Sequential recommendation (SR) tasks aim to predict users' next interaction by learning their behavior sequence and capturing the connection between users' past interactions and their changing preferences. Conventional SR models often focus solely on capturing sequential patterns within the training data, neglecting the broader context and semantic information embedded in item titles from external sources. This limits their predictive power and adaptability. Large language models (LLMs) have recently shown promise in SR tasks due to their advanced understanding capabilities and strong generalization abilities. Researchers have attempted to enhance LLMs-based recommendation performance by incorporating information from conventional SR models. However, previous approaches have encountered problems such as 1) limited textual information leading to poor recommendation performance, 2) incomplete understanding and utilization of conventional SR model information by LLMs, and 3) excessive complexity and low interpretability of LLMs-based methods. To improve the performance of LLMs-based SR, we propose a novel framework, Distilling Sequential Pattern to Enhance LLMs-based Sequential Recommendation (DELRec), which aims to extract knowledge from conventional SR models and enable LLMs to easily comprehend and utilize the extracted knowledge for more effective SRs. DELRec consists of two main stages: 1) Distill Pattern from Conventional SR Models, focusing on extracting behavioral patterns exhibited by conventional SR models using soft prompts through two well-designed strategies; 2) LLMs-based Sequential Recommendation, aiming to fine-tune LLMs to effectively use the distilled auxiliary information to perform SR tasks. Extensive experimental results conducted on four real datasets validate the effectiveness of the DELRec framework.

Sequential recommendation (SR) aims to predict users’ next actions based on historical interaction sequences. Classical methods are developed based on deep learning mechanisms such as CNN, RNN, and Transformer to capture users’ behavioral sequential patterns. Despite their certain achievements, they still face challenges like data sparsity and limited understanding of item features. To address these issues, researchers have proposed the application of auxiliary information to enhance SR. In this paper, we realized that both cross-domain and multimodal information can be leveraged as auxiliary information to further improve the performance of SR, but how to make full use of them is faced with problems such as semantic inconsistency, inadequate user preferences mining, and the introduction of noise. To this end, we propose a MultiModal Cross-Domain Sequential Recommendation (MMCDSR) method, serving as a framework to jointly model modal and domain information for application in the SR. In MMCDSR, we design, (1) a semantic contrastive learning module to align modal and domain representations of items, (2) a sequential interest discovery module for capturing user preferences from different perspectives, and (3) an adaptive attention fusion module to eliminate noise features and generate the final user representation for the recommendation. Extensive experiments on six datasets from Amazon demonstrate that MMCDSR effectively leverages multimodal and cross-domain information, alleviates data sparsity issues, and significantly outperforms current baseline models in recommendation accuracy.

Cross-Domain Recommendation (CDR) is proposed to address the long-standing data sparsity problem in recommender systems (RSs). Traditional CDR only leverages relatively richer information from an auxiliary domain to improve the performance in a sparser domain, which is also called single-target CDR. In recent years, dual-target CDR has been proposed to improve recommendation performance in both domains simultaneously. The existing dual-target CDR methods are based on common users to achieve knowledge transfer between domains. We argue that the existing methods face two challenges: (1) how to learn more representative user and item embeddings in each domain, and (2) in the case of a small number of common users in real-world datasets, how to achieve better knowledge transfer. To address these challenges, in this paper, we propose a contrastive learning (CL) framework, called CL-DTCDR. In CL-DTCDR, we first design a CL task in each domain to learn more representative user and item embeddings. Then, we further construct positive pairs of the user and her/his most similar user between domains to optimize user embeddings. By two CL tasks, CL-DTCDR effectively improves performance in both domains. Extensive experiments conducted on three real-world datasets demonstrate that CL-DTCDR significantly outperforms the state-of-the-art approaches.

Recently, Graph Neural Networks (GNNs) have become a mainstream recommender system method, where it captures high-order collaborative signals between nodes by performing convolution operations on the user-item interaction graph to predict user preferences for different items. However, in real scenarios, the user-item interaction graph is extremely sparse, which means numerous users only interact with a small number of items, resulting in the inability of GNN in learning high-quality node embeddings. To alleviate this problem, the Graph Contrastive Learning (GCL)-based recommender system method is proposed. GCL improves embedding quality by maximizing the similarity of the positive pair and minimizing the similarity of the negative pair. However, most GCL-based methods use heuristic data augmentation methods, i.e., random node/edge drop and attribute masking, to construct contrastive pairs, resulting in the loss of important information. To solve the problems in GCL-based methods, we propose a novel method, Candidate-aware Graph Contrastive Learning for Recommendation, called CGCL. In CGCL, we explore the relationship between the user and the candidate item in the embedding at different layers and use similar semantic embeddings to construct contrastive pairs. By our proposed CGCL, we construct structural neighbor contrastive learning objects, candidate contrastive learning objects, and candidate structural neighbor contrastive learning objects to obtain high-quality node embeddings. To validate the proposed model, we conducted extensive experiments on three publicly available datasets. Compared with various state-of-the-art DNN-, GNN- and GCL-based methods, our proposed CGCL achieved significant improvements in all indicators.