Small-Group Learning, with Application to Neural Architecture Search

• URL: http://arxiv.org/abs/2012.12502v2
• Date: Thu, 11 Mar 2021 03:38:50 GMT
• Title: Small-Group Learning, with Application to Neural Architecture Search
• Authors: Xuefeng Du, Pengtao Xie
• Abstract summary: In human learning, a small group of students work together towards the same learning objective, where they express their understanding of a topic to their peers, compare their ideas, and help each other to trouble-shoot problems. In this paper, we aim to investigate whether this human learning method can be borrowed to train better machine learning models, by developing a novel ML framework -- small-group learning (SGL) SGL is formulated as a multi-level optimization framework consisting of three learning stages: each learner trains a model independently and uses this model to perform pseudo-labeling; each learner trains another model using datasets pseudo-
• Score: 17.86826990290058
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In human learning, an effective learning methodology is small-group learning: a small group of students work together towards the same learning objective, where they express their understanding of a topic to their peers, compare their ideas, and help each other to trouble-shoot problems. In this paper, we aim to investigate whether this human learning method can be borrowed to train better machine learning models, by developing a novel ML framework -- small-group learning (SGL). In our framework, a group of learners (ML models) with different model architectures collaboratively help each other to learn by leveraging their complementary advantages. Specifically, each learner uses its intermediately trained model to generate a pseudo-labeled dataset and re-trains its model using pseudo-labeled datasets generated by other learners. SGL is formulated as a multi-level optimization framework consisting of three learning stages: each learner trains a model independently and uses this model to perform pseudo-labeling; each learner trains another model using datasets pseudo-labeled by other learners; learners improve their architectures by minimizing validation losses. An efficient algorithm is developed to solve the multi-level optimization problem. We apply SGL for neural architecture search. Results on CIFAR-100, CIFAR-10, and ImageNet demonstrate the effectiveness of our method.

Related papers

• ConML: A Universal Meta-Learning Framework with Task-Level Contrastive Learning [49.447777286862994]
  ConML is a universal meta-learning framework that can be applied to various meta-learning algorithms. We demonstrate that ConML integrates seamlessly with optimization-based, metric-based, and amortization-based meta-learning algorithms.
  arXiv  Detail & Related papers  (2024-10-08T12:22:10Z)
• LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement [93.38736019287224]
  "LLMs-as-Instructors" framework autonomously enhances the training of smaller target models. Inspired by the theory of "Learning from Errors", this framework employs an instructor LLM to meticulously analyze the specific errors within a target model. Within this framework, we implement two strategies: "Learning from Error," which focuses solely on incorrect responses to tailor training data, and "Learning from Error by Contrast", which uses contrastive learning to analyze both correct and incorrect responses for a deeper understanding of errors.
  arXiv  Detail & Related papers  (2024-06-29T17:16:04Z)
• Language models are weak learners [71.33837923104808]
  We show that prompt-based large language models can operate effectively as weak learners. We incorporate these models into a boosting approach, which can leverage the knowledge within the model to outperform traditional tree-based boosting. Results illustrate the potential for prompt-based LLMs to function not just as few-shot learners themselves, but as components of larger machine learning pipelines.
  arXiv  Detail & Related papers  (2023-06-25T02:39:19Z)
• CodeGen2: Lessons for Training LLMs on Programming and Natural Languages [116.74407069443895]
  We unify encoder and decoder-based models into a single prefix-LM. For learning methods, we explore the claim of a "free lunch" hypothesis. For data distributions, the effect of a mixture distribution and multi-epoch training of programming and natural languages on model performance is explored.
  arXiv  Detail & Related papers  (2023-05-03T17:55:25Z)
• Implicit Offline Reinforcement Learning via Supervised Learning [83.8241505499762]
  Offline Reinforcement Learning (RL) via Supervised Learning is a simple and effective way to learn robotic skills from a dataset collected by policies of different expertise levels. We show how implicit models can leverage return information and match or outperform explicit algorithms to acquire robotic skills from fixed datasets.
  arXiv  Detail & Related papers  (2022-10-21T21:59:42Z)
• Learning from Mistakes based on Class Weighting with Application to Neural Architecture Search [12.317568257671427]
  We propose a simple and effective multi-level optimization framework called learning from mistakes (LFM) The primary objective is to train a model to perform effectively on target tasks by using a re-weighting technique to prevent similar mistakes in the future. In this formulation, we learn the class weights by minimizing the validation loss of the model and re-train the model with the synthetic data from the image generator weighted by class-wise performance and real data.
  arXiv  Detail & Related papers  (2021-12-01T04:56:49Z)
• Distill on the Go: Online knowledge distillation in self-supervised learning [1.1470070927586016]
  Recent works have shown that wider and deeper models benefit more from self-supervised learning than smaller models. We propose Distill-on-the-Go (DoGo), a self-supervised learning paradigm using single-stage online knowledge distillation. Our results show significant performance gain in the presence of noisy and limited labels.
  arXiv  Detail & Related papers  (2021-04-20T09:59:23Z)
• Interleaving Learning, with Application to Neural Architecture Search [12.317568257671427]
  We propose a novel machine learning framework referred to as interleaving learning (IL) In our framework, a set of models collaboratively learn a data encoder in an interleaving fashion. We apply interleaving learning to search neural architectures for image classification on CIFAR-10, CIFAR-100, and ImageNet.
  arXiv  Detail & Related papers  (2021-03-12T00:54:22Z)
• Learning to Rank Learning Curves [15.976034696758148]
  We present a new method that saves computational budget by terminating poor configurations early on in the training. We show that our model is able to effectively rank learning curves without having to observe many or very long learning curves.
  arXiv  Detail & Related papers  (2020-06-05T10:49:52Z)
• Auto-Ensemble: An Adaptive Learning Rate Scheduling based Deep Learning Model Ensembling [11.324407834445422]
  This paper proposes Auto-Ensemble (AE) to collect checkpoints of deep learning model and ensemble them automatically. The advantage of this method is to make the model converge to various local optima by scheduling the learning rate in once training.
  arXiv  Detail & Related papers  (2020-03-25T08:17:31Z)
• Three Approaches for Personalization with Applications to Federated Learning [68.19709953755238]
  We present a systematic learning-theoretic study of personalization. We provide learning-theoretic guarantees and efficient algorithms for which we also demonstrate the performance. All of our algorithms are model-agnostic and work for any hypothesis class.
  arXiv  Detail & Related papers  (2020-02-25T01:36:43Z)

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.