Improved Compositional Generalization by Generating Demonstrations for Meta-Learning

• URL: http://arxiv.org/abs/2305.13092v2
• Date: Sat, 12 Oct 2024 14:10:16 GMT
• Title: Improved Compositional Generalization by Generating Demonstrations for Meta-Learning
• Authors: Sam Spilsbury, Pekka Marttinen, Alexander Ilin,
• Abstract summary: We show substantially improved performance on a previously unsolved compositional behaviour split without a loss of performance on other splits. In this case, searching for relevant demonstrations even with an oracle function is not sufficient to attain good performance when using meta-learning.
• Score: 53.818234285773165
• License:
• Abstract: Meta-learning and few-shot prompting are viable methods to induce certain types of compositional behaviour. However, these methods can be very sensitive to the choice of support examples used. Choosing good supports from the training data for a given test query is already a difficult problem, but in some cases solving this may not even be enough. We consider a grounded language learning problem (gSCAN) where good support examples for certain test splits might not even exist in the training data, or would be infeasible to search for. We design an agent which instead generates possible supports which are relevant to the test query and current state of the world, then uses these supports via meta-learning to solve the test query. We show substantially improved performance on a previously unsolved compositional behaviour split without a loss of performance on other splits. Further experiments show that in this case, searching for relevant demonstrations even with an oracle function is not sufficient to attain good performance when using meta-learning.

Related papers

• Adapting Vision-Language Models to Open Classes via Test-Time Prompt Tuning [50.26965628047682]
  Adapting pre-trained models to open classes is a challenging problem in machine learning. In this paper, we consider combining the advantages of both and come up with a test-time prompt tuning approach. Our proposed method outperforms all comparison methods on average considering both base and new classes.
  arXiv  Detail & Related papers  (2024-08-29T12:34:01Z)
• In-context Learning with Retrieved Demonstrations for Language Models: A Survey [23.24271704145876]
  Few-shot in-context learners (ICL) are adept at adapting to new tasks with just a few demonstrations in the input context. Instead of using a fixed set of demonstrations, one recent development is to retrieve demonstrations tailored to each input query. We discuss and compare different design choices for retrieval models, retrieval training procedures, and inference algorithms.
  arXiv  Detail & Related papers  (2024-01-21T23:34:42Z)
• RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning [53.52699766206808]
  We propose Retrieval for In-Context Learning (RetICL), a learnable method for modeling and optimally selecting examples sequentially for in-context learning. We evaluate RetICL on math word problem solving and scientific question answering tasks and show that it consistently outperforms or matches and learnable baselines.
  arXiv  Detail & Related papers  (2023-05-23T20:15:56Z)
• APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation [56.387647750094466]
  Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images. Most advanced solutions exploit a metric learning framework that performs segmentation through matching each query feature to a learned class-specific prototype. We present an adaptive prototype representation by introducing class-specific and class-agnostic prototypes.
  arXiv  Detail & Related papers  (2021-11-24T04:38:37Z)
• A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning [14.720411598827365]
  splitting data from each task into train and validation sets during meta-training. We argue that the train-validation split encourages the learned representation to be low-rank without compromising on expressivity. Since sample efficiency benefits from low-rankness, the splitting strategy will require very few samples to solve unseen test tasks.
  arXiv  Detail & Related papers  (2021-06-29T17:59:33Z)
• Does My Representation Capture X? Probe-Ably [2.624902795082451]
  Probing (or diagnostic classification) has become a popular strategy for investigating whether a given set of intermediate features is present in representations of neural models. We introduce Probe-Ably: an extendable probing framework which supports and automates the application of probing methods to the user's inputs.
  arXiv  Detail & Related papers  (2021-04-12T20:43:10Z)
• Conditional Meta-Learning of Linear Representations [57.90025697492041]
  Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. In this work we overcome this issue by inferring a conditioning function, mapping the tasks' side information into a representation tailored to the task at hand. We propose a meta-algorithm capable of leveraging this advantage in practice.
  arXiv  Detail & Related papers  (2021-03-30T12:02:14Z)
• Is Support Set Diversity Necessary for Meta-Learning? [14.231486872262531]
  We propose a modification to traditional meta-learning approaches in which we keep the support sets fixed across tasks, thus reducing task diversity. Surprisingly, we find that not only does this modification not result in adverse effects, it almost always improves the performance for a variety of datasets and meta-learning methods.
  arXiv  Detail & Related papers  (2020-11-28T02:28:42Z)
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation [64.91560451900125]
  State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results. Few-shot segmentation is proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples. Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information.
  arXiv  Detail & Related papers  (2020-08-04T10:41:32Z)

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.