Sequential recommendation aims to predict the next item a user is likely to interact with based on their historical interaction sequence. Capturing user intent is crucial in this process, as each interaction is typically driven by specific intentions (e.g., buying skincare products for skin maintenance, buying makeup for cosmetic purposes, etc.). However, users often have multiple, dynamically changing intents, making it challenging for models to accurately learn these intents when relying on the entire historical sequence as input. To address this, we propose a novel framework called Intent Oriented Contrastive Learning for Sequential Recommendation (IOCLRec). This framework begins by segmenting users’ sequential behaviors into multiple subsequences, which represent the coarse-grained intents of users at different points in their interaction history. These subsequences form the basis for the three contrastive learning modules within IOCLRec. The fine-grained intent contrastive learning module uncovers detailed intent representations, while the single-intent and multi-intent contrastive learning modules utilize intent-oriented data augmentation operators to capture the diverse intents of users. These three modules work synergistically, driving comprehensive performance optimization in intricate sequential recommendation scenarios. Our method has been extensively evaluated on four public datasets, demonstrating superior effectiveness.

Abstract. We obtain lower and upper bounds for the maximum weight of a directed cut in the classes of weighted digraphs and weighted acyclic digraphs as well as in some of their subclasses. We compare our results with those obtained for the maximum size of a directed cut in unweighted digraphs. In particular, we show that a lower bound obtained by Alon, Bollobás, Gyárfás, Lehel, and Scott [ J. Graph Theory, 55 (2007), pp. 1–13] for unweighted acyclic digraphs can be extended to weighted digraphs with the maximum length of a cycle being bounded by a constant and the weight of every arc being at least one. We state a number of open problems.