Towards Learning and Explaining Indirect Causal Effects in Neural Networks

• URL: http://arxiv.org/abs/2303.13850v3
• Date: Mon, 8 Jan 2024 07:15:57 GMT
• Title: Towards Learning and Explaining Indirect Causal Effects in Neural Networks
• Authors: Abbavaram Gowtham Reddy, Saketh Bachu, Harsharaj Pathak, Benin L Godfrey, Vineeth N. Balasubramanian, Varshaneya V, Satya Narayanan Kar
• Abstract summary: We view an NN as a structural causal model (SCM) and extend our focus to include indirect causal effects by introducing feedforward connections among input neurons. We propose an ante-hoc method that captures and maintains direct, indirect, and total causal effects during NN model training. We also propose an algorithm for quantifying learned causal effects in an NN model and efficient approximation strategies for quantifying causal effects in high-dimensional data.
• Score: 22.658383399117003
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, there has been a growing interest in learning and explaining causal effects within Neural Network (NN) models. By virtue of NN architectures, previous approaches consider only direct and total causal effects assuming independence among input variables. We view an NN as a structural causal model (SCM) and extend our focus to include indirect causal effects by introducing feedforward connections among input neurons. We propose an ante-hoc method that captures and maintains direct, indirect, and total causal effects during NN model training. We also propose an algorithm for quantifying learned causal effects in an NN model and efficient approximation strategies for quantifying causal effects in high-dimensional data. Extensive experiments conducted on synthetic and real-world datasets demonstrate that the causal effects learned by our ante-hoc method better approximate the ground truth effects compared to existing methods.

Related papers

• Estimating Peer Direct and Indirect Effects in Observational Network Data [16.006409149421515]
  We propose a general setting which considers both peer direct effects and peer indirect effects, and the effect of an individual's own treatment. We use attention mechanisms to distinguish the influences of different neighbors and explore high-order neighbor effects through graph neural networks. Our theoretical findings have the potential to improve intervention strategies in networked systems, with applications in areas such as social networks and epidemiology.
  arXiv  Detail & Related papers  (2024-08-21T10:02:05Z)
• Neural Networks with Causal Graph Constraints: A New Approach for Treatment Effects Estimation [0.951494089949975]
  We present a new model, NN-CGC, that considers additional information from the causal graph. We show that our method is robust to imperfect causal graphs and that using partial causal information is preferable to ignoring it.
  arXiv  Detail & Related papers  (2024-04-18T14:57:17Z)
• CausalDialogue: Modeling Utterance-level Causality in Conversations [83.03604651485327]
  We have compiled and expanded upon a new dataset called CausalDialogue through crowd-sourcing. This dataset includes multiple cause-effect pairs within a directed acyclic graph (DAG) structure. We propose a causality-enhanced method called Exponential Average Treatment Effect (ExMATE) to enhance the impact of causality at the utterance level in training neural conversation models.
  arXiv  Detail & Related papers  (2022-12-20T18:31:50Z)
• NESTER: An Adaptive Neurosymbolic Method for Causal Effect Estimation [37.361149306896024]
  Causal effect estimation from observational data is a central problem in causal inference. We propose an adaptive method called Neurosymbolic Causal Effect Estimator (NESTER) Our comprehensive empirical results show that NESTER performs better than state-of-the-art methods on benchmark datasets.
  arXiv  Detail & Related papers  (2022-11-08T16:48:46Z)
• Modeling Associative Plasticity between Synapses to Enhance Learning of Spiking Neural Networks [4.736525128377909]
  Spiking Neural Networks (SNNs) are the third generation of artificial neural networks that enable energy-efficient implementation on neuromorphic hardware. We propose a robust and effective learning mechanism by modeling the associative plasticity between synapses. Our approaches achieve superior performance on static and state-of-the-art neuromorphic datasets.
  arXiv  Detail & Related papers  (2022-07-24T06:12:23Z)
• Knowledge Enhanced Neural Networks for relational domains [83.9217787335878]
  We focus on a specific method, KENN, a Neural-Symbolic architecture that injects prior logical knowledge into a neural network. In this paper, we propose an extension of KENN for relational data.
  arXiv  Detail & Related papers  (2022-05-31T13:00:34Z)
• Learning Neural Causal Models with Active Interventions [83.44636110899742]
  We introduce an active intervention-targeting mechanism which enables a quick identification of the underlying causal structure of the data-generating process. Our method significantly reduces the required number of interactions compared with random intervention targeting. We demonstrate superior performance on multiple benchmarks from simulated to real-world data.
  arXiv  Detail & Related papers  (2021-09-06T13:10:37Z)
• 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)
• Efficient Causal Inference from Combined Observational and Interventional Data through Causal Reductions [68.6505592770171]
  Unobserved confounding is one of the main challenges when estimating causal effects. We propose a novel causal reduction method that replaces an arbitrary number of possibly high-dimensional latent confounders. We propose a learning algorithm to estimate the parameterized reduced model jointly from observational and interventional data.
  arXiv  Detail & Related papers  (2021-03-08T14:29:07Z)
• Network Diffusions via Neural Mean-Field Dynamics [52.091487866968286]
  We propose a novel learning framework for inference and estimation problems of diffusion on networks. Our framework is derived from the Mori-Zwanzig formalism to obtain an exact evolution of the node infection probabilities. Our approach is versatile and robust to variations of the underlying diffusion network models.
  arXiv  Detail & Related papers  (2020-06-16T18:45:20Z)

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.