skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Dagma-DCE: Interpretable, Non-Parametric Differentiable Causal Discovery
We introduce Dagma-DCE, an interpretable and model-agnostic scheme for differentiable causal discovery. Current non- or over-parametric methods in differentiable causal discovery use opaque proxies of ``independence'' to justify the inclusion or exclusion of a causal relationship. We show theoretically and empirically that these proxies may be arbitrarily different than the actual causal strength. Juxtaposed to existing differentiable causal discovery algorithms, Dagma-DCE uses an interpretable measure of causal strength to define weighted adjacency matrices. In a number of simulated datasets, we show our method achieves state-of-the-art level performance. We additionally show that Dagma-DCE allows for principled thresholding and sparsity penalties by domain-experts. The code for our method is available open-source at https://github.com/DanWaxman/DAGMA-DCE, and can easily be adapted to arbitrary differentiable models.  more » « less
Award ID(s):
2212506
PAR ID:
10513859
Author(s) / Creator(s):
; ;
Publisher / Repository:
IEEE Open Journal of Signal Processing,
Date Published:
Journal Name:
IEEE Open Journal of Signal Processing
Volume:
5
ISSN:
2644-1322
Page Range / eLocation ID:
393 to 401
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. (, EUSIPCO)
    One of the most important problems in science is understanding causation. This problem is particularly challenging when causation has to be inferred from observational data only. A further challenge of this problem is if the observed data were generated in the presence of latent confounders. In this paper, we propose a method for detecting confounders in multivariate time series using a recently introduced concept referred to as differential causal effect (DCE). The solution is based on feature-based Gaussian processes that are not only used for estimating the DCE of the observed time series but also for estimating the latent confounders. We demonstrate the performance of the proposed method with several examples. They show that the proposed approach can detect confounders and can accurately estimate causal strengths. 
    more » « less
  2. ; ; ; (, Proceedings of the International Conference on Artificial Intelligence and Statistics)
    Arindam Banerjee; Kenji Fukumizu (Ed.)
    The data drawn from biological, economic, and social systems are often confounded due to the presence of unmeasured variables. Prior work in causal discovery has focused on discrete search procedures for selecting acyclic directed mixed graphs (ADMGs), specifically ancestral ADMGs, that encode ordinary conditional independence constraints among the observed variables of the system. However, confounded systems also exhibit more general equality restrictions that cannot be represented via these graphs, placing a limit on the kinds of structures that can be learned using ancestral ADMGs. In this work, we derive differentiable algebraic constraints that fully characterize the space of ancestral ADMGs, as well as more general classes of ADMGs, arid ADMGs and bow-free ADMGs, that capture all equality restrictions on the observed variables. We use these constraints to cast causal discovery as a continuous optimization problem and design differentiable procedures to find the best fitting ADMG when the data comes from a confounded linear system of equations with correlated errors. We demonstrate the efficacy of our method through simulations and application to a protein expression dataset. Code implementing our methods is open-source and publicly available at https: //gitlab.com/rbhatta8/dcd and will be incorporated into the Ananke package. 
    more » « less
  3. ; ; (, Advances in neural information processing systems)
    Recent text-based causal methods attempt to mitigate confounding bias by estimating proxies of confounding variables that are partially or imperfectly measured from unstructured text data. These approaches, however, assume analysts have supervised labels of the confounders given text for a subset of instances, a constraint that is sometimes infeasible due to data privacy or annotation costs. In this work, we address settings in which an important confounding variable is completely unobserved. We propose a new causal inference method that uses two instances of pre-treatment text data, infers two proxies using two zero-shot models on the separate instances, and applies these proxies in the proximal g-formula. We prove, under certain assumptions about the instances of text and accuracy of the zero-shot predictions, that our method of inferring text-based proxies satisfies identification conditions of the proximal g-formula while other seemingly reasonable proposals do not. To address untestable assumptions associated with our method and the proximal g-formula, we further propose an odds ratio falsification heuristic that flags when to proceed with downstream effect estimation using the inferred proxies. We evaluate our method in synthetic and semi-synthetic settings---the latter with real-world clinical notes from MIMIC-III and open large language models for zero-shot prediction---and find that our method produces estimates with low bias. We believe that this text-based design of proxies allows for the use of proximal causal inference in a wider range of scenarios, particularly those for which obtaining suitable proxies from structured data is difficult. 
    more » « less
  4. ; ; ; ; ; ; ; ; ; ; et al (, Atmospheric Chemistry and Physics)
    Abstract. The chemical compound 1,2-dichloroethane (DCE), or ethylene dichloride, is an industrial very short-lived substance (VSLS) whose major use is as a feedstock in the production chain of polyvinyl chloride (PVC). Like other chlorinated VSLSs, transport of DCE (and/or its atmospheric oxidation products) to the stratosphere could contribute to ozone depletion there. However, despite annual production volumes greatly exceeding those of more prominent VSLSs (e.g. dichloromethane), global DCE observations are sparse; thus, the magnitude and distribution of DCE emissions and trends in its atmospheric abundance are poorly known. In this study, we performed an exploratory analysis of the global DCE budget between 2002 and 2020. Combining bottom-up data on annual production and assumptions around fugitive losses during production and feedstock use, we assessed the DCE source strength required to reproduce atmospheric DCE observations. We show that the TOMCAT/SLIMCAT 3-D chemical transport model (CTM) reproduces DCE measurements from various aircraft missions well, including HIPPO (2009–2011), ATom (2016–2018), and KORUS-AQ (2016), along with surface measurements from Southeast Asia, when assuming a regionally varying production emission factor in the range of 0.5 %–1.5 %. Our findings imply substantial fugitive losses of DCE and/or substantial emissive applications (e.g. solvent use) that are poorly reported. We estimate that DCE's global source increased by ∼ 45 % between 2002 (349 ± 61 Gg yr−1) and 2020 (505 ± 90 Gg yr−1), with its contribution to stratospheric chlorine increasing from 8.2 (± 1.5) to ∼ 12.9 (± 2.4) ppt Cl (where ppt denotes parts per trillion) over this period. DCE's relatively short overall tropospheric lifetime (∼ 83 d) limits, although does not preclude, its transport to the stratosphere, and we show that its impact on ozone is small at present. Annually averaged, DCE is estimated to have decreased ozone in the lower stratosphere by up to several parts per billion (< 1 %) in 2020, although a larger effect in the springtime Southern Hemisphere polar lower stratosphere is apparent (decreases of up to ∼ 1.3 %). Given strong potential for growth in DCE production tied to demand for PVC, ongoing measurements would be of benefit to monitor potential future increases in its atmospheric abundance and its contribution to ozone depletion. 
    more » « less
  5. ; ; ; ; ; (, Proceedings of the AAAI Conference on Artificial Intelligence)
    Identifying the causal pathways of unfairness is a critical objective for improving policy design and algorithmic decision-making. Prior work in causal fairness analysis often requires knowledge of the causal graph, hindering practical applications in complex or low-knowledge domains. Moreover, global discovery methods that learn causal structure from data can display unstable performance on finite samples, preventing robust fairness conclusions. To mitigate these challenges, we introduce local discovery for direct discrimination (LD3): a method that uncovers structural evidence of direct unfairness by identifying the causal parents of an outcome variable. LD3 performs a linear number of conditional independence tests relative to variable set size, and allows for latent confounding under the sufficient condition that all parents of the outcome are observed. We show that LD3 returns a valid adjustment set (VAS) under a new graphical criterion for the weighted controlled direct effect, a qualitative indicator of direct discrimination. LD3 limits unnecessary adjustment, providing interpretable VAS for assessing unfairness. We use LD3 to analyze causal fairness in two complex decision systems: criminal recidivism prediction and liver transplant allocation. LD3 was more time-efficient and returned more plausible results on real-world data than baselines, which took 46× to 5870× longer to execute. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email