A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features

• URL: http://arxiv.org/abs/2206.01717v1
• Date: Fri, 3 Jun 2022 17:49:38 GMT
• Title: A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features
• Authors: Zhenmei Shi, Junyi Wei, Yingyu Liang
• Abstract summary: An important characteristic of neural networks is their ability to learn representations of the input data with effective features for prediction. We consider learning problems motivated by practical data, where the labels are determined by a set of class relevant patterns and the inputs are generated from these. We prove that neural networks trained by gradient descent can succeed on these problems.
• Score: 18.321479102352875
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: An important characteristic of neural networks is their ability to learn representations of the input data with effective features for prediction, which is believed to be a key factor to their superior empirical performance. To better understand the source and benefit of feature learning in neural networks, we consider learning problems motivated by practical data, where the labels are determined by a set of class relevant patterns and the inputs are generated from these along with some background patterns. We prove that neural networks trained by gradient descent can succeed on these problems. The success relies on the emergence and improvement of effective features, which are learned among exponentially many candidates efficiently by exploiting the data (in particular, the structure of the input distribution). In contrast, no linear models on data-independent features of polynomial sizes can learn to as good errors. Furthermore, if the specific input structure is removed, then no polynomial algorithm in the Statistical Query model can learn even weakly. These results provide theoretical evidence showing that feature learning in neural networks depends strongly on the input structure and leads to the superior performance. Our preliminary experimental results on synthetic and real data also provide positive support.

Related papers

• Coding schemes in neural networks learning classification tasks [52.22978725954347]
  We investigate fully-connected, wide neural networks learning classification tasks. We show that the networks acquire strong, data-dependent features. Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
  arXiv  Detail & Related papers  (2024-06-24T14:50:05Z)
• Deep networks for system identification: a Survey [56.34005280792013]
  System identification learns mathematical descriptions of dynamic systems from input-output data. Main aim of the identified model is to predict new data from previous observations. We discuss architectures commonly adopted in the literature, like feedforward, convolutional, and recurrent networks.
  arXiv  Detail & Related papers  (2023-01-30T12:38:31Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach [80.8446673089281]
  We propose a new learning paradigm with graph representation and learning. Our framework contains two modules: 1) a backbone network (e.g., feedforward neural nets) as a lower model takes features as input and outputs predicted labels; 2) a graph neural network as an upper model learns to extrapolate embeddings for new features via message passing over a feature-data graph built from observed data.
  arXiv  Detail & Related papers  (2021-10-09T09:02:45Z)
• Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning [43.504548777955854]
  We study how contrastive learning learns the feature representations for neural networks by analyzing its feature learning process. We prove that contrastive learning using textbfReLU networks provably learns the desired sparse features if proper augmentations are adopted.
  arXiv  Detail & Related papers  (2021-05-31T16:42:09Z)
• 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)
• Efficacy of Bayesian Neural Networks in Active Learning [11.609770399591516]
  We show that Bayesian neural networks are more efficient than ensemble based techniques in capturing uncertainty. Our findings also reveal some key drawbacks of the ensemble techniques, which was recently shown to be more effective than Monte Carlo dropouts.
  arXiv  Detail & Related papers  (2021-04-02T06:02:11Z)
• How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks [80.55378250013496]
  We study how neural networks trained by gradient descent extrapolate what they learn outside the support of the training distribution. Graph Neural Networks (GNNs) have shown some success in more complex tasks.
  arXiv  Detail & Related papers  (2020-09-24T17:48:59Z)
• Malicious Network Traffic Detection via Deep Learning: An Information Theoretic View [0.0]
  We study how homeomorphism affects learned representation of a malware traffic dataset. Our results suggest that although the details of learned representations and the specific coordinate system defined over the manifold of all parameters differ slightly, the functional approximations are the same.
  arXiv  Detail & Related papers  (2020-09-16T15:37:44Z)

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.