Maximum Manifold Capacity Representations in State Representation Learning
The expanding research on manifold-based self-supervised learning (SSL) builds on the manifold hypothesis, which suggests that the inherent complexity of high-dimensional data can be unraveled through lower-dimensional manifold embeddings. Capitalizing on this, DeepInfomax with an unbalanced atlas (DIM-UA) has emerged as a powerful tool and yielded impressive results for state representations in reinforcement learning. Meanwhile, Maximum Manifold Capacity Representation (MMCR) presents a new frontier for SSL by optimizing class separability via manifold compression. However, MMCR demands extensive input views, resulting in significant computational costs and protracted pre-training durations. Bridging this gap, we present an innovative integration of MMCR into existing SSL methods, incorporating a discerning regularization strategy that enhances the lower bound of mutual information. We also propose a novel state representation learning method extending DIM-UA, embedding a nuclear norm loss to enforce manifold consistency robustly. On experimentation with the Atari Annotated RAM Interface, our method improves DIM-UA significantly with the same number of target encoding dimensions. The mean F1 score averaged over categories is 78% compared to 75% of DIM-UA. There are also compelling gains when implementing SimCLR and Barlow Twins. This supports our SSL innovation as a paradigm shift, enabling more nuanced high-dimensional data representations.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningSelf-Supervised LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations
The efficient coding hypothesis proposes that the response properties of sensory systems are adapted to the statistics of their inputs such that they capture maximal information about the environment, subject to biologic…
Contrastive LearningObject RecognitionSelf-Supervised LearningGeneralized Category Discovery via Token Manifold Capacity Learning
Generalized category discovery (GCD) is essential for improving deep learning models' robustness in open-world scenarios by clustering unlabeled data containing both known and novel categories. Traditional GCD methods fo…
ClusteringTowards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations
Maximum Manifold Capacity Representations (MMCR) is a recent multi-view self-supervised learning (MVSSL) method that matches or surpasses other leading MVSSL methods. MMCR is intriguing because it does not fit neatly int…
Self-Supervised LearningMAPLE: Self-Supervised Learning-Enhanced Nonlinear Dimensionality Reduction for Visual Analysis
We present a new nonlinear dimensionality reduction method, MAPLE, that enhances UMAP by improving manifold modeling. MAPLE employs a self-supervised learning approach to more efficiently encode low-dimensional manifold …
Self-Supervised LearningDimensionality ReductionClassification and Geometry of General Perceptual Manifolds
Perceptual manifolds arise when a neural population responds to an ensemble of sensory signals associated with different physical features (e.g., orientation, pose, scale, location, and intensity) of the same perceptual …
ClassificationGeneral ClassificationObjectObject Recognition