Representation learning is essential for deep-neural-network-based recommender systems to capture user preferences and item features within fixed-dimensional user and item vectors. Unlike existing representation learning methods that either treat each user preference and item feature uniformly or categorize them into discrete clusters, we argue that in the real world, user preferences and item features are naturally expressed and organized in a hierarchical manner, leading to a new direction for representation learning. In this article, we introduce a novel matryoshka representation learning method for recommendation (MRL4Rec) , by which we restructure user and item vectors into matryoshka representations with nested vector spaces to explicitly represent user preferences and item features at different hierarchical layers. We theoretically establish that training with the same triplets for each sliced vector cannot guarantee representation learning with hierarchical structures. Subsequently, we propose the layer- and hardness-adaptive negative sampling (LHANS) mechanism to construct training triplets, which further ensures the soundness of learned matryoshka representations in capturing hierarchical user preferences and item features. The experiments demonstrate that MRL4Rec can consistently and substantially outperform a number of state-of-the-art competitors on several real-life datasets. Our code is publicly available at https://github.com/Riwei-HEU/MRL .

Implicit feedback has become the primary source of training data for modern recommender systems due to its abundance and ease of collection. However, the inherent noise in implicit feedback poses significant challenges to model training. Existing denoising approaches either completely remove suspected noisy interactions (re-sampling) or uniformly adjust their importance (re-weighting). Such coarse-grained treatments fail to capture the complex nature of noise in real-world scenarios, where different aspects of an interaction may have varying noise levels.

Negative sampling plays a crucial role in implicit-feedback-based collaborative filtering, where it leverages massive unlabeled data to generate negative signals for guiding supervised learning. The current state-of-the-art approaches focus on utilizing hard negative samples that contain more information to establish a better decision boundary. To strike a balance between efficiency and effectiveness, most existing methods adopt a two-pass approach: In the first pass, a fixed number of unobserved items are sampled using a simple static distribution, while, in the second pass, a more sophisticated negative sampling strategy is employed to select the final negative items. However, selecting negative samples solely from the original items in a dataset is inherently restricted due to the limited available choices and thus may not be able to effectively contrast positive samples. In this article, we empirically validate this observation through meticulously designed experiments and identify three major limitations of existing solutions: ambiguous trap, information discrimination, and false-negative samples. Our response to such limitations is to introduce “denoised” and “augmented” negative samples that may not exist in the original dataset. This direction renders a few substantial technical challenges. First, constructing augmented negative samples may introduce excessive noise that eventually distorts the decision boundary. Second, the scarcity of supervision signals hampers the denoising process. To this end, we introduce, to the best of our knowledge, a novel generic denoising and augmented negative sampling paradigm and provide a concrete instantiation. First, we disentangle the hard and easy factors of negative items. Then, we regulate the augmentation of easy factors by carefully considering the direction and magnitude. Next, we propose a reverse attention mechanism to learn a user’s negative preference, which allows us to perform a dimension-level denoising procedure on hard factors. Finally, we design an advanced negative sampling strategy to identify the final negative samples, taking into account both the score function used in existing methods and, to the best of our knowledge, a novel metric called synthesization gain. Through extensive experiments on real-world datasets, we demonstrate that our method substantially outperforms state-of-the-art baselines. Our code is publicly available at https://github.com/Asa9aoTK/ANS-Recbole .

Negative sampling is essential for implicit collaborative filtering to provide proper negative training signals so as to achieve desirable performance. We experimentally unveil a common limitation of all existing negative sampling methods that they can only select negative samples of a fixed hardness level, leading to the false positive problem (FPP) and false negative problem (FNP). We then propose a new paradigm called adaptive hardness negative sampling (AHNS) and discuss its three key criteria. By adaptively selecting negative samples with appropriate hardnesses during the training process, AHNS can well mitigate the impacts of FPP and FNP. Next, we present a concrete instantiation of AHNS called AHNS_{p

Cross-domain sequential recommendation (CDSR) aims to predict the next item that a user is most likely to interact with based on past sequential behavior from multiple domains. Existing works on CDSR usually transfer knowledge across different domains by linking items between domains via common users, which suffers from the following limitations: (1) due to the inherent differences between the domains, transferring information across domains can be affected by different representations of related items in different domains. (2) None of existing studies consider the time interval information among items, which is essential in sequential recommendation to capture user intents over time. In this work, we propose a novel cross-domain sequential recommendation model to address the above challenges. Specifically, we first design a shared proxy item encoder to generate a universal representation for each item in all domains by using its textual descriptions. Then, we develop a time-interval-aware attention encoder to represent sequences by considering the time interval information. Moreover, we present a contrastive learning auxiliary task to enhance a cross-domain sequence by weighing the importance of the items in the auxiliary domain with respect to the objective domain. Experiments demonstrate the superiority of our proposed method from various aspects.

Negative sampling is essential for implicit-feedback-based collaborative filtering, which is used to constitute negative signals from massive unlabeled data to guide supervised learning. The state-of-the-art idea is to utilize hard negative samples that carry more useful information to form a better decision boundary. To balance efficiency and effectiveness, the vast majority of existing methods follow the two-pass approach, in which the first pass samples a fixed number of unobserved items by a simple static distribution and then the second pass selects the final negative items using a more sophisticated negative sampling strategy. However, selecting negative samples from the original items in a dataset is inherently restricted due to the limited available choices, and thus may not be able to contrast positive samples well. In this paper, we confirm this observation via carefully designed experiments and introduce two major limitations of existing solutions: ambiguous trap and information discrimination.

Negative sampling is essential for implicit collaborative filtering to generate negative samples from massive unlabeled data. Unlike existing strategies that consider items as a whole when selecting negative items, we argue that normally user interactions are mainly driven by some relevant, but not all, factors of items, leading to a new direction of negative sampling. In this paper, we introduce a novel disentangled negative sampling (DENS) method. We first disentangle the relevant and irrelevant factors of positive and negative items using a hierarchical gating module. Next, we design a factor-aware sampling strategy to identify the best negative samples by contrasting the relevant factors while keeping irrelevant factors similar. To ensure the credibility of the disentanglement, we propose to adopt contrastive learning and introduce four pairwise contrastive tasks, which enable to learn better disentangled representations of the relevant and irrelevant factors and remove the dependency on ground truth. Extensive experiments on five real-world datasets demonstrate the superiority of DENS against several state-of-the-art competitors, achieving over 7% improvement over the strongest baseline in terms of [email protected] and [email protected] Our code is publically available at https://github.com/Riwei-HEU/DENS .

As an emerging paradigm, session-based recommendation is aimed at recommending the next item based on a set of anonymous sessions. Effectively representing a session that is normally a short interaction sequence renders a major technical challenge. In view of the limitations of pioneering studies that explore collaborative information from other sessions, in this paper we propose a new direction to enhance session representations by learning multi-faceted session-independent global item relations. In particular, we identify three types of advantageous global item relations, including negative relations that have not been studied before, and propose different graph construction methods to capture such relations. We then devise a novel multi-faceted global item relation (MGIR) model to encode different relations using different aggregation layers and generate enhanced session representations by fusing positive and negative relations. Our solution is flexible to accommodate new item relations and can easily integrate existing session representation learning methods to generate better representations from global relation enhanced session information. Extensive experiments on three benchmark datasets demonstrate the superiority of our model over a large number of state-of-the-art methods. Specifically, we show that learning negative relations is critical for session-based recommendation.