Related papers: Stratified Expert Cloning for Retention-Aware Reco…
Although a variety of methods have been proposed for sequential recommendation, it is still far from being well solved partly due to two challenges. First, the existing methods often lack the simultaneous consideration of the global…
In the context of a short video & live stream mixed recommendation scenario, the live stream recommendation system (RS) decides whether to allocate at most one live stream into the video feed for each user request. To maximize long-term…
We propose a theoretical framework for studying behavior cloning of complex expert demonstrations using generative modeling. Our framework invokes low-level controllers - either learned or implicit in position-command control - to stabilize…
Leveraging planning during learning and decision-making is central to the long-term development of intelligent agents. Recent works have successfully combined tree-based search methods and self-play learning mechanisms to this end. However,…
Semi-supervised learning (SSL) is an efficient framework that can train models with both labeled and unlabeled data, but may generate ambiguous and non-distinguishable representations when lacking adequate labeled samples. With…
Reinforcement learning (RL) algorithms have demonstrated promising results on complex tasks, yet often require impractical numbers of samples since they learn from scratch. Meta-RL aims to address this challenge by leveraging experience…
Recommender systems play a crucial role in tackling the challenge of information overload by delivering personalized recommendations based on individual user preferences. Deep learning techniques, such as RNNs, GNNs, and Transformer…
Reinforcement learning (RL) has shown great promise in optimizing long-term user interest in recommender systems. However, existing RL-based recommendation methods need a large number of interactions for each user to learn a robust…
On the internet, web surfers, in the search of information, always strive for recommendations. The solutions for generating recommendations become more difficult because of exponential increase in information domain day by day. In this…
Recommendation system plays an important role in online web applications. Sequential recommender further models user short-term preference through exploiting information from latest user-item interaction history. Most of the sequential…
Named Entity Recognition (NER) models capable of Continual Learning (CL) are realistically valuable in areas where entity types continuously increase (e.g., personal assistants). Meanwhile the learning paradigm of NER advances to new…
In modern social media platforms, an effective content recommendation should benefit both creators to bring genuine benefits to them and consumers to help them get really interesting content. To address the limitations of existing methods…
Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. However, a notable limitation of PbRL is its dependency on substantial human feedback. This dependency stems…
Supervised Learning is a way of developing Artificial Intelligence systems in which a computer algorithm is trained on labeled data inputs. Effectiveness of a Supervised Learning algorithm is determined by its performance on a given dataset…
Real-world tasks such as garment manipulation and table rearrangement demand robots to perform generalizable, highly precise, and long-horizon actions. Although imitation learning has proven to be an effective approach for teaching robots…
Video understanding plays a fundamental role for content moderation on short video platforms, enabling the detection of inappropriate content. While classification remains the dominant approach for content moderation, it often struggles in…
With the evolution of data collection ways, it is possible to produce abundant data described by multiple feature sets. Previous studies show that including more features does not necessarily bring positive effect. How to prevent the…
Model performance evaluation is a critical and expensive task in machine learning and computer vision. Without clear guidelines, practitioners often estimate model accuracy using a one-time completely random selection of the data. However,…
Self-supervised learning (SSL) has emerged as a powerful technique for learning rich representations from unlabeled data. The data representations are able to capture many underlying attributes of data, and be useful in downstream…
Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Existing methods typically treat parameters…