Browse State-of-the-Art › Information Plane

Information Plane

11 papers with code · 0 benchmarks · 0 datasets archive 2025-07-28

Methodology

To obtain the Information Plane (IP) of deep neural networks, which shows the trajectories of the hidden layers during training in a 2D plane using as coordinate axes the mutual information between the input and the hidden layer, and the mutual information between the output and the hidden layer.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 30 · with a code link: 11 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (2 of 30 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 30 of 30, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from.

  • Previous work proposed to analyze DNNs in the Information Plane; i. e., the plane of the Mutual Information values that each layer preserves on the input and output variables.
  • The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks.
  • 14 Feb 2024 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
    End-to-end (E2E) training, optimizing the entire model through error backpropagation, fundamentally supports the advancements of deep learning.
  • 22 Feb 2022 1 repository listed
    Even after pruning the filters from convolutional layers of LeNet-5 drastically (i. e. from 20, 50 to 2, 3, respectively), only a small accuracy drop of 0.
  • 15 Feb 2021 1 repository listed
    Thus, we conclude that the compression phase is not necessary for generalization in representation learning.
  • 9 Feb 2021 1 repository listed
    Conventionally, it resorts to characterizing the information plane, that is, plotting I(Y;Z) versus I(X;Z) for all solutions obtained from different initial points.
  • 16 Sep 2020 1 repository listed
    Applying our results can serve to guide analysis methods for machine learning engineers and suggests that neural networks that can exploit the convolution theorem are equally accurate as standard convolutional neural…
  • 8 Jun 2020 1 repository listed
    The Information Bottleneck (IB) framework is a general characterization of optimal representations obtained using a principled approach for balancing accuracy and complexity.
  • 15 May 2020 1 repository listed
    Recently, the Information Plane (IP) was proposed to analyze them, which is based on the information-theoretic concept of mutual information (MI).
  • 27 Jan 2018 1 repository listed
    To the best of our knowledge EDGE is the first non-parametric MI estimator that can achieve parametric MSE rates with linear time complexity.
  • 1 Jan 2018 1 repository listed
    The practical successes of deep neural networks have not been matched by theoretical progress that satisfyingly explains their behavior.
  • Information plane and compression-gnostic feedback in quantum machine learning
    4 Nov 2024 0 repositories listed
    The information plane (Tishby et al. arXiv:physics/0004057, Shwartz-Ziv et al. arXiv:1703.00810) has been proposed as an analytical tool for studying the learning dynamics of neural networks.
  • Enhancing Neural Network Interpretability Through Conductance-Based Information Plane Analysis
    26 Aug 2024 0 repositories listed
    The Information Plane is a conceptual framework used to analyze the flow of information in neural networks, but traditional methods based on activations may not fully capture the dynamics of information processing.
  • Lightweight Conceptual Dictionary Learning for Text Classification Using Information Compression
    28 Apr 2024 0 repositories listed
    We propose a novel, lightweight supervised dictionary learning framework for text classification based on data compression and representation.
  • Information Plane Analysis Visualization in Deep Learning via Transfer Entropy
    1 Apr 2024 0 repositories listed
    In a feedforward network, Transfer Entropy (TE) can be used to measure the influence that one layer has on another by quantifying the information transfer between them during training.
  • Improving the Robustness of Quantized Deep Neural Networks to White-Box Attacks using Stochastic Quantization and Information-Theoretic Ensemble Training
    30 Nov 2023 0 repositories listed
    Most real-world applications that employ deep neural networks (DNNs) quantize them to low precision to reduce the compute needs.
  • SoFaiR: Single Shot Fair Representation Learning
    26 Apr 2022 0 repositories listed
    To avoid discriminatory uses of their data, organizations can learn to map them into a representation that filters out information related to sensitive attributes.
  • Mutual information estimation for graph convolutional neural networks
    31 Mar 2022 0 repositories listed
    Measuring model performance is a key issue for deep learning practitioners.
  • A Comparative Genomic Analysis of Coronavirus Families Using Chaos Game Representation and Fisher-Shannon Complexity
    13 Jul 2021 0 repositories listed
    From its first emergence in Wuhan, China in December, 2019 the COVID-19 pandemic has caused unprecedented health crisis throughout the world.
  • Fundamental Limits and Tradeoffs in Invariant Representation Learning
    19 Dec 2020 0 repositories listed
    A wide range of machine learning applications such as privacy-preserving learning, algorithmic fairness, and domain adaptation/generalization among others, involve learning invariant representations of the data that aim…
  • On Information Plane Analyses of Neural Network Classifiers -- A Review
    21 Mar 2020 0 repositories listed
    We review the current literature concerned with information plane analyses of neural network classifiers.
  • On Predictive Information in RNNs
    21 Oct 2019 0 repositories listed
    Certain biological neurons demonstrate a remarkable capability to optimally compress the history of sensory inputs while being maximally informative about the future.
  • Information Plane Analysis of Deep Neural Networks via Matrix-Based Renyi's Entropy and Tensor Kernels
    25 Sep 2019 0 repositories listed
    Analyzing deep neural networks (DNNs) via information plane (IP) theory has gained tremendous attention recently as a tool to gain insight into, among others, their generalization ability.
  • Information Plane Analysis of Deep Neural Networks via Matrix--Based Renyi's Entropy and Tensor Kernels
    25 Sep 2019 0 repositories listed
    Analyzing deep neural networks (DNNs) via information plane (IP) theory has gained tremendous attention recently as a tool to gain insight into, among others, their generalization ability.
  • On Predictive Information Sub-optimality of RNNs
    25 Sep 2019 0 repositories listed
    Certain biological neurons demonstrate a remarkable capability to optimally compress the history of sensory inputs while being maximally informative about the future.
  • On the Trajectory of Stochastic Gradient Descent in the Information Plane
    1 May 2019 0 repositories listed
    Studying the evolution of information theoretic quantities during Stochastic Gradient Descent (SGD) learning of Artificial Neural Networks (ANNs) has gained popularity in recent years.
  • REPRESENTATION COMPRESSION AND GENERALIZATION IN DEEP NEURAL NETWORKS
    1 May 2019 0 repositories listed
    Understanding the groundbreaking performance of Deep Neural Networks is one of the greatest challenges to the scientific community today.
  • Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane
    1 Sep 2018 0 repositories listed
    Inspired by the pioneering work of information bottleneck principle for Deep Neural Networks (DNNs) analysis, we design an information plane based framework to evaluate the capability of DNNs for image classification…
  • Understanding Autoencoders with Information Theoretic Concepts
    30 Mar 2018 0 repositories listed
    Despite their great success in practical applications, there is still a lack of theoretical and systematic methods to analyze deep neural networks.
  • Distinguishing noise from chaos: objective versus subjective criteria using Horizontal Visibility Graph
    9 Jan 2014 0 repositories listed
    A recently proposed methodology called the Horizontal Visibility Graph (HVG) [Luque et al., Phys.

Syntology lines on 3 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections