Explainable AI in industry

Gade, Krishna; Geyik, Sahin Cem; Kenthapadi, Krishnaram; Mithal, Varun; Taly, Ankur

doi:10.1145/3351095.3375664

Cited by 30 publications

(26 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Explainable machine learning is concerned with the problem of providing explanations for complex machine learning models. Towards this goal, various streams of research follow different explainability paradigms which can roughly be categorized into feature highlighting and counterfactual explanations (Guidotti et al, 2018;Gade et al, 2019).…”

Section: Explanation Mechanisms For Deep Learning With Tabular Datamentioning

confidence: 99%

Deep Neural Networks and Tabular Data: A Survey

Borisov¹,

Leemann²,

Seßler³

et al. 2021

Preprint

View full text Add to dashboard Cite

Heterogeneous tabular data are the most commonly used form of data and are essential for numerous critical and computationally demanding applications. On homogeneous data sets, deep neural networks have repeatedly shown excellent performance and have therefore been widely adopted. However, their application to modeling tabular data (inference or generation) remains highly challenging. This work provides an overview of state-of-the-art deep learning methods for tabular data. We start by categorizing them into three groups: data transformations, specialized architectures, and regularization models. We then provide a comprehensive overview of the main approaches in each group. A discussion of deep learning approaches for generating tabular data is complemented by strategies for explaining deep models on tabular data. Our primary contribution is to address the main research streams and existing methodologies in this area, while highlighting relevant challenges and open research questions. To the best of our knowledge, this is the first in-depth look at deep learning approaches for tabular data. This work can serve as a valuable starting point and guide for researchers and practitioners interested in deep learning with tabular data.

show abstract

Section: Explanation Mechanisms For Deep Learning With Tabular Datamentioning

confidence: 99%

Deep Neural Networks and Tabular Data: A Survey

Borisov¹,

Leemann²,

Seßler³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Nevertheless, this prediction model generally exceeds simple linear models or decision trees and random forest predictions. Yet, such simple models are still preferred in the field of medical science due to their simplicity and interpretability [153][154][155] . Many studies have been targeted to build and execute model-agnostic interpretability tools [156][157][158] .…”

Section: Machine Learning Algorithmsmentioning

confidence: 99%

Metabolite, Protein, And Tissue Dysfunction Associated With COVID-19 Disease Severity

Rahnavard

Mann

Giri

et al. 2021

Preprint

View full text Add to dashboard Cite

Proteins are direct products of the genome and metabolites are functional products of interactions between the host and other factors such as environment, disease state, clinical information, etc. Omics data, including proteins and metabolites, are useful in characterizing biological processes underlying COVID-19 along with patient data and clinical information, yet few methods are available to effectively analyze such diverse and unstructured data. Using an integrated approach that combines proteomics and metabolomics data, we investigated the changes in metabolites and proteins in relation to patient characteristics (e.g., age, gender, and health outcome) and clinical information (e.g., metabolic panel and complete blood count test results). We found significant enrichment of biological indicators of lung, liver, and gastrointestinal dysfunction associated with disease severity using metabolite and protein profiles. Our analyses specifically identified enriched proteins that play a critical role in responses to injury or infection within these anatomical sites, but may contribute to excessive systemic inflammation within the context of COVID-19. Furthermore, we have used this information in conjunction with machine learning algorithms to predict the health status of patients presenting symptoms of COVID-19. This work provides a roadmap for understanding the biochemical pathways and molecular mechanisms that drive disease severity, progression, and treatment of COVID-19.

show abstract

“…Such issues create barrier to entry for revolutionizing technologies. But these barriers are also being addressed in recent research ( [54][55][56]).…”

Section: Discussionmentioning

confidence: 99%

Promise of AI in Defi, A Literary Analysis

Sadman¹,

Rahman²,

Gupta³

2021

Preprint

View full text Add to dashboard Cite

Decentralized Finance (DeFi) is an emerging and revolutionizing field with notable uncertainties of reliability to be used on a mass scale. On the other hand, Artificial Intelligence (AI) has proved to be a crucial helping tool in numerous domains. In this study, we present a systematic review of the utility of AI in Defi in terms of impact, reliability, and security and conduct exhaustive analysis. We further conclude from our extensive literature review that we can identify possible new research opportunities in AI to bridge the gap of trust between peers and make the integration of DeFi more agile in the near future.

show abstract

Explainable AI in industry

Cited by 30 publications

References 4 publications

Deep Neural Networks and Tabular Data: A Survey

Deep Neural Networks and Tabular Data: A Survey

Metabolite, Protein, And Tissue Dysfunction Associated With COVID-19 Disease Severity

Promise of AI in Defi, A Literary Analysis

Contact Info

Product

Resources

About