Product search is crucial for customers to discover and purchase products. With the growing importance of AI explanations, many KG-based methods use independent reasoning paths to provide explanations for retrieved results. However, these methods often fail to relate explanations to the current query and provide only single-facet explanations rather than multi-facet explanations that address users’ diverse search intents, such as different categories or bands. To overcome this issue, we propose an explainable product search model QGCNM, to generate query-aware multi-facet explanations through hierarchical graph convolution. Specifically, we design a query-aware graph convolutional ranker to excavate user’s multi-aspect search intent and develop a multi-path reasoner to explore the intent-based multiple paths for multi-facet explanations. Empirical evaluations on Amazon datasets show that QGCNM outperforms existing models on retrieval effectiveness and has better explanation abilities.

User behavior records serve as the foundation for recommender systems. While the behavior data exhibits ease of acquisition, it often suffers from varying quality. Current methods employ data valuation to discern high-quality data from low-quality data. However, they tend to employ blackbox design, lacking transparency and interpretability. Besides, they are typically tailored to specific evaluation metrics, leading to limited generality across various tasks. To overcome these issues, we propose an explainable and versatile framework DVR which can enhance the efficiency of data utilization tailored to any requirements of the model architectures and evaluation metrics. For explainable data valuation, a data valuator is presented to evaluate the data quality via calculating its Shapley value from the game-theoretic perspective, ensuring robust mathematical properties and reliability. In order to accommodate various evaluation metrics, including differentiable and non-differentiable ones, a metric adapter is devised based on reinforcement learning, where a metric is treated as the reinforcement reward that guides model optimization. Extensive experiments conducted on various benchmarks verify that our framework can improve the performance of current recommendation algorithms on various metrics including ranking accuracy, diversity, and fairness. Specifically, our framework achieves up to 34.7% improvements over existing methods in terms of representative NDCG metric. The code is available at https://github.com/renqii/DVR.

Product search is crucial for users to find and purchase products they need. Personalized product search, which models users’ search intent and provides tailored results, has become a prominent research problem in industry and academia. Recent studies often leverage knowledge graphs (KGs) to improve search performance and generate explanations for search results. However, existing KG-based methods treat search and explanation tasks separately and explore paths in KGs as explanations, creating a gap between search results and generated explanations. Also, path-formed explanations in KGs are not flexible enough to build correlations with the user’s current query. To address these challenges, we propose P-PEG, a unified prompt-aware framework for personalized product search and explanation generation. P-PEG leverages a pre-trained language model (PLM) and search signal to enhance the generation of user-understandable explanations. We introduce a prompt learning technique and design prompt generators for search and explanation generation tasks based on a fixed PLM. By incorporating search results in explanation-based prompts, we bridge the gap between search results and explanations, facilitating better interaction. Additionally, we utilize the user’s current query, historical search log, and KGs to personalize the explanations and inject task knowledge into PLM. Experimental results show that P-PEG outperforms existing methods in the explanation generation task of the three datasets and the search task of the Electronics dataset, and achieves comparable performance in the search task of the Cellphones & Accessories and CD & Vinyl datasets.

Traditional search engines usually provide identical search results for all users, overlooking individual preferences. To counter this limitation, personalized search has been developed to re-rank results based on user preferences derived from query logs. Deep learning-based personalized search methods have shown promise, but they rely heavily on abundant training data, making them susceptible to data sparsity challenges. This paper proposes a Cognitive Personalized Search (CoPS) model, which integrates Large Language Models (LLMs) with a cognitive memory mechanism inspired by human cognition. CoPS employs LLMs to enhance user modeling and user search experience. The cognitive memory mechanism comprises sensory memory for quick sensory responses, working memory for sophisticated cognitive responses, and long-term memory for storing historical interactions. CoPS handles new queries using a three-step approach: identifying re-finding behaviors, constructing user profiles with relevant historical information, and ranking documents based on personalized query intent. Experiments show that CoPS outperforms baseline models in zero-shot scenarios.

Product search is one of the most effective tools for people to browse and purchase products on e-commerce platforms. Recent advances have mainly focused on ranking products by their likelihood to be purchased through retrieval models. However, they overlook the problem that users may not understand why certain products are retrieved for them. The lack of appropriate explanations can lead to an unsatisfactory user experience and further decrease user trust in the platforms. To address this problem, we propose a Query-aware Explainable Product Search with Reinforcement Knowledge Reasoning, namelyQEPS, which uses search behaviors related to the current query to reinforce explanations. Specifically, with the aim of retrieving suitable products with explanations, QEPS takes full advantage of the user-product knowledge graph (KG) and develops a reinforcement learning approach, characterized by the demonstration-guided policy network and query-aware rewards, to perform explicit multi-step reasoning on the KG. The reasoning paths between users and products are automatically derived from the current query-related search behavior, which can provide valuable signals as to why the retrieved products are more likely to satisfy the user's search intent. Empirical experiments on four datasets show that our model achieves remarkable performance and is able to generate reasonable explanations for the search results.

Ambiguity in queries is a common problem in information retrieval. There are currently two solutions: search result personalization and diversification. The former aims to tailor results for different users based on their preferences, but the limitations are redundant results and incomplete capture of user intents. The goal of the latter is to return results that cover as many aspects related to the query as possible. It improves diversity yet loses personality and cannot return the exact results the user wants. Intuitively, such two solutions can complement each other and bring more satisfactory reranking results. In this article, we propose a novel framework, namely, PnD , to integrate personalization and diversification reasonably. We employ the degree of refinding to determine the weight of personalization dynamically. Moreover, to improve the diversity and relevance of reranked results simultaneously, we design a reset RNN structure (RRNN) with the “reset gate” to measure the influence of the newly selected document on novelty. Besides, we devise a “subtopic learning layer” to learn the virtual subtopics, which can yield fine-grained representations of queries, documents, and user profiles. Experimental results illustrate that our model can significantly outperform existing search result personalization and diversification methods.

Knowledge graphs (KGs) have been widely used in recommendation systems to improve recommendation accuracy and interpretability effectively. Recent research usually endows KG reasoning to find the multi-hop user-item connection paths for explaining why an item is recommended. The existing path-finding process is well designed by logic-driven inference algorithms, while there exists a gap between how algorithms and users perceive the reasoning process. Factually, human thinking is a natural reasoning process that can provide more proper and convincing explanations of why particular decisions are made. Motivated by the Dual Process Theory in cognitive science, we propose a cognition-aware KG reasoning model CogER for Explainable Recommendation, which imitates the human cognition process and designs two modules, i.e., System~1 (making intuitive judgment) and System~2 (conducting explicit reasoning), to generate the actual decision-making process. At each step during the cognition-aware reasoning process, System~1 generates an intuitive estimation of the next-step entity based on the user's historical behavior, and System~2 conducts explicit reasoning and selects the most promising knowledge entities. These two modules work iteratively and are mutually complementary, enabling our model to yield high-quality recommendations and proper reasoning paths. Experiments on three real-world datasets show that our model achieves better recommendation results with explanations compared with previous methods.

Recent studies show that historical behaviors (such as queries and their clicks) contained in a search session can benefit the ranking performance of subsequent queries in the session. Existing neural context-aware ranking models usually rank documents based on either latent representations of user search behaviors or the word-level interactions between the candidate document and each historical behavior in the search session. However, these two kinds of models both have their own drawbacks. Representation-based models neglect fine-grained information on word-level interactions, whereas interaction-based models suffer from the length restriction of session sequence because of the large cost of word-level interactions. To complement the limitations of these two kinds of models, we propose a unified context-aware document ranking model that takes full advantage of both representation and interaction. Specifically, instead of matching a candidate document with every single historical query in a session, we encode the session history into a latent representation and use this representation to enhance the current query and the candidate document. We then just match the enhanced query and candidate document with several matching components to capture the fine-grained information of word-level interactions. Rich experiments on two public query logs prove the effectiveness and efficiency of our model for leveraging representation and interaction.

Knowledge graph (KG) entity typing focuses on inferring possible entity type instances, which is a significant subtask of knowledge graph completion (KGC). Existing entity typing methods usually exploit the entity representation to model the transmission between entities and their types, which cannot fully explore the fine-grained entity typing on identifying the semantic type of an entity. To address these issues, we propose Neighborhood-Attention Neural Fine-Grained Entity Typing (AttEt), which considers the neighborhood information of the entities from KGs to bridge entities and their types together. In this paper, AttEt first develops a type-specific attention mechanism to aggregate the neighborhood knowledge of the given entity with type-specific weights. These weights are beneficial to capture various characteristics for different types of the entity, and further imply the complex correlation among these fine-grained types. Then, AttEt adaptively integrates the aggregated neighbor-level representation with entity inherent embedding to calculate the matching score between the entity and its candidate type. Besides, many entities are sparse in their relations with other entities in KGs, which makes the entity typing task more challenging. To solve this problem, we present a smooth strategy on relation-sparsity entities to improve the robustness of the model. Extensive experiments on two real-world datasets (Freebase and YAGO) show that AttEt significantly outperforms state-of-the-art baselines in the [email protected] by 2.11% on Freebase and by 8.42% on YAGO, respectively.

Product search has been an important way for people to find products on online shopping platforms. Existing approaches in personalized product search mainly embed user preferences into one single vector. However, this simple strategy easily results in sub-optimal representations, failing to model and disentangle user’s multiple preferences. To overcome this problem, we proposed a category-aware multi-interest model to encode users as multiple preference embeddings to represent user-specific interests. Specifically, we also capture the category indications for each preference to indicate the distribution of categories it focuses on, which is derived from rich relations between users, products, and attributes. Based on these category indications, we develop a category attention mechanism to aggregate these various preference embeddings considering current queries and items as the user’s comprehensive representation. By this means, we can use this representation to calculate matching scores of retrieved items to determine whether they meet the user’s search intent. Besides, we introduce a homogenization regularization term to avoid the redundancy between user interests. Experimental results show that the proposed method significantly outperforms existing approaches.

Selecting reliable negative training instances is the challenging task in the implicit feedback-based recommendation, which is optimized by pairwise learning on user feedback data. The existing methods usually exploit various negative samplers (i.e., heuristic-based or GAN-based sampling) on user feedback data to improve the quality of negative samples. However, these methods usually focused on maintaining the hard negative samples with a high gradient for training, causing the false negative samples to be selected preferentially. The limitation of the false negative noise amplification may lead to overfitting and further poor generalization of the model. To address this issue, we propose a Gain-Tuning Dynamic Negative Sampling GDNS to make the recommendation more robust and effective. Our proposed model designs an expectational gain sampler, concerning the expectation of user’ preference gap between the positive and negative samples in training, to guide the negative selection dynamically. This gain-tuning negative sampler can effectively identify the false negative samples and further diminish the risk of introducing false negative instances. Moreover, for improving the training efficiency, we construct positive and negative groups for each user in each iteration, and develop a group-wise optimizer to optimize them in a cross manner. Experiments on two real-world datasets show our approach significantly outperforms state-of-the-art negative sampling baselines.

The core objective of modelling recommender systems from implicit feedback is to maximize the positive sample score sp and minimize the negative sample score sn, which can usually be summarized into two paradigms: the pointwise and the pairwise. The pointwise approaches fit each sample with its label individually, which is flexible in weighting and sampling on instance-level but ignores the inherent ranking property. By qualitatively minimizing the relative score sn − sp, the pairwise approaches capture the ranking of samples naturally but suffer from training efficiency. Additionally, both approaches are hard to explicitly provide a personalized decision boundary to determine if users are interested in items unseen. To address those issues, we innovatively introduce an auxiliary score bu for each user to represent the User Interest Boundary(UIB) and individually penalize samples that cross the boundary with pairwise paradigms, i.e., the positive samples whose score is lower than bu and the negative samples whose score is higher than bu. In this way, our approach successfully achieves a hybrid loss of the pointwise and the pairwise to combine the advantages of both. Analytically, we show that our approach can provide a personalized decision boundary and significantly improve the training efficiency without any special sampling strategy. Extensive results show that our approach achieves significant improvements on not only the classical pointwise or pairwise models but also state-of-the-art models with complex loss function and complicated feature encoding.

Knowledge graph embedding is an effective way to represent knowledge graph, which greatly enhance the performances on knowledge graph completion tasks, e.g., entity or relation prediction. For knowledge graph embedding models, designing a powerful loss framework is crucial to the discrimination between correct and incorrect triplets. Margin-based ranking loss is a commonly used negative sampling framework to make a suitable margin between the scores of positive and negative triples. However, this loss can not ensure ideal low scores for the positive triplets and high scores for the negative triplets, which is not beneficial for knowledge completion tasks. In this paper, we present a double limit scoring loss to separately set upper bound for correct triplets and lower bound for incorrect triplets, which provides more effective and flexible optimization for knowledge graph embedding. Upon the presented loss framework, we present several knowledge graph embedding models including TransE-SS, TransH-SS, TransD-SS, ProjE-SS and ComplEx-SS. The experimental results on link prediction and triplet classification show that our proposed models have the significant improvement compared to state-of-the-art baselines.

Recurrent neural network(RNN) has achieved remarkable performances in complex reasoning on knowledge bases, which usually takes as inputs vector embeddings of relations along a path between an entity pair. However, it is insufficient to extract local correlations of a path due to RNN is better at capturing global sequential information of a path. In this paper, we take full advantages of convolutional neural network that can effectively extract local features, and propose a convolutional-based RNN architecture denoted as C-RNN to perform reasoning. C-RNN first utilizes CNN to extract local high-level correlation features of a path, and then feeds the correlation features into recurrent neural network to model the path representation. Our C-RNN architecture is adaptable to obtain not only local features but also global sequential features of a path. Based on C-RNN architecture, we devise two models, the unidirectional C-RNN and bidirectional C-RNN. We empirically evaluate them on a large-scale FreeBase+ClueWeb prediction task. Experimental results show that C-RNN models achieve state-of-the-art predictive performance.

In knowledge graph embedding models, the margin-based ranking loss as the common loss function is usually used to encourage discrimination between golden triplets and incorrect triplets, which has proved effective in many translation-based models for knowledge graph embedding. However, we find that the loss function cannot ensure the fact that the scoring of correct triplets must be low enough to fulfill the translation. In this paper, we present a limit-based scoring loss to provide lower scoring of a golden triplet, and then to extend two basic translation models TransE and TransH, separately to TransE-RS and TransH-RS by combining limit-based scoring loss with margin-based ranking loss. Both the presented models have low complexities of parameters benefiting for application on large scale graphs. In experiments, we evaluate our models on two typical tasks including triplet classification and link prediction, and also analyze the scoring distributions of positive and negative triplets by different models. Experimental results show that the introduced limit-based scoring loss is effective to improve the capacities of knowledge graph embedding.