The Causal Abstraction Network: Theory and Learning

• URL: http://arxiv.org/abs/2509.25236v1
• Date: Thu, 25 Sep 2025 07:48:25 GMT
• Title: The Causal Abstraction Network: Theory and Learning
• Authors: Gabriele D'Acunto, Paolo Di Lorenzo, Sergio Barbarossa,
• Abstract summary: Causal artificial intelligence aims to enhance explainability, robustness, and trustworthiness in AI by leveraging structural causal models (SCMs)<n>Recent advances formalize network sheaves of causal knowledge.<n>We introduce the causal abstraction network (CAN), a specific instance of such sheaves where (i)s are Gaussian, (ii) maps are transposes of constructive linear abstractions.
• Score: 14.952578725545344
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Causal artificial intelligence aims to enhance explainability, trustworthiness, and robustness in AI by leveraging structural causal models (SCMs). In this pursuit, recent advances formalize network sheaves of causal knowledge. Pushing in the same direction, we introduce the causal abstraction network (CAN), a specific instance of such sheaves where (i) SCMs are Gaussian, (ii) restriction maps are transposes of constructive linear causal abstractions (CAs), and (iii) edge stalks correspond -- up to rotation -- to the node stalks of more detailed SCMs. We investigate the theoretical properties of CAN, including algebraic invariants, cohomology, consistency, global sections characterized via the Laplacian kernel, and smoothness. We then tackle the learning of consistent CANs. Our problem formulation separates into edge-specific local Riemannian problems and avoids nonconvex, costly objectives. We propose an efficient search procedure as a solution, solving the local problems with SPECTRAL, our iterative method with closed-form updates and suitable for positive definite and semidefinite covariance matrices. Experiments on synthetic data show competitive performance in the CA learning task, and successful recovery of diverse CAN structures.

Related papers

• Learning Consistent Causal Abstraction Networks [14.952578725545344]
  Causal artificial intelligence aims to enhance explainability, robustness, and trustworthiness in AI by leveraging structural causal models (SCMs)<n>We tackle the consistent abstraction network (CAN)<n>Experiments show competitive learning on synthetic data, and successful recovery of diverse CAN structures.
  arXiv  Detail & Related papers  (2026-02-02T16:16:29Z)
• The Relativity of Causal Knowledge [4.051523221722475]
  Recent advances in artificial intelligence reveal the limits of purely predictive systems and call for a shift toward causal and collaborative reasoning.<n>We introduce the relativity of causal knowledge, which posits structural causal models (SCMs) are inherently imperfect, subjective representations embedded within networks of relationships.
  arXiv  Detail & Related papers  (2025-03-13T16:24:48Z)
• Causal Abstraction Learning based on the Semantic Embedding Principle [8.867171632530908]
  Structural causal models (SCMs) allow us to investigate complex systems at multiple levels of resolution.<n>We present a category-theoretic approach to SCMs that enables the learning of a CA by finding a morphism between the low- and high-level measures.
  arXiv  Detail & Related papers  (2025-02-01T11:54:44Z)
• Semantic Loss Functions for Neuro-Symbolic Structured Prediction [74.18322585177832]
  We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training. It is agnostic to the arrangement of the symbols, and depends only on the semantics expressed thereby. It can be combined with both discriminative and generative neural models.
  arXiv  Detail & Related papers  (2024-05-12T22:18:25Z)
• Multi-modal Causal Structure Learning and Root Cause Analysis [67.67578590390907]
  We propose Mulan, a unified multi-modal causal structure learning method for root cause localization. We leverage a log-tailored language model to facilitate log representation learning, converting log sequences into time-series data. We also introduce a novel key performance indicator-aware attention mechanism for assessing modality reliability and co-learning a final causal graph.
  arXiv  Detail & Related papers  (2024-02-04T05:50:38Z)
• Causal Optimal Transport of Abstractions [8.642152250082368]
  Causal abstraction (CA) theory establishes formal criteria for relating multiple structural causal models (SCMs) at different levels of granularity. We propose COTA, the first method to learn abstraction maps from observational and interventional data without assuming complete knowledge of the underlying SCMs. We extensively evaluate COTA on synthetic and real world problems, and showcase its advantages over non-causal, independent and aggregated COTA formulations.
  arXiv  Detail & Related papers  (2023-12-13T12:54:34Z)
• Structure Learning and Parameter Estimation for Graphical Models via Penalized Maximum Likelihood Methods [0.0]
  In the thesis, we consider two different types of PGMs: Bayesian networks (BNs) which are static, and continuous time Bayesian networks which, as the name suggests, have a temporal component. We are interested in recovering their true structure, which is the first step in learning any PGM.
  arXiv  Detail & Related papers  (2023-01-30T20:26:13Z)
• Amortized Inference for Causal Structure Learning [72.84105256353801]
  Learning causal structure poses a search problem that typically involves evaluating structures using a score or independence test. We train a variational inference model to predict the causal structure from observational/interventional data. Our models exhibit robust generalization capabilities under substantial distribution shift.
  arXiv  Detail & Related papers  (2022-05-25T17:37:08Z)
• Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis [94.64007376939735]
  We theoretically characterize the impact of connectivity patterns on the convergence of deep neural networks (DNNs) under gradient descent training. We show that by a simple filtration on "unpromising" connectivity patterns, we can trim down the number of models to evaluate.
  arXiv  Detail & Related papers  (2022-05-11T17:43:54Z)
• The Causal Neural Connection: Expressiveness, Learnability, and Inference [125.57815987218756]
  An object called structural causal model (SCM) represents a collection of mechanisms and sources of random variation of the system under investigation. In this paper, we show that the causal hierarchy theorem (Thm. 1, Bareinboim et al., 2020) still holds for neural models. We introduce a special type of SCM called a neural causal model (NCM), and formalize a new type of inductive bias to encode structural constraints necessary for performing causal inferences.
  arXiv  Detail & Related papers  (2021-07-02T01:55:18Z)
• Disentangling Observed Causal Effects from Latent Confounders using Method of Moments [67.27068846108047]
  We provide guarantees on identifiability and learnability under mild assumptions. We develop efficient algorithms based on coupled tensor decomposition with linear constraints to obtain scalable and guaranteed solutions.
  arXiv  Detail & Related papers  (2021-01-17T07:48:45Z)

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.