Related papers: Zero-Shot Task Transfer
Developing meta-learning algorithms that are un-biased toward a subset of training tasks often requires hand-designed criteria to weight tasks, potentially resulting in sub-optimal solutions. In this paper, we introduce a new principled and…
To comply with AI and data regulations, the need to forget private or copyrighted information from trained machine learning models is increasingly important. The key challenge in unlearning is forgetting the necessary data in a timely…
Task embeddings are low-dimensional representations that are trained to capture task properties. In this paper, we propose MetaEval, a collection of $101$ NLP tasks. We fit a single transformer to all MetaEval tasks jointly while…
Do visual tasks have a relationship, or are they unrelated? For instance, could having surface normals simplify estimating the depth of an image? Intuition answers these questions positively, implying existence of a structure among visual…
Spatio-temporal machine learning is critically needed for a variety of societal applications, such as agricultural monitoring, hydrological forecast, and traffic management. These applications greatly rely on regional features that…
We propose a meta-learning algorithm utilizing a linear transformer that carries out null-space projection of neural network outputs. The main idea is to construct an alternative classification space such that the error signals during…
The task of triplet extraction aims to extract pairs of entities and their corresponding relations from unstructured text. Most existing methods train an extraction model on training data involving specific target relations, and are…
Neural Architecture Search (NAS) methods have been shown to outperform hand-designed models and help to democratize AI. However, NAS methods often start from scratch with each new task, making them computationally expensive and limiting…
Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data. In this work, we propose to transfer the \textit{cross-task}…
Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper…
Massively multilingual models are promising for transfer learning across tasks and languages. However, existing methods are unable to fully leverage training data when it is available in different task-language combinations. To exploit such…
We develop new algorithms for simultaneous learning of multiple tasks (e.g., image classification, depth estimation), and for adapting to unseen task/domain distributions within those high-level tasks (e.g., different environments). First,…
Entity matching (EM) identifies data records that refer to the same real-world entity. Despite the effort in the past years to improve the performance in EM, the existing methods still require a huge amount of labeled data in each domain…
In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate learning of novel future tasks. Under the assumption that future tasks are 'related' to previous tasks, the accumulated knowledge should be learned in a…
Exploring the transferability between heterogeneous tasks sheds light on their intrinsic interconnections, and consequently enables knowledge transfer from one task to another so as to reduce the training effort of the latter. In this…
Modern deep learning methods have achieved great success in machine learning and computer vision fields by learning a set of pre-defined datasets. Howerver, these methods perform unsatisfactorily when applied into real-world situations. The…
While neural networks are powerful function approximators, they suffer from catastrophic forgetting when the data distribution is not stationary. One particular formalism that studies learning under non-stationary distribution is provided…
Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics. Existing approaches either compute dense keypoint…
Zero-Shot Learning (ZSL) is an extreme form of transfer learning, where no labelled examples of the data to be classified are provided during the training stage. Instead, ZSL uses additional information learned about the domain, and relies…
In autonomous and mobile robotics, one of the main challenges is the robust on-the-fly perception of the environment, which is often unknown and dynamic, like in autonomous drone racing. In this work, we propose a novel deep neural…