Related papers: PEACE: Prototype lEarning Augmented transferable f…

Training a robotic policy from scratch using deep reinforcement learning methods can be prohibitively expensive due to sample inefficiency. To address this challenge, transferring policies trained in the source domain to the target domain…

Conversational Recommender Systems (CRS) has become an emerging research topic seeking to perform recommendations through interactive conversations, which generally consist of generation and recommendation modules. Prior work on CRS tends…

Knowledge graphs (KGs) provide reliable external knowledge for a wide variety of AI tasks in the form of structured triples. Knowledge graph pre-training (KGP) aims to pre-train neural networks on large-scale KGs and provide unified…

Cross-domain sequential recommendation is the task of predict the next item that the user is most likely to interact with based on past sequential behavior from multiple domains. One of the key challenges in cross-domain sequential…

Reinforcement Learning (RL) provides a framework in which agents can be trained, via trial and error, to solve complex decision-making problems. Learning with little supervision causes RL methods to require large amounts of data, rendering…

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…

Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids. However, the…

Transcending the single-preference paradigm, aligning LLMs with diverse human values is pivotal for robust deployment. Contemporary Multi-Objective Preference Alignment (MPA) approaches predominantly rely on static linear scalarization or…

Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Despite the strong performance of Pre-Trained Models (PTMs) in CIL, a critical issue persists: learning new classes often…

Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift, unsupervised…

In many real-world scenarios, an autonomous agent often encounters various tasks within a single complex environment. We propose to build a graph abstraction over the environment structure to accelerate the learning of these tasks. Here,…

Cold-start issues have been more and more challenging for providing accurate recommendations with the fast increase of users and items. Most existing approaches attempt to solve the intractable problems via content-aware recommendations…

Generative large language models(LLMs) are proficient in solving general problems but often struggle to handle domain-specific tasks. This is because most of domain-specific tasks, such as personalized recommendation, rely on task-related…

One crucial aspect of partial domain adaptation (PDA) is how to select the relevant source samples in the shared classes for knowledge transfer. Previous PDA methods tackle this problem by re-weighting the source samples based on their…

Modern recommender systems trained on domain-specific data often struggle to generalize across multiple domains. Cross-domain sequential recommendation has emerged as a promising research direction to address this challenge; however,…

Deep Reinforcement Learning has been able to achieve amazing successes in a variety of domains from video games to continuous control by trying to maximize the cumulative reward. However, most of these successes rely on algorithms that…

Unsupervised domain adaptation (UDA) has been successfully applied to transfer knowledge from a labeled source domain to target domains without their labels. Recently introduced transferable prototypical networks (TPN) further addresses…

Real estate appraisal is important for a variety of endeavors such as real estate deals, investment analysis, and real property taxation. Recently, deep learning has shown great promise for real estate appraisal by harnessing substantial…

Domain adaptation (DA) attempts to transfer the knowledge from a labeled source domain to an unlabeled target domain that follows different distribution from the source. To achieve this, DA methods include a source classification objective…

Our goal in this research is to study a more realistic environment in which we can conduct weakly-supervised multi-modal instance-level product retrieval for fine-grained product categories. We first contribute the Product1M datasets, and…