Longer historical behaviors often improve recommendation accuracy but bring efficient problems. As sequences get longer, the following two main challenges have not been addressed: (1) efficient modeling under increasing sequence length and (2) interest drifting within historical items. In this paper, we propose Iterative Sparse Attention for Long-sequence Recommendation (ISA) with Sparse Attention Layer and Iterative Attention Layer to efficiently capture sequential pattern and expand the receptive field of each historical items. We take the pioneering step to address the efficient and interest drifting challenges for the long-sequence recommendation simultaneously. The theoretical analysis illustrates that our proposed iterative method can approximate full attention efficiently. Experiments on two real-world datasets show the superiority of our proposed method against state-of-the-art baselines.

Session-based recommendation (SBR) methods often rely on user behavior data, which can struggle with the sparsity of session data, limiting performance. Researchers have identified that beyond behavioral signals, rich semantic information in item descriptions is crucial for capturing hidden user intent. While Large Language Models (LLMs) offer new ways to leverage this semantic data, the challenges of session anonymity, short-sequence nature, and high LLM training costs have hindered the development of a lightweight, efficient LLM framework for SBR. To address the above challenges, we propose an LLM-enhanced SBR framework that integrates semantic and behavioral signals from multiple views. This two-stage framework leverages the strengths of both LLMs and traditional SBR models while minimizing training costs. In the first stage, we use multi-view prompts to infer latent user intentions at the session semantic level, supported by an intent localization module to alleviate LLM hallucinations. In the second stage, we align and unify these semantic inferences with behavioral representations, effectively merging insights from both large and small models. Extensive experiments on two real datasets demonstrate that the LLM4SBR framework can effectively improve model performance. We release our codes along with the baselines at https://github.com/tsinghua-fib-lab/LLM4SBR .

We propose some better word embedding models based on vLBL model and ivLBL model by sharing representations between context and target words and using document representations. Our proposed models are much simpler which have almost half less parameters than the state-of-the-art methods. We achieve better results on word analogy task than the best ones reported before using significantly less training data and computing time.

Many remote authentication schemes attempt to preserve user anonymity from the eavesdropper. However, authentication schemes in many e-commerce transactions require not only anonymous to the eavesdropper but also to the authentication server. In this paper, we propose a remote authentication scheme using smart card to fulfill both of the requirements. The proposed scheme achieves mutual authentication and allows users to choose and change their own passwords freely and securely. We only use one-way hash function and bitwise XOR operation in the proposed scheme and so the scheme has a low computational complexity. By using timestamp and random numbers, the proposed scheme can resist the denial of service attack and the replay attack. Also, the scheme is secure against guessing attack, insider attack, stolen-verifier attack, reflection attack, and impersonation attack.