Related papers: Combining Models of Approximation with Partial Lea…

The growing literature of Federated Learning (FL) has recently inspired Federated Reinforcement Learning (FRL) to encourage multiple agents to federatively build a better decision-making policy without sharing raw trajectories. Despite its…

Continual learning is the problem of integrating new information in a model while retaining the knowledge acquired in the past. Despite the tangible improvements achieved in recent years, the problem of continual learning is still an open…

Learning probabilistic surrogates for partial differential equations remains challenging in data-scarce regimes: neural operators require large amounts of high-fidelity data, while generative approaches typically sacrifice resolution…

Grammatical inference is a classical problem in computational learning theory and a topic of wider influence in natural language processing. We treat grammars as a model of computation and propose a novel neural approach to induction of…

Many contrastive and meta-learning approaches learn representations by identifying common features in multiple views. However, the formalism for these approaches generally assumes features to be shared across views to be captured…

Learning near-optimal behaviour from an expert's demonstrations typically relies on the assumption that the learner knows the features that the true reward function depends on. In this paper, we study the problem of learning from…

Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos partially relevant to a given query. The core challenge lies in learning robust query-video alignment against spurious semantic correlations arising from inherent…

For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the…

In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. However, due to a problem known as catastrophic forgetting, neural networks suffer substantial…

End-to-end models for autonomous driving hold the promise of learning complex behaviors directly from sensor data, but face critical challenges in safety and handling long-tail events. Reinforcement Learning (RL) offers a promising path to…

Federated Learning (FL) is a novel, multidisciplinary Machine Learning paradigm where multiple clients, such as mobile devices, collaborate to solve machine learning problems. Initially introduced in Kone{\v{c}}n{\'y} et al. (2016a,b);…

Federated learning (FL) is a paradigm where many clients collaboratively train a model under the coordination of a central server, while keeping the training data locally stored. However, heterogeneous data distributions over different…

Few-shot class-incremental learning is to recognize the new classes given few samples and not forget the old classes. It is a challenging task since representation optimization and prototype reorganization can only be achieved under little…

Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguarding data privacy. On top of that, Federated Continual Learning (FCL) also accounts for data…

Recent advancements in cognitive science and multi-round reasoning techniques for Large Language Models (LLMs) suggest that iterative thinking processes improve problem-solving performance in complex tasks. Inspired by this, approaches like…

Partial label learning (PLL) seeks to train generalizable classifiers from datasets with inexact supervision, a common challenge in real-world applications. Existing studies have developed numerous approaches to progressively refine and…

Robust and efficient learning remains a challenging problem in robotics, in particular with complex visual inputs. Inspired by human attention mechanism, with which we quickly process complex visual scenes and react to changes in the…

We propose to study the problem of few-shot learning with the prism of inference on a partially observed graphical model, constructed from a collection of input images whose label can be either observed or not. By assimilating generic…

Federated learning is a communication-efficient training process that alternates between local training at the edge devices and averaging the updated local model at the central server. Nevertheless, it is impractical to achieve a perfect…

The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability…