The integration of Large Language Models (LLMs) into e-commerce platforms has significantly enhanced user experience through personalized recommendations and automated customer support. However, existing Retrieval-Augmented Generation (RAG) frameworks face challenges when applied to e-commerce product Question Answering (QA), such as handling extensive product catalogs, ensuring timely knowledge updates, and maintaining efficient retrieval performance. In this paper, we propose ItemRAG, a novel framework that combines RAG with item-based knowledge computing to address these challenges. ItemRAG decouples QA templates from specific products by leveraging a dynamic knowledge graph, enabling efficient updates and reducing the size of the knowledge base. The framework includes state analysis to capture user intent and context, grouped indexing for efficient retrieval, and knowledge computing to dynamically generate accurate answers. Experimental results demonstrate that decoupled-based ItemRAG significantly outperforms the Coupled-based RAG approaches (CoupledRAG) in retrieval accuracy and generation quality, achieving higher precision, recall, F1-score, and factual correctness. Our work highlights the efficacy of integrating the knowledge graph with RAG to enhance LLM-based e-commerce customer service systems.

Multi-task learning (MTL) can boost the performance of individual tasks by mutual learning among multiple related tasks. However, when these tasks assume diverse complexities, their corresponding losses involved in the MTL objective inevitably compete with each other and ultimately make the learning biased towards simple tasks rather than complex ones. To address this imbalanced learning problem, we propose a novel MTL method that can equip multiple existing deep MTL model architectures with a sequential cooperative distillation (SCD) module. Specifically, we first introduce an efficient mechanism to measure the similarity between tasks, and group similar tasks into the same block to allow their cooperative learning from each other. Based on this, the grouped task blocks are sorted in a queue to determine the learning sequence of the tasks according to their complexities estimated with the defined performance indicator. Finally, a distillation between the individual task-specific models and the MTL model is performed block by block from complex to simple manner, achieving a balance between competition and cooperation among learning multiple tasks. Extensive experiments demonstrate that our method is significantly more competitive compared with state-of-the-art methods, ranking No.1 with average performances across multiple datasets by improving 12.95% and 3.72% compared with OMTL and MTLKD, respectively.

The domain adversarial neural network (DANN) methods have been successfully proposed and attracted much attention recently. In DANNs, a discriminator is trained to discriminate the domain labels of features generated by a generator, whereas the generator attempts to confuse it such that the distributions between domains are aligned. As a result, it actually encourages the whole alignment or transfer between domains, while the inter-class discriminative information across domains is not considered. In this paper, we present a Discrimination-Aware Domain Adversarial Neural Network (DA2NN) method to introduce the discriminative information or the discrepancy of inter-class instances across domains into deep domain adaptation. DA2NN considers both the alignment within the same class and the separation among different classes across domains in knowledge transfer via multiple discriminators. Empirical results show that DA2NN can achieve better classification performance compared with the DANN methods.

With the rapid development of Web 2.0, more and more people are sharing their opinions about online products, so there is much product review data. However, it is difficult to compare products directly using ratings because many ratings are based on different scales or ratings are even missing. This paper addresses the following question: given textual reviews, how can we automatically determine the semantic orientations of reviewers and then rank different items? Due to the absence of ratings in many reviews, it is difficult to collect sufficient rating data for certain specific categories of products (e.g., movies), but it is easier to find rating data in another different but related category (e.g., books). We refer to this problem as transfer rating, and try to train a better ranking model for items in the interested category with the help of rating data from another related category. Specifically, we developed a ranking-oriented method called TRate for determining the semantic orientations and for ranking different items and formulated it in a regularized algorithm for rating knowledge transfer by bridging the two related categories via a shared latent semantic space. Tests on the Epinion dataset verified its effectiveness.