相关论文: Intent Contrastive Learning for Sequential Recomme…

Recommender systems are designed to learn user preferences from observed feedback and comprise many fundamental tasks, such as rating prediction and post-click conversion rate (pCVR) prediction. However, the observed feedback usually suffer…

In session-based or sequential recommendation, it is important to consider a number of factors like long-term user engagement, multiple types of user-item interactions such as clicks, purchases etc. The current state-of-the-art supervised…

Recent advances in recommendation with large language models (LLMs) often rely on either commonsense augmentation at the item-category level or implicit intent modeling on existing knowledge graphs. However, such approaches struggle to…

In order to model the evolution of user preference, we should learn user/item embeddings based on time-ordered item purchasing sequences, which is defined as Sequential Recommendation (SR) problem. Existing methods leverage sequential…

Social recommendations utilize social relations to enhance the representation learning for recommendations. Most social recommendation models unify user representations for the user-item interactions (collaborative domain) and social…

Cross-domain recommendation (CDR) aims to improve recommendation accuracy in sparse domains by transferring knowledge from data-rich domains. However, existing CDR approaches often assume that user-item interaction data across domains is…

Contrastive learning is widely used for recommendation model learning, where selecting representative and informative negative samples is critical. Existing methods usually focus on centralized data, where abundant and high-quality negative…

Conventional Intent Detection (ID) models are usually trained offline, which relies on a fixed dataset and a predefined set of intent classes. However, in real-world applications, online systems usually involve continually emerging new user…

Transformer-based sequential recommendation (SR) models excel at modeling long-range dependencies in user behavior via self-attention. However, updating them with continuously arriving behavior sequences incurs high computational costs or…

Most dialogue systems in real world rely on predefined intents and answers for QA service, so discovering potential intents from large corpus previously is really important for building such dialogue services. Considering that most…

The emerging in-context learning (ICL) ability of large language models (LLMs) has prompted their use for predictive tasks in various domains with different data types, including tabular data, facilitated by serialization methods. However,…

The effectiveness of contrastive learning in sequential recommendation hinges on the construction of contrastive views, which ideally should be both semantically consistent and diverse. However, most existing CL-based methods rely on…

Recommending novel content, which expands user horizons by introducing them to new interests, has been shown to improve users' long-term experience on recommendation platforms \cite{chen2021values}. Users however are not constantly looking…

Graph-based collaborative filtering has emerged as a powerful paradigm for delivering personalized recommendations. Despite their demonstrated effectiveness, these methods often neglect the underlying intents of users, which constitute a…

Contrastive self-supervised learning (CSL) based on instance discrimination typically attracts positive samples while repelling negatives to learn representations with pre-defined binary self-supervision. However, vanilla CSL is inadequate…

Demonstration selection is a practical bottleneck in in-context learning (ICL): under a tight prompt budget, accuracy can change substantially depending on which few-shot examples are included, yet selection must remain cheap enough to run…

New intent discovery is a crucial capability for task-oriented dialogue systems. Existing methods focus on transferring in-domain (IND) prior knowledge to out-of-domain (OOD) data through pre-training and clustering stages. They either…

Many modern online services feature personalized recommendations. A central challenge when providing such recommendations is that the reason why an individual user accesses the service may change from visit to visit or even during an…

Reinforcement learning (RL) has made significant progress in various domains, but scaling it to long-horizon tasks with complex decision-making remains challenging. Skill learning attempts to address this by abstracting actions into…

In-Context Learning (ICL) empowers Large Language Models (LLMs) with the ability to learn from a few examples provided in the prompt, enabling downstream generalization without the requirement for gradient updates. Despite encouragingly…