly extended user representation in the user behavior sequence and uses multiple fully connected layers to obtain the global user interest representation, thereby improving the model’s memorization ability for users. Then, a multikernel convolutional network is employed to learn the behavior patterns of the user with different window sizes to solve the problem of pattern diversity and interest mutation noise in behavioral sequences. Finally, the model implements implicit second-order feature interactions across the user-side, item-side, and contextual features via a multihead self-attention network, which can maintain the model’s performance in the presence of scarce user behavior sequences. Compared with the benchmark model, deep interest network (DIN), our model achieved RelaImpr gains of 1.67%, 3.36%, and 3.04% on three publicly available datasets and 6.09%, 6.08%, and 10.22% with the elimination of user history behavior sequence information. Experiments and discussions on module ablation and parameters that have a significant impact on model performance are also presented.

The flourishment of machine learning and deep learning methods has boosted the development of cheminformatics, especially regarding the application of drug discovery and new material exploration. Lower time and space expenses make it possible for scientists to search the enormous chemical space. Recently, some work combined reinforcement learning strategies with recurrent neural network (RNN)-based models to optimize the property of generated small molecules, which notably improved a batch of critical factors for these candidates. However, a common problem among these RNN-based methods is that several generated molecules have difficulty in synthesizing despite owning higher desired properties such as binding affinity. However, RNN-based framework better reproduces the molecule distribution among the training set than other categories of models during molecule exploration tasks. Thus, to optimize the whole exploration process and make it contribute to the optimization of specified molecules, we devised a light-weighted pipeline called Magicmol; this pipeline has a re-mastered RNN network and utilize SELFIES presentation instead of SMILES. Our backbone model achieved extraordinary performance while reducing the training cost; moreover, we devised reward truncate strategies to eliminate the model collapse problem. Additionally, adopting SELFIES presentation made it possible to combine STONED-SELFIES as a post-processing procedure for specified molecule optimization and quick chemical space exploration.

The adaptive neurofuzzy inference system (ANFIS) is a structured multioutput learning machine that has been successfully adopted in learning problems without noise or outliers. However, it does not work well for learning problems with noise or outliers. High-accuracy real-time forecasting of traffic flow is extremely difficult due to the effect of noise or outliers from complex traffic conditions. In this study, a novel probabilistic learning system, probabilistic regularized extreme learning machine combined with ANFIS (probabilistic R-ELANFIS), is proposed to capture the correlations among traffic flow data and, thereby, improve the accuracy of traffic flow forecasting. The new learning system adopts a fantastic objective function that minimizes both the mean and the variance of the model bias. The results from an experiment based on real-world traffic flow data showed that, compared with some kernel-based approaches, neural network approaches, and conventional ANFIS learning systems, the proposed probabilistic R-ELANFIS achieves competitive performance in terms of forecasting ability and generalizability.

In nanometric integrated circuits, to harden reliability-critical gates (RCGs) is an important step to improve overall circuit reliability at a low cost. To locate RCGs quickly and efficiently is a key prerequisite for selective hardening at the early stage of circuit design. This article develops a new approach for locating RCGs for multiple input vectors in combinational circuits, using an input vector-oriented pruning technology to identify RCGs, and a sensitivity-based algorithm to measure the criticality of gate reliability (CGR) for each identified RCG. To accelerate the location of RCGs, a feedback-based algorithm mines the accumulated simulation data for each RCG, and a grouping algorithm handles RCGs with similar CGR in the stage of convergence checking. Simulations on 74-series and ISCAS 85 benchmark circuits show that the average accuracy of the proposed method is 0.986 with Monte–Carlo (MC) as the reference and it is 7181 times faster than the MC model. Also, this method performs better than other approximate algorithms in terms of location accuracy and time overhead.

Reliable circuits help prevent artificial intelligence (AI) systems from being corrupted by the soft errors occurred in memories or combinational circuits, which promotes the development of AI security. However, it is a great challenge to measure the reliability of combinational circuits at register transfer level (RTL) rapidly and efficiently. In this paper, a new fast and accurate computational model based on stochastic computation (SC) is presented to meet these objectives. In the proposed approach, the circuit netlists at RTL are parsed to satisfy the requirements of SC on the bitstream structure of the circuits, and then a Sobol sequence-based algorithm for generating uniform non-Bernoulli sequences is built to reduce the random fluctuations occurred in probability calculations. After that, an adaptive algorithm based on a MAX–MIN ant system is constructed using graphics processing unit-based parallel schemes to greatly accelerate the calculation. The experimental results validate our proposed technique, showing that this approach was approximately 51 and 42 times faster than the traditional SC approach and the stochastic computational model (SCM), respectively; its required sequence length was approximately 1.66 times shorter than that of the traditional SC approach, and its relative error was two times smaller than that of the SCM.