Set-based Meta-Interpolation for Few-Task Meta-Learning
- URL: http://arxiv.org/abs/2205.09990v3
- Date: Sat, 3 Jun 2023 16:48:41 GMT
- Title: Set-based Meta-Interpolation for Few-Task Meta-Learning
- Authors: Seanie Lee, Bruno Andreis, Kenji Kawaguchi, Juho Lee, Sung Ju Hwang
- Abstract summary: We propose a novel domain-agnostic task augmentation method, Meta-Interpolation, to densify the meta-training task distribution.
We empirically validate the efficacy of Meta-Interpolation on eight datasets spanning across various domains.
- Score: 79.85241791994562
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Meta-learning approaches enable machine learning systems to adapt to new
tasks given few examples by leveraging knowledge from related tasks. However, a
large number of meta-training tasks are still required for generalization to
unseen tasks during meta-testing, which introduces a critical bottleneck for
real-world problems that come with only few tasks, due to various reasons
including the difficulty and cost of constructing tasks. Recently, several task
augmentation methods have been proposed to tackle this issue using
domain-specific knowledge to design augmentation techniques to densify the
meta-training task distribution. However, such reliance on domain-specific
knowledge renders these methods inapplicable to other domains. While Manifold
Mixup based task augmentation methods are domain-agnostic, we empirically find
them ineffective on non-image domains. To tackle these limitations, we propose
a novel domain-agnostic task augmentation method, Meta-Interpolation, which
utilizes expressive neural set functions to densify the meta-training task
distribution using bilevel optimization. We empirically validate the efficacy
of Meta-Interpolation on eight datasets spanning across various domains such as
image classification, molecule property prediction, text classification and
speech recognition. Experimentally, we show that Meta-Interpolation
consistently outperforms all the relevant baselines. Theoretically, we prove
that task interpolation with the set function regularizes the meta-learner to
improve generalization.
Related papers
- MetaModulation: Learning Variational Feature Hierarchies for Few-Shot
Learning with Fewer Tasks [63.016244188951696]
We propose a method for few-shot learning with fewer tasks, which is by metaulation.
We modify parameters at various batch levels to increase the meta-training tasks.
We also introduce learning variational feature hierarchies by incorporating the variationalulation.
arXiv Detail & Related papers (2023-05-17T15:47:47Z) - Learning Action Translator for Meta Reinforcement Learning on
Sparse-Reward Tasks [56.63855534940827]
This work introduces a novel objective function to learn an action translator among training tasks.
We theoretically verify that the value of the transferred policy with the action translator can be close to the value of the source policy.
We propose to combine the action translator with context-based meta-RL algorithms for better data collection and more efficient exploration during meta-training.
arXiv Detail & Related papers (2022-07-19T04:58:06Z) - Fast Inference and Transfer of Compositional Task Structures for
Few-shot Task Generalization [101.72755769194677]
We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph.
Our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks.
Our experiment results on 2D grid-world and complex web navigation domains show that the proposed method can learn and leverage the common underlying structure of the tasks for faster adaptation to the unseen tasks.
arXiv Detail & Related papers (2022-05-25T10:44:25Z) - Meta Learning on a Sequence of Imbalanced Domains with Difficulty
Awareness [6.648670454325191]
A typical setting across current meta learning algorithms assumes a stationary task distribution during meta training.
We consider realistic scenarios where task distribution is highly imbalanced with domain labels unavailable in nature.
We propose a kernel-based method for domain change detection and a difficulty-aware memory management mechanism.
arXiv Detail & Related papers (2021-09-29T00:53:09Z) - Improving the Generalization of Meta-learning on Unseen Domains via
Adversarial Shift [3.1219977244201056]
We propose a model-agnostic shift layer to learn how to simulate the domain shift and generate pseudo tasks.
Based on the pseudo tasks, the meta-learning model can learn cross-domain meta-knowledge, which can generalize well on unseen domains.
arXiv Detail & Related papers (2021-07-23T07:29:30Z) - Meta-Learning with Fewer Tasks through Task Interpolation [67.03769747726666]
Current meta-learning algorithms require a large number of meta-training tasks, which may not be accessible in real-world scenarios.
By meta-learning with task gradient (MLTI), our approach effectively generates additional tasks by randomly sampling a pair of tasks and interpolating the corresponding features and labels.
Empirically, in our experiments on eight datasets from diverse domains, we find that the proposed general MLTI framework is compatible with representative meta-learning algorithms and consistently outperforms other state-of-the-art strategies.
arXiv Detail & Related papers (2021-06-04T20:15:34Z) - MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and
Architectures [61.73533544385352]
We propose a transferable perturbation, MetaPerturb, which is meta-learned to improve generalization performance on unseen data.
As MetaPerturb is a set-function trained over diverse distributions across layers and tasks, it can generalize heterogeneous tasks and architectures.
arXiv Detail & Related papers (2020-06-13T02:54:59Z) - Attentive Feature Reuse for Multi Task Meta learning [17.8055398673228]
We develop new algorithms for simultaneous learning of multiple tasks.
We propose an attention mechanism to dynamically specialize the network, at runtime, for each task.
Our method improves performance on new, previously unseen environments.
arXiv Detail & Related papers (2020-06-12T19:33:11Z) - Information-Theoretic Generalization Bounds for Meta-Learning and
Applications [42.275148861039895]
Key performance measure for meta-learning is the meta-generalization gap.
This paper presents novel information-theoretic upper bounds on the meta-generalization gap.
arXiv Detail & Related papers (2020-05-09T05:48:01Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.