Related papers: FAST: Similarity-based Knowledge Transfer for Effi…

Simultaneous translation (ST) starts translations synchronously while reading source sentences, and is used in many online scenarios. The previous wait-k policy is concise and achieved good results in ST. However, wait-k policy faces two…

The growing popularity of transfer learning, due to the availability of models pre-trained on vast amounts of data, makes it imperative to understand when the knowledge of these pre-trained models can be transferred to obtain…

We address the challenge of getting efficient yet accurate recognition systems with limited labels. While recognition models improve with model size and amount of data, many specialized applications of computer vision have severe resource…

One of the most fundamental, and yet relatively less explored, goals in transfer learning is the efficient means of selecting top candidates from a large number of previously trained models (optimized for various "source" tasks) that would…

Transfer in reinforcement learning refers to the notion that generalization should occur not only within a task but also across tasks. We propose a transfer framework for the scenario where the reward function changes between tasks but the…

Transfer effects manifest themselves both during training using a fixed data set and in inductive inference using accumulating data. We hypothesize that perturbing the data set by including more samples, instead of perturbing the model by…

Multi-Agent Reinforcement Learning (MARL) algorithms are widely adopted in tackling complex tasks that require collaboration and competition among agents in dynamic Multi-Agent Systems (MAS). However, learning such tasks from scratch is…

Neural Transfer Learning (TL) is becoming ubiquitous in Natural Language Processing (NLP), thanks to its high performance on many tasks, especially in low-resourced scenarios. Notably, TL is widely used for neural domain adaptation to…

In this paper, we investigate the problem of fast spectrum sharing in vehicle-to-everything communication. In order to improve the spectrum efficiency of the whole system, the spectrum of vehicle-to-infrastructure links is reused by…

Learning in games has been widely used to solve many cooperative multi-agent problems such as coverage control, consensus, self-reconfiguration or vehicle-target assignment. One standard approach in this domain is to formulate the problem…

Continual learning of a stream of tasks is an active area in deep neural networks. The main challenge investigated has been the phenomenon of catastrophic forgetting or interference of newly acquired knowledge with knowledge from previous…

Intermediate-task transfer can benefit a wide range of NLP tasks with properly selected source datasets. However, it is computationally infeasible to experiment with all intermediate transfer combinations, making choosing a useful source…

We consider a serious, previously-unexplored challenge facing almost all approaches to scaling up entity resolution (ER) to multiple data sources: the prohibitive cost of labeling training data for supervised learning of similarity scores…

Parameter-Efficient Transfer Learning (PETL) aims at efficiently adapting large models pre-trained on massive data to downstream tasks with limited task-specific data. In view of the practicality of PETL, previous works focus on tuning a…

Exploration and adaptation to new tasks in a transfer learning setup is a central challenge in reinforcement learning. In this work, we build on the idea of modeling a distribution over policies in a Bayesian deep reinforcement learning…

When faced with learning a set of inter-related tasks from a limited amount of usable data, learning each task independently may lead to poor generalization performance. Multi-Task Learning (MTL) exploits the latent relations between tasks…

Transfer reinforcement learning aims to improve the sample efficiency of solving unseen new tasks by leveraging experiences obtained from previous tasks. We consider the setting where all tasks (MDPs) share the same environment dynamic…

Most existing works on continual learning (CL) focus on overcoming the catastrophic forgetting (CF) problem, with dynamic models and replay methods performing exceptionally well. However, since current works tend to assume exclusivity or…

Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is an adaptation policy that updates the actor policy based on…

Solving multiple visual tasks using individual models can be resource-intensive, while multi-task learning can conserve resources by sharing knowledge across different tasks. Despite the benefits of multi-task learning, such techniques can…