Rethinking Teacher-Student Curriculum Learning through the Cooperative Mechanics of Experience

• URL: http://arxiv.org/abs/2404.03084v2
• Date: Thu, 12 Sep 2024 16:56:59 GMT
• Title: Rethinking Teacher-Student Curriculum Learning through the Cooperative Mechanics of Experience
• Abstract summary: Teacher-Student Curriculum Learning (TSCL) is a curriculum learning framework that draws inspiration from human cultural transmission and learning. We propose a data-centric perspective to analyze the underlying mechanics of the teacher-student interactions in TSCL.
• Score: 15.00590722099547
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Teacher-Student Curriculum Learning (TSCL) is a curriculum learning framework that draws inspiration from human cultural transmission and learning. It involves a teacher algorithm shaping the learning process of a learner algorithm by exposing it to controlled experiences. Despite its success, understanding the conditions under which TSCL is effective remains challenging. In this paper, we propose a data-centric perspective to analyze the underlying mechanics of the teacher-student interactions in TSCL. We leverage cooperative game theory to describe how the composition of the set of experiences presented by the teacher to the learner, as well as their order, influences the performance of the curriculum that is found by TSCL approaches. To do so, we demonstrate that for every TSCL problem, an equivalent cooperative game exists, and several key components of the TSCL framework can be reinterpreted using game-theoretic principles. Through experiments covering supervised learning, reinforcement learning, and classical games, we estimate the cooperative values of experiences and use value-proportional curriculum mechanisms to construct curricula, even in cases where TSCL struggles. The framework and experimental setup we present in this work represents a novel foundation for a deeper exploration of TSCL, shedding light on its underlying mechanisms and providing insights into its broader applicability in machine learning.

Related papers

• A Lightweight Scrum Sprint Simulation to Help Learners Traverse the Empirical Process Control Threshold Concept [0.0]
  Empirical process control, a way of managing work based on the observation of the successes or misfortunes of earlier activities, is a key process in Scrum.<n>We present a lightweight, scalable, free and customizable sprint simulation activity designed to teach students how to empirically control a Scrum project.
  arXiv  Detail & Related papers  (2026-05-02T20:23:19Z)
• Impact of UK Postgraduate Student Experiences on Academic Performance in Blended Learning: A Data Analytics Approach [0.0527359582877518]
  Blended learning has become a dominant educational model in higher education in the UK and worldwide.<n>This paper investigates the interaction between different dimensions of student learning experiences and academic achievement.
  arXiv  Detail & Related papers  (2025-11-15T18:42:43Z)
• Reconciling Different Theories of Learning with an Agent-based Model of Procedural Learning [0.27624021966289597]
  We propose a new computational model of human learning, Procedural ABICAP, that reconciles the ICAP, Knowledge-Learning-Instruction, and cognitive load theory frameworks for learning procedural knowledge. ICAP assumes that constructive learning generally yields better learning outcomes, while theories such as KLI and CLT claim that this is not always true.
  arXiv  Detail & Related papers  (2024-08-23T20:45:14Z)
• Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning [99.05401042153214]
  In-context learning (ICL) is potentially attributed to two major abilities: task recognition (TR) and task learning (TL) We take the first step by examining the pre-training dynamics of the emergence of ICL. We propose a simple yet effective method to better integrate these two abilities for ICL at inference time.
  arXiv  Detail & Related papers  (2024-06-20T06:37:47Z)
• Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning [9.660673938961416]
  Demonstration ordering is an important strategy for in-context learning (ICL) We propose a simple but effective demonstration ordering method for ICL, named the few-shot In-Context Curriculum Learning (ICCL)
  arXiv  Detail & Related papers  (2024-02-16T14:55:33Z)
• CLGT: A Graph Transformer for Student Performance Prediction in Collaborative Learning [6.140954034246379]
  We present an extended graph transformer framework for collaborative learning (CLGT) for evaluating and predicting the performance of students. The experimental results confirm that the proposed CLGT outperforms the baseline models in terms of performing predictions based on the real-world datasets.
  arXiv  Detail & Related papers  (2023-07-30T09:54:30Z)
• NCL++: Nested Collaborative Learning for Long-Tailed Visual Recognition [63.90327120065928]
  We propose a Nested Collaborative Learning (NCL++) which tackles the long-tailed learning problem by a collaborative learning. To achieve the collaborative learning in long-tailed learning, the balanced online distillation is proposed. In order to improve the meticulous distinguishing ability on the confusing categories, we further propose a Hard Category Mining.
  arXiv  Detail & Related papers  (2023-06-29T06:10:40Z)
• On the Statistical Benefits of Curriculum Learning [33.94130046391917]
  We study the benefits of Curriculum learning (CL) in the multitask linear regression problem under both structured and unstructured settings. Our results reveal that adaptive learning can be fundamentally harder than the oracle learning in the unstructured setting.
  arXiv  Detail & Related papers  (2021-11-13T14:51:07Z)
• 3D Human Action Representation Learning via Cross-View Consistency Pursuit [52.19199260960558]
  We propose a Cross-view Contrastive Learning framework for unsupervised 3D skeleton-based action Representation (CrosSCLR) CrosSCLR consists of both single-view contrastive learning (SkeletonCLR) and cross-view consistent knowledge mining (CVC-KM) modules, integrated in a collaborative learning manner.
  arXiv  Detail & Related papers  (2021-04-29T16:29:41Z)
• Mutual Contrastive Learning for Visual Representation Learning [1.9355744690301404]
  We present a collaborative learning method called Mutual Contrastive Learning (MCL) for general visual representation learning. Benefiting from MCL, each model can learn extra contrastive knowledge from others, leading to more meaningful feature representations. Experimental results on supervised and self-supervised image classification, transfer learning and few-shot learning show that MCL can lead to consistent performance gains.
  arXiv  Detail & Related papers  (2021-04-26T13:32:33Z)
• A Survey on Curriculum Learning [48.36129047271622]
  Curriculum learning (CL) is a training strategy that trains a machine learning model from easier data to harder data. As an easy-to-use plug-in, the CL strategy has demonstrated its power in improving the generalization capacity and convergence rate of various models.
  arXiv  Detail & Related papers  (2020-10-25T17:15:04Z)
• Interaction-limited Inverse Reinforcement Learning [50.201765937436654]
  We present two different training strategies: Curriculum Inverse Reinforcement Learning (CIRL) covering the teacher's perspective, and Self-Paced Inverse Reinforcement Learning (SPIRL) focusing on the learner's perspective. Using experiments in simulations and experiments with a real robot learning a task from a human demonstrator, we show that our training strategies can allow a faster training than a random teacher for CIRL and than a batch learner for SPIRL.
  arXiv  Detail & Related papers  (2020-07-01T12:31:52Z)
• Dual Policy Distillation [58.43610940026261]
  Policy distillation, which transfers a teacher policy to a student policy, has achieved great success in challenging tasks of deep reinforcement learning. In this work, we introduce dual policy distillation(DPD), a student-student framework in which two learners operate on the same environment to explore different perspectives of the environment. The key challenge in developing this dual learning framework is to identify the beneficial knowledge from the peer learner for contemporary learning-based reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2020-06-07T06:49:47Z)

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.