Minimal Sufficient Representations for Self-interpretable Deep Neural Networks

• URL: http://arxiv.org/abs/2603.24041v1
• Date: Wed, 25 Mar 2026 07:51:21 GMT
• Title: Minimal Sufficient Representations for Self-interpretable Deep Neural Networks
• Abstract summary: DeepIn is a self-interpretable neural network framework that adaptively identifies and learns the minimal representation necessary for preserving the full expressive capacity of standard DNNs.<n>We show that DeepIn can correctly identify the minimal representation dimension, select relevant variables, and recover the minimal sufficient network architecture for prediction.<n>Across biomedical and vision benchmarks, DeepIn improves both predictive accuracy and interpretability, reducing error by up to 30% on real-world datasets.
• Score: 2.333384279860279
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks (DNNs) achieve remarkable predictive performance but remain difficult to interpret, largely due to overparameterization that obscures the minimal structure required for interpretation. Here we introduce DeepIn, a self-interpretable neural network framework that adaptively identifies and learns the minimal representation necessary for preserving the full expressive capacity of standard DNNs. We show that DeepIn can correctly identify the minimal representation dimension, select relevant variables, and recover the minimal sufficient network architecture for prediction. The resulting estimator achieves optimal non-asymptotic error rates that adapt to the learned minimal dimension, demonstrating that recovering minimal sufficient structure fundamentally improves generalization error. Building on these guarantees, we further develop hypothesis testing procedures for both selected variables and learned representations, bridging deep representation learning with formal statistical inference. Across biomedical and vision benchmarks, DeepIn improves both predictive accuracy and interpretability, reducing error by up to 30% on real-world datasets while automatically uncovering human-interpretable discriminative patterns. Our results suggest that interpretability and statistical rigor can be embedded directly into deep architectures without sacrificing performance.

Related papers

• SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces [91.71563221166417]
  Implicit neural representations are powerful for geometric modeling, but their practical use is often limited by the high computational cost.<n>We propose an efficient neural implicit geometry representation framework with spatially adaptive network depth.
  arXiv  Detail & Related papers  (2026-04-15T14:14:17Z)
• Just How Flexible are Neural Networks in Practice? [89.80474583606242]
  It is widely believed that a neural network can fit a training set containing at least as many samples as it has parameters. In practice, however, we only find solutions via our training procedure, including the gradient and regularizers, limiting flexibility.
  arXiv  Detail & Related papers  (2024-06-17T12:24:45Z)
• IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learning [11.5992081385106]
  We propose a novel framework for uncertainty quantification via information bottleneck (IB-UQ) for scientific machine learning tasks. We incorporate the bottleneck by a confidence-aware encoder, which encodes inputs into latent representations according to the confidence of the input data. We also propose a data augmentation based information bottleneck objective which can enhance the quality of the extrapolation uncertainty.
  arXiv  Detail & Related papers  (2023-02-07T05:56:42Z)
• Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets [57.06026574261203]
  We provide theoretical evidence for learning low-dimensional state spaces, which can also model long-term memory. Experiments corroborate our theory, demonstrating extrapolation via learning low-dimensional state spaces with both linear and non-linear RNNs.
  arXiv  Detail & Related papers  (2022-10-25T14:45:15Z)
• A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness [33.09831377640498]
  We study approaches to improve uncertainty property of a single network, based on a single, deterministic representation. We propose Spectral-normalized Neural Gaussian Process (SNGP), a simple method that improves the distance-awareness ability of modern DNNs. On a suite of vision and language understanding benchmarks, SNGP outperforms other single-model approaches in prediction, calibration and out-of-domain detection.
  arXiv  Detail & Related papers  (2022-05-01T05:46:13Z)
• Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks [4.153804257347222]
  We present Agglomerator, a framework capable of providing a representation of part-whole hierarchies from visual cues. We evaluate our method on common datasets, such as SmallNORB, MNIST, FashionMNIST, CIFAR-10, and CIFAR-100.
  arXiv  Detail & Related papers  (2022-03-07T10:56:13Z)
• Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces [41.55700086945413]
  This paper studies the nonparametric estimation of Lipschitz operators using deep neural networks. Under the assumption that the target operator exhibits a low dimensional structure, our error bounds decay as the training sample size increases. Our results give rise to fast rates by exploiting low dimensional structures of data in operator estimation.
  arXiv  Detail & Related papers  (2022-01-01T16:33:44Z)
• Mitigating Performance Saturation in Neural Marked Point Processes: Architectures and Loss Functions [50.674773358075015]
  We propose a simple graph-based network structure called GCHP, which utilizes only graph convolutional layers. We show that GCHP can significantly reduce training time and the likelihood ratio loss with interarrival time probability assumptions can greatly improve the model performance.
  arXiv  Detail & Related papers  (2021-07-07T16:59:14Z)
• Locally Sparse Networks for Interpretable Predictions [7.362415721170984]
  We propose a framework for training locally sparse neural networks where the local sparsity is learned via a sample-specific gating mechanism. The sample-specific sparsity is predicted via a textitgating network, which is trained in tandem with the textitprediction network. We demonstrate that our method outperforms state-of-the-art models when predicting the target function with far fewer features per instance.
  arXiv  Detail & Related papers  (2021-06-11T15:46:50Z)
• Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks [54.27962244835622]
  This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs) In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit. We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
  arXiv  Detail & Related papers  (2020-07-03T01:37:16Z)
• Deep Dimension Reduction for Supervised Representation Learning [51.10448064423656]
  We propose a deep dimension reduction approach to learning representations with essential characteristics. The proposed approach is a nonparametric generalization of the sufficient dimension reduction method. We show that the estimated deep nonparametric representation is consistent in the sense that its excess risk converges to zero.
  arXiv  Detail & Related papers  (2020-06-10T14:47:43Z)

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.