Information Plane Analysis of Binary Neural Networks

• URL: http://arxiv.org/abs/2605.03636v1
• Date: Tue, 05 May 2026 11:08:18 GMT
• Title: Information Plane Analysis of Binary Neural Networks
• Abstract summary: We perform IP analyses on binary neural networks (BNNs) where activations are discrete and MI is finite.<n>We train BNNs to investigate the existence of late-stage compression phases and the relationship between compressed representations and generalisation performance.
• Score: 6.259398755176288
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Information plane (IP) analysis has been suggested to study the training dynamics of deep neural networks through mutual information (MI) between inputs, representations, and targets. However, its statistical validity is often compromised by the difficulty of estimating MI from samples of high-dimensional, deterministic representations. In this work, we perform IP analyses on binary neural networks (BNNs) where activations are discrete and MI is finite. We characterise the finite-sample behaviour of the plug-in entropy estimator and identify regimes for sample size $N$ and representation dimensionality $D$ under which MI estimates are reliable. Outside these regimes, we show that empirical MI estimates saturate to $\log_2 N$, rendering IP trajectories uninformative. Restricting attention to the reliable regime, we train 375 BNNs to investigate the existence of late-stage compression phases and the relationship between compressed representations and generalisation performance. Our results show that while late-stage compression is frequently observed, compressed latent representations do not consistently correlate with improved generalization performance. Instead, the relationship between compression and generalisation is highly dependent on task, architecture, and regularisation.

Related papers

• On the Generalization Behavior of Deep Residual Networks From a Dynamical System Perspective [1.0388986221727612]
  Deep neural networks (DNNs) have significantly advanced machine learning, with model depth playing a central role in their successes.<n>In this work, we establish generalization error bounds for both discrete- and continuous-time residual networks (ResNets) by combining Rademacher complexity, flow maps of dynamical systems, and the convergence behavior of ResNets in the deep-layer limit.<n>Findings provide a unified understanding of generalization across both discrete- and continuous-time ResNets, helping to close the gap in both the order of sample complexity and assumptions between the discrete- and continuous-time settings.
  arXiv  Detail & Related papers  (2026-02-24T13:59:06Z)
• Data-Driven Deep MIMO Detection:Network Architectures and Generalization Analysis [50.20709408241935]
  This paper proposes inspecting the fully data-driven DeepSIC detection within a Network-of-MLPs architecture.<n>Within such an architecture, DeepSIC can be upgraded as a graph-based message-passing process using Graph Neural Networks (GNNs)<n>GNNSIC achieves excellent expressivity comparable to DeepSIC with substantially fewer trainable parameters.
  arXiv  Detail & Related papers  (2026-02-13T04:38:51Z)
• Generalization in Representation Models via Random Matrix Theory: Application to Recurrent Networks [7.721672385781673]
  We first study the generalization error of models that use a fixed feature representation (frozen intermediate layers) followed by a trainable readout layer.<n>We apply Random Matrix Theory to derive a closed-form expression for the generalization error.<n>We then apply this analysis to recurrent representations and obtain concise formula that characterize their performance.
  arXiv  Detail & Related papers  (2025-11-04T09:30:31Z)
• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy [55.014926694758195]
  Entropy and mutual information in neural networks provide rich information on the learning process. We leverage data geometry to access the underlying manifold and reliably compute these information-theoretic measures. We show that they form noise-resistant measures of intrinsic dimensionality and relationship strength in high-dimensional simulated data.
  arXiv  Detail & Related papers  (2023-12-04T01:32:42Z)
• Probabilistically Rewired Message-Passing Neural Networks [41.554499944141654]
  Message-passing graph neural networks (MPNNs) emerged as powerful tools for processing graph-structured input. MPNNs operate on a fixed input graph structure, ignoring potential noise and missing information. We devise probabilistically rewired MPNNs (PR-MPNNs) which learn to add relevant edges while omitting less beneficial ones.
  arXiv  Detail & Related papers  (2023-10-03T15:43:59Z)
• Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
  neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
  arXiv  Detail & Related papers  (2023-10-02T03:25:32Z)
• Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression [37.69303106863453]
  The Information Bottleneck (IB) principle offers an information-theoretic framework for analyzing the training process of deep neural networks (DNNs) In this paper, we introduce a framework for conducting IB analysis of general NNs. We also perform IB analysis on a close-to-real-scale, which reveals new features of the MI dynamics.
  arXiv  Detail & Related papers  (2023-05-13T21:44:32Z)
• Data efficiency and extrapolation trends in neural network interatomic potentials [0.0]
  We show how architectural and optimization choices influence the generalization of neural network interatomic potentials (NNIPs) We show that test errors in NNIP follow a scaling relation and can be robust to noise, but cannot predict MD stability in the high-accuracy regime. Our work provides a deep learning justification for the extrapolation performance of many common NNIPs.
  arXiv  Detail & Related papers  (2023-02-12T00:34:05Z)
• 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)
• Understanding Generalization in Deep Learning via Tensor Methods [53.808840694241]
  We advance the understanding of the relations between the network's architecture and its generalizability from the compression perspective. We propose a series of intuitive, data-dependent and easily-measurable properties that tightly characterize the compressibility and generalizability of neural networks.
  arXiv  Detail & Related papers  (2020-01-14T22:26:57Z)

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.