Fast and Slow Learning of Recurrent Independent Mechanisms

• URL: http://arxiv.org/abs/2105.08710v2
• Date: Wed, 19 May 2021 03:10:30 GMT
• Title: Fast and Slow Learning of Recurrent Independent Mechanisms
• Authors: Kanika Madan, Nan Rosemary Ke, Anirudh Goyal, Bernhard Sch\"olkopf, Yoshua Bengio
• Abstract summary: We propose a training framework in which the pieces of knowledge an agent needs and its reward function are stationary and can be re-used across tasks. An attention mechanism dynamically selects which modules can be adapted to the current task. We find that meta-learning the modular aspects of the proposed system greatly helps in achieving faster adaptation in a reinforcement learning setup.
• Score: 80.38910637873066
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel combinations of existing pieces of knowledge. We hypothesize that such a decomposition of knowledge is particularly relevant for being able to generalize in a systematic manner to out-of-distribution changes. To study these ideas, we propose a particular training framework in which we assume that the pieces of knowledge an agent needs and its reward function are stationary and can be re-used across tasks. An attention mechanism dynamically selects which modules can be adapted to the current task, and the parameters of the selected modules are allowed to change quickly as the learner is confronted with variations in what it experiences, while the parameters of the attention mechanisms act as stable, slowly changing, meta-parameters. We focus on pieces of knowledge captured by an ensemble of modules sparsely communicating with each other via a bottleneck of attention. We find that meta-learning the modular aspects of the proposed system greatly helps in achieving faster adaptation in a reinforcement learning setup involving navigation in a partially observed grid world with image-level input. We also find that reversing the role of parameters and meta-parameters does not work nearly as well, suggesting a particular role for fast adaptation of the dynamically selected modules.

Related papers

• MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities [72.68829963458408]
  We present MergeNet, which learns to bridge the gap of parameter spaces of heterogeneous models. The core mechanism of MergeNet lies in the parameter adapter, which operates by querying the source model's low-rank parameters. MergeNet is learned alongside both models, allowing our framework to dynamically transfer and adapt knowledge relevant to the current stage.
  arXiv  Detail & Related papers  (2024-04-20T08:34:39Z)
• Interactive Continual Learning: Fast and Slow Thinking [19.253164551254734]
  This paper presents a novel Interactive Continual Learning framework, enabled by collaborative interactions among models of various sizes. To improve memory retrieval in System1, we introduce the CL-vMF mechanism, based on the von Mises-Fisher (vMF) distribution. Comprehensive evaluation of our proposed ICL demonstrates significant resistance to forgetting and superior performance relative to existing methods.
  arXiv  Detail & Related papers  (2024-03-05T03:37:28Z)
• What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition [20.742004197901576]
  We propose a novel framework for zero-shot module composition, which encompasses existing and some novel variations for selecting, weighting, and combining parameter modules. We conduct the first comprehensive benchmarking study of various zero-shot knowledge composition strategies. Our results highlight the efficacy of ensembling but also hint at the power of simple though often-ignored weighting methods.
  arXiv  Detail & Related papers  (2024-01-23T13:35:47Z)
• 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)
• Modular Deep Learning [120.36599591042908]
  Transfer learning has recently become the dominant paradigm of machine learning. It remains unclear how to develop models that specialise towards multiple tasks without incurring negative interference. Modular deep learning has emerged as a promising solution to these challenges.
  arXiv  Detail & Related papers  (2023-02-22T18:11:25Z)
• Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks [62.63852372239708]
  Meta learning aims to learn the learning methodology for machine learning from observed tasks, so as to generalize to new query tasks. We interpret such learning methodology as learning an explicit hyper- parameter prediction function shared by all training tasks. Such setting guarantees that the meta-learned learning methodology is able to flexibly fit diverse query tasks.
  arXiv  Detail & Related papers  (2021-07-06T04:05:08Z)
• Behavior Priors for Efficient Reinforcement Learning [97.81587970962232]
  We consider how information and architectural constraints can be combined with ideas from the probabilistic modeling literature to learn behavior priors. We discuss how such latent variable formulations connect to related work on hierarchical reinforcement learning (HRL) and mutual information and curiosity based objectives. We demonstrate the effectiveness of our framework by applying it to a range of simulated continuous control domains.
  arXiv  Detail & Related papers  (2020-10-27T13:17:18Z)
• A Combinatorial Perspective on Transfer Learning [27.7848044115664]
  We study how the learning of modular solutions can allow for effective generalization to both unseen and potentially differently distributed data. Our main postulate is that the combination of task segmentation, modular learning and memory-based ensembling can give rise to generalization on an exponentially growing number of unseen tasks.
  arXiv  Detail & Related papers  (2020-10-23T09:53:31Z)

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.