Time series with missing values are ubiquitous in healthcare scenarios, presenting significant challenges for analysis. Despite existing methods addressing imputation, they predominantly focus on leveraging intra-series information, neglecting the potential benefits that inter-series information could provide, such as reducing uncertainty and memorization effect. To bridge this gap, we propose PRIME, Prototype Recurrent Imputation ModEl, which integrates both intra-series and inter-series information for imputing missing values in irregularly sampled time series. PRIME comprises a prototype memory module for learning inter-series information, a bidirectional gated recurrent unit utilizing prototype information for imputation, and an attentive prototypical refinement module for adjusting imputations. We conduct extensive experiments on four datasets, and the results underscore PRIME’s superiority over the state-of-the-art models by up to 26% relative improvement in mean square error. Our code is available at https://jcst.ict.ac.cn/news/382.

Partial label learning (PLL) learns under label ambiguity where each training instance is annotated with a set of candidate labels, among which only one is the ground-truth label. Recent advances showed that PLL can be promoted by combining label disambiguation with representation learning coherently, which achieved state-of-the-art performance. However, most of the existing deep PLL methods over-emphasize pulling the inaccurate pseudo-label-induced positive samples and fail to achieve a balance between the intra-class compactness and the inter-class separability, thus leading to a sub-optimal representation space. In this paper, we solve this issue by taking into account the pure negative supervision information which can be extracted perfectly from the non-candidate label set. Methodologically, we propose a novel framework Negative Prototypical Contrasting (NPC). The optimization objective of NPC contrasts each instance with its candidate prototypes against its negative prototypes, aiming at a sufficiently distinguishable representation space. Based on the learned representations, the label disambiguation process is performed in a moving-average style. Theoretically, we show that the objective of NPC is equivalent to solving a constrained maximum likelihood optimization. We also justify applying the moving average from the stochastic expectation-maximization perspective. Empirically, extensive experiments demonstrate that the proposed NPC method achieves state-of-the-art classification performance on various datasets, and even competes with its supervised counterparts.