Bits and Pieces: Understanding Information Decomposition from Part-whole Relationships and Formal Logic
Not on the map. Why?
Abstract (arXiv)
Partial information decomposition (PID) seeks to decompose the multivariate mutual information that a set of source variables contains about a target variable into basic pieces, the so called "atoms of information". Each atom describes a distinct way in which the sources may contain information about the target. In this paper we show, first, that the entire theory of partial information decomposition can be derived from considerations of elementary parthood relationships between information contributions. This way of approaching the problem has the advantage of directly characterizing the atoms of information, instead of taking an indirect approach via the concept of redundancy. Secondly, we describe several intriguing links between PID and formal logic. In particular, we show how to define a measure of PID based on the information provided by certain statements about source realizations. Furthermore, we show how the mathematical lattice structure underlying PID theory can be translated into an isomorphic structure of logical statements with a particularly simple ordering relation: logical implication. The conclusion to be drawn from these considerations is that there are three isomorphic "worlds" of partial information decomposition, i.e. three equivalent ways to mathematically describe the decomposition of the information carried by a set of sources about a target: the world of parthood relationships, the world of logical statements, and the world of antichains that was utilized by Williams and Beer in their original exposition of PID theory. We additionally show how the parthood perspective provides a systematic way to answer a type of question that has been much discussed in the PID field: whether a partial information decomposition can be uniquely determined based on concepts other than redundant information.
Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Aug 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 3; 2023: 5; 2024: 2; 2025: 2; 2026: 1.
15 papers.
Sort:
By area:
- 2023To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Reviewcited by 72
- 2021A Rigorous Information-Theoretic Definition of Redundancy and Relevancy in Feature Selection Based on (Partial) Information Decompositioncited by 25
- 2023Learning from data with structured missingnesscited by 24
- 2023More Synergy, Less Redundancy: Exploiting Joint Mutual Information for Self-Supervised Learningcited by 11
- 2022A Measure of the Complexity of Neural Representations based on Partial Information Decompositioncited by 10
- 2023Information decomposition in complex systems via machine learningcited by 9
- 2023A General Framework for Interpretable Neural Learning based on Local Information-Theoretic Goal Functionscited by 8
- 2022Synergistic information supports modality integration and flexible learning in neural networks solving multiple taskscited by 7
- 2022Ultra-marginal Feature Importance: Learning from Data with Causal Guaranteescited by 6
- 2025Stochastic Forward-Forward Learning through Representational Dimensionality Compressioncited by 4
- 2026Auditing Language Model Unlearning via Information Decompositioncited by 3
- 2024What should a neuron aim for? Designing local objective functions based on information theorycited by 2
3 more
- 2021Interaction-Aware Sensitivity Analysis for Aerodynamic Optimization Results using Information Theorycited by 0
- 2024Rethinking Self-Supervised Learning Within the Framework of Partial Information Decompositioncited by 0
- 2025Redundancy Maximization as a Principle of Associative Memory Learning in Hopfield Networkscited by 0
- 2026Auditing Language Model Unlearning via Information Decomposition21 Jan 2026
- 2025Redundancy Maximization as a Principle of Associative Memory Learning in Hopfield Networks4 Nov 2025
- 2025Stochastic Forward-Forward Learning through Representational Dimensionality Compression22 May 2025
- 2024What should a neuron aim for? Designing local objective functions based on information theory3 Dec 2024
- 2024Rethinking Self-Supervised Learning Within the Framework of Partial Information Decomposition3 Dec 2024
- 2023Information decomposition in complex systems via machine learning10 Jul 2023
- 2023More Synergy, Less Redundancy: Exploiting Joint Mutual Information for Self-Supervised Learning2 Jul 2023
- 2023A General Framework for Interpretable Neural Learning based on Local Information-Theoretic Goal Functions3 Jun 2023
- 2023To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review19 Apr 2023
- 2023Learning from data with structured missingness4 Apr 2023
- 2022Synergistic information supports modality integration and flexible learning in neural networks solving multiple tasks6 Oct 2022
- 2022A Measure of the Complexity of Neural Representations based on Partial Information Decomposition21 Sep 2022
3 more
- 2022Ultra-marginal Feature Importance: Learning from Data with Causal Guarantees21 Apr 2022
- 2021Interaction-Aware Sensitivity Analysis for Aerodynamic Optimization Results using Information Theory10 Dec 2021
- 2021A Rigorous Information-Theoretic Definition of Redundancy and Relevancy in Feature Selection Based on (Partial) Information Decomposition10 May 2021
- 2023To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Reviewcited by 72
- 2021A Rigorous Information-Theoretic Definition of Redundancy and Relevancy in Feature Selection Based on (Partial) Information Decompositioncited by 25
- 2023Learning from data with structured missingnesscited by 24
- 2023More Synergy, Less Redundancy: Exploiting Joint Mutual Information for Self-Supervised Learningcited by 11
- 2022A Measure of the Complexity of Neural Representations based on Partial Information Decompositioncited by 10
- 2023Information decomposition in complex systems via machine learningcited by 9
- 2023A General Framework for Interpretable Neural Learning based on Local Information-Theoretic Goal Functionscited by 8
- 2022Synergistic information supports modality integration and flexible learning in neural networks solving multiple taskscited by 7
- 2022Ultra-marginal Feature Importance: Learning from Data with Causal Guaranteescited by 6
- 2025Stochastic Forward-Forward Learning through Representational Dimensionality Compressioncited by 4
- 2024What should a neuron aim for? Designing local objective functions based on information theorycited by 2
- 2021Interaction-Aware Sensitivity Analysis for Aerodynamic Optimization Results using Information Theorycited by 0
12 most cited of 14 All 14 (JSON)
- 2025Redundancy Maximization as a Principle of Associative Memory Learning in Hopfield Networks4 Nov 2025
- 2025Stochastic Forward-Forward Learning through Representational Dimensionality Compression22 May 2025
- 2024What should a neuron aim for? Designing local objective functions based on information theory3 Dec 2024
- 2024Rethinking Self-Supervised Learning Within the Framework of Partial Information Decomposition3 Dec 2024
- 2023Information decomposition in complex systems via machine learning10 Jul 2023
- 2023More Synergy, Less Redundancy: Exploiting Joint Mutual Information for Self-Supervised Learning2 Jul 2023
- 2023A General Framework for Interpretable Neural Learning based on Local Information-Theoretic Goal Functions3 Jun 2023
- 2023To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review19 Apr 2023
- 2023Learning from data with structured missingness4 Apr 2023
- 2022Synergistic information supports modality integration and flexible learning in neural networks solving multiple tasks6 Oct 2022
- 2022A Measure of the Complexity of Neural Representations based on Partial Information Decomposition21 Sep 2022
- 2022Ultra-marginal Feature Importance: Learning from Data with Causal Guarantees21 Apr 2022
12 newest of 14 All 14 (JSON)