Cold-start sequential recommendation, where user interaction histories are sparse or minimal, remains a significant challenge in recommendation systems. Current meta-learning-based approaches rely heavily on the interaction histories of regular users to construct meta-tasks, aiming to acquire prior knowledge for cold-start adaptation. However, these methods often fail to account for preference discrepancies between regular and cold-start users, leading to biased preference modeling and suboptimal recommendations. To address this issue, we propose a novel counterfactual task-augmented meta-learning method for cold-start sequential recommendations. Our approach intervenes in user interaction histories to create counterfactual sequences that simulate potential but unrealized user behaviors, establishing counterfactual tasks within a meta-learning framework. Additionally, we aggregate meta-path neighbors to uncover latent relationships between items, enabling more detailed and accurate modeling of user preferences. Moreover, by integrating real and counterfactual task losses, we jointly optimize the model through a combination of global and local updates, enhancing its adaptability to cold-start scenarios. Extensive experiments demonstrate that our method significantly outperforms existing state-of-the-art techniques, achieving superior results in cold-start sequential recommendation tasks.

Multi-criteria (MC) ratings can improve the predictive performance of recommender systems by introducing fine-grained auxiliary information. The existing MC methods usually model each criterion rating independently and leverage a utility function (e.g., simple averaging) for recommendation purpose. However, this modeling paradigm ignores two important aspects. First, the MC rating view significantly increases data sparsity, which poses a serious challenge for mining users’ MC preferences. Second, the noisy interactions carried by MC ratings may generate misleading decision results. To jointly address the above limitations, we propose a Self-supervised Multi-Criteria Recommendation (SMCR) framework, which aims to mitigate the negative impact caused by the data sparsity and noise problems. Specifically, the SMCR first models higher-order dependencies among users and items based on graph convolutional neural networks. Subsequently, an inter-criterion attentional mechanism is constructed to measure the heterogeneity exhibited by users in their MC preferences. Moreover, we design a cross-criteria self-supervised learning task that augments the robustness of embedding representations through knowledge transfer among views. The optimization objective of this task effectively suppresses the interference of sparse environment and noise on the model. The experimental results in four real scenarios demonstrate that the proposed SMCR outperforms the state-of-the-art MC baselines.

Multi-criteria (MC) ratings as auxiliary supervisory signals can improve the prediction accuracy of recommender systems. The existing MC methods learn the representations of users and items in Euclidean space to estimate the interaction probabilities. However, this modeling paradigm ignores two important aspects. Firstly, when embedding power-law distribution data and personalized MC preferences in Euclidean space, the model may produce suboptimal solutions due to the distortion of the hierarchical structure. Secondly, the inevitable noise in MC ratings may hinder the recommendation quality of the model. To address the above issues, we propose a novel framework called Hyperbolic Multi-Criteria Recommendation (HMCR), which aims to mine users' MC behavioral features on hyperbolic manifolds and mitigate the noise interference through knowledge transfer among the criteria. Specifically, we map the representations on each criterion view to a hyperbolic space with adjustable curvature based on the Lorentz model, which is used to capture the hierarchical structure of collective user behavior. The MC preferences of individual users are fused by calculating the hyperbolic attention among each criterion and the overall rating. Moreover, we design a self-supervised contrastive loss to suppress the negative impact of noise interactions on the model. The experimental results on four real-world datasets show that the HMCR significantly outperforms the existing baselines.

Recommender systems are designed to assist users in discovering interesting items and bringing profits to online platforms. The existing works primarily explore the correlation between historical feedback and model predictions through the data-driven paradigm based on a single user-item rating matrix (i.e., overall rating). However, this single-criterion methods ignore the users’ multi-criteria (MC) behavioral characteristics. For example, a hotel system allows users to rate from multiple dimensions, such as environment and location (i.e., MC ratings). Moreover, selection bias is pervasive in user behavior data. Traditional data-driven methods may induce spurious association and amplified biases. To address the above challenges, we propose a debiasing framework called Multi-Criteria Causal Recommendation (MCCR), which encapsulates users’ diverse MC preferences and employs causal inference to construct novel training and inference strategies. Specifically, we first represent the causal relationships among variables in MC scenarios through the structural causal model. Then, we mitigate the negative impact of selection bias through the back-door adjustment. Next, a graph representation learning framework suitable for MC ratings is developed, which is used to extract higher-order information and infer the heterogeneity of users’ preferences with different criteria. Experimental results on six real datasets demonstrate that the MCCR significantly outperforms the existing baselines.