Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination

• URL: http://arxiv.org/abs/2311.02960v2
• Date: Tue, 9 Jan 2024 16:16:34 GMT
• Title: Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
• Authors: Peng Wang, Xiao Li, Can Yaras, Zhihui Zhu, Laura Balzano, Wei Hu, and Qing Qu
• Abstract summary: We show that each layer of a deep linear network progressively compresses within-class features at a geometric rate and discriminates between-class features at a linear rate. This is the first quantitative characterization of feature evolution in hierarchical representations of deep linear networks.
• Score: 33.273226655730326
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks perform hierarchical feature learning across layers. In this work, we attempt to unveil this mystery by investigating the structures of intermediate features. Motivated by our empirical findings that linear layers mimic the roles of deep layers in nonlinear networks for feature learning, we explore how deep linear networks transform input data into output by investigating the output (i.e., features) of each layer after training in the context of multi-class classification problems. Toward this goal, we first define metrics to measure within-class compression and between-class discrimination of intermediate features, respectively. Through theoretical analysis of these two metrics, we show that the evolution of features follows a simple and quantitative pattern from shallow to deep layers when the input data is nearly orthogonal and the network weights are minimum-norm, balanced, and approximate low-rank: Each layer of the linear network progressively compresses within-class features at a geometric rate and discriminates between-class features at a linear rate with respect to the number of layers that data have passed through. To the best of our knowledge, this is the first quantitative characterization of feature evolution in hierarchical representations of deep linear networks. Empirically, our extensive experiments not only validate our theoretical results numerically but also reveal a similar pattern in deep nonlinear networks which aligns well with recent empirical studies. Moreover, we demonstrate the practical implications of our results in transfer learning. Our code is available at \url{https://github.com/Heimine/PNC_DLN}.

Related papers

• Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data [4.14360329494344]
  We characterize simplicity bias for general datasets in the context of two-layer neural networks with small weights and trained with gradient flow. For datasets with an XOR-like pattern, we precisely identify the learned features and demonstrate that simplicity bias intensifies during later training stages. These results indicate that features learned in the middle stages of training may be more useful for OOD transfer.
  arXiv  Detail & Related papers  (2024-05-27T16:00:45Z)
• Neural Collapse in the Intermediate Hidden Layers of Classification Neural Networks [0.0]
  (NC) gives a precise description of the representations of classes in the final hidden layer of classification neural networks. In the present paper, we provide the first comprehensive empirical analysis of the emergence of (NC) in the intermediate hidden layers.
  arXiv  Detail & Related papers  (2023-08-05T01:19:38Z)
• Understanding Deep Neural Networks via Linear Separability of Hidden Layers [68.23950220548417]
  We first propose Minkowski difference based linear separability measures (MD-LSMs) to evaluate the linear separability degree of two points sets. We demonstrate that there is a synchronicity between the linear separability degree of hidden layer outputs and the network training performance.
  arXiv  Detail & Related papers  (2023-07-26T05:29:29Z)
• Hidden Classification Layers: Enhancing linear separability between classes in neural networks layers [0.0]
  We investigate the impact on deep network performances of a training approach. We propose a neural network architecture which induces an error function involving the outputs of all the network layers.
  arXiv  Detail & Related papers  (2023-06-09T10:52:49Z)
• Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks [49.808194368781095]
  We show that three-layer neural networks have provably richer feature learning capabilities than two-layer networks. This work makes progress towards understanding the provable benefit of three-layer neural networks over two-layer networks in the feature learning regime.
  arXiv  Detail & Related papers  (2023-05-11T17:19:30Z)
• A Law of Data Separation in Deep Learning [41.58856318262069]
  We study the fundamental question of how deep neural networks process data in the intermediate layers. Our finding is a simple and quantitative law that governs how deep neural networks separate data according to class membership.
  arXiv  Detail & Related papers  (2022-10-31T02:25:38Z)
• Rank Diminishing in Deep Neural Networks [71.03777954670323]
  Rank of neural networks measures information flowing across layers. It is an instance of a key structural condition that applies across broad domains of machine learning. For neural networks, however, the intrinsic mechanism that yields low-rank structures remains vague and unclear.
  arXiv  Detail & Related papers  (2022-06-13T12:03:32Z)
• A neural anisotropic view of underspecification in deep learning [60.119023683371736]
  We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
  arXiv  Detail & Related papers  (2021-04-29T14:31:09Z)
• Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior [80.5637175255349]
  We propose a new enriched prior based Dual-constrained Deep Semi-Supervised Coupled Factorization Network, called DS2CF-Net. To ex-tract hidden deep features, DS2CF-Net is modeled as a deep-structure and geometrical structure-constrained neural network. Our network can obtain state-of-the-art performance for representation learning and clustering.
  arXiv  Detail & Related papers  (2020-09-08T13:10:21Z)
• ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification [49.87503122462432]
  We introduce a novel neural network termed Relation-and-Margin learning Network (ReMarNet) Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms. Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples.
  arXiv  Detail & Related papers  (2020-06-27T13:50:20Z)

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.