Skip to Main Content
HBS Home
  • About
  • Academic Programs
  • Alumni
  • Faculty & Research
  • Baker Library
  • Giving
  • Harvard Business Review
  • Initiatives
  • News
  • Recruit
  • Map / Directions
Faculty & Research
  • Faculty
  • Research
  • Featured Topics
  • Academic Units
  • …→
  • Harvard Business School→
  • Faculty & Research→
  • Research
    • Research
    • Publications
    • Global Research Centers
    • Case Development
    • Initiatives & Projects
    • Research Services
    • Seminars & Conferences
    →
  • Publications→

Publications

Publications

Filter Results : (18) Arrow Down
Filter Results : (18) Arrow Down Arrow Up

Show Results For

  • All HBS Web  (69)
    • Faculty Publications  (18)

    Show Results For

    • All HBS Web  (69)
      • Faculty Publications  (18)

      Graph Neural Networks Remove Graph Neural Networks →

      Page 1 of 18 Results

      Are you looking for?

      → Search All HBS Web
      • 2022
      • Article

      Efficiently Training Low-Curvature Neural Networks

      By: Suraj Srinivas, Kyle Matoba, Himabindu Lakkaraju and Francois Fleuret
      Standard deep neural networks often have excess non-linearity, making them susceptible to issues such as low adversarial robustness and gradient instability. Common methods to address these downstream issues, such as adversarial training, are expensive and often...  View Details
      Keywords: AI and Machine Learning
      Citation
      Read Now
      Related
      Srinivas, Suraj, Kyle Matoba, Himabindu Lakkaraju, and Francois Fleuret. "Efficiently Training Low-Curvature Neural Networks." Advances in Neural Information Processing Systems (NeurIPS) (2022).
      • 2022
      • Article

      Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods.

      By: Chirag Agarwal, Marinka Zitnik and Himabindu Lakkaraju
      As Graph Neural Networks (GNNs) are increasingly employed in real-world applications, it becomes critical to ensure that the stakeholders understand the rationale behind their predictions. While several GNN explanation methods have been proposed recently, there has...  View Details
      Keywords: Graph Neural Networks; Explanation Methods; Mathematical Methods; Framework; Theory; Analysis
      Citation
      Read Now
      Related
      Agarwal, Chirag, Marinka Zitnik, and Himabindu Lakkaraju. "Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods." Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS) 25th (2022).
      • Article

      Pattern Detection in the Activation Space for Identifying Synthesized Content

      By: Celia Cintas, Skyler Speakman, Girmaw Abebe Tadesse, Victor Akinwande, Edward McFowland III and Komminist Weldemariam
      Generative Adversarial Networks (GANs) have recently achieved unprecedented success in photo-realistic image synthesis from low-dimensional random noise. The ability to synthesize high-quality content at a large scale brings potential risks as the generated samples may...  View Details
      Keywords: Subset Scanning; Generative Models; Synthetic Content Detection
      Citation
      Register to Read
      Related
      Cintas, Celia, Skyler Speakman, Girmaw Abebe Tadesse, Victor Akinwande, Edward McFowland III, and Komminist Weldemariam. "Pattern Detection in the Activation Space for Identifying Synthesized Content." Pattern Recognition Letters 153 (January 2022): 207–213.
      • September 15, 2021
      • Article

      Improving Deconvolution Methods in Biology Through Open Innovation Competitions: An Application to the Connectivity Map

      By: Andrea Blasco, Ted Natoli, Michael G. Endres, Rinat A. Sergeev, Steven Randazzo, Jin Hyun Paik, N.J. Maximilian Macaluso, Rajiv Narayan, Xiaodong Lu, David Peck, Karim R. Lakhani and Aravind Subramanian
      A recurring problem in biomedical research is how to isolate signals of distinct populations (cell types, tissues, and genes) from composite measures obtained by a single analyte or sensor. Existing computational deconvolution approaches work well in many specific...  View Details
      Keywords: Deconvolution; Methods; Open Innovation Competition; Genomics; Research; Innovation and Invention
      Citation
      Find at Harvard
      Read Now
      Related
      Blasco, Andrea, Ted Natoli, Michael G. Endres, Rinat A. Sergeev, Steven Randazzo, Jin Hyun Paik, N.J. Maximilian Macaluso, Rajiv Narayan, Xiaodong Lu, David Peck, Karim R. Lakhani, and Aravind Subramanian. "Improving Deconvolution Methods in Biology Through Open Innovation Competitions: An Application to the Connectivity Map." Bioinformatics 37, no. 18 (September 15, 2021).
      • 2021
      • Working Paper

      Deep Learning for Two-Sided Matching

      By: Sai Srivatsa Ravindranatha, Zhe Feng, Shira Li, Jonathan Ma, Scott Duke Kominers and David Parkes
      We initiate the use of a multi-layer neural network to model two-sided matching and to explore the design space between strategy-proofness and stability. It is well known that both properties cannot be achieved simultaneously but the efficient frontier in this design...  View Details
      Keywords: Strategy-proofness; Deep Learning; Two-Sided Platforms; Marketplace Matching; Balance and Stability
      Citation
      Read Now
      Related
      Srivatsa Ravindranatha, Sai, Zhe Feng, Shira Li, Jonathan Ma, Scott Duke Kominers, and David Parkes. "Deep Learning for Two-Sided Matching." Working Paper, July 2021.
      • 2021
      • Chapter

      Towards a Unified Framework for Fair and Stable Graph Representation Learning

      By: Chirag Agarwal, Himabindu Lakkaraju and Marinka Zitnik
      As the representations output by Graph Neural Networks (GNNs) are increasingly employed in real-world applications, it becomes important to ensure that these representations are fair and stable. In this work, we establish a key connection between counterfactual...  View Details
      Keywords: Graph Neural Networks; AI and Machine Learning; Prejudice and Bias
      Citation
      Read Now
      Related
      Agarwal, Chirag, Himabindu Lakkaraju, and Marinka Zitnik. "Towards a Unified Framework for Fair and Stable Graph Representation Learning." In Proceedings of the 37th Conference on Uncertainty in Artificial Intelligence, edited by Cassio de Campos and Marloes H. Maathuis, 2114–2124. AUAI Press, 2021.
      • 2021
      • Working Paper

      First Law of Motion: Influencer Video Advertising on TikTok

      By: Jeremy Yang, Juanjuan Zhang and Yuhan Zhang
      This paper engineers an intuitive feature that is predictive of the causal effect of influencer video advertising on product sales. We propose the concept of m-score, a summary statistic that captures the extent to which a product is advertised in the most engaging...  View Details
      Keywords: Influencer Advertising; Video Advertising; Computer Vision; Machine Learning; Advertising; Online Technology
      Citation
      SSRN
      Related
      Yang, Jeremy, Juanjuan Zhang, and Yuhan Zhang. "First Law of Motion: Influencer Video Advertising on TikTok." Working Paper, March 2021.
      • January 2021
      • Article

      Machine Learning for Pattern Discovery in Management Research

      By: Prithwiraj Choudhury, Ryan Allen and Michael G. Endres
      Supervised machine learning (ML) methods are a powerful toolkit for discovering robust patterns in quantitative data. The patterns identified by ML could be used for exploratory inductive or abductive research, or for post-hoc analysis of regression results to detect...  View Details
      Keywords: Machine Learning; Supervised Machine Learning; Induction; Abduction; Exploratory Data Analysis; Pattern Discovery; Decision Trees; Random Forests; Neural Networks; ROC Curve; Confusion Matrix; Partial Dependence Plots; AI and Machine Learning
      Citation
      Find at Harvard
      Read Now
      Related
      Choudhury, Prithwiraj, Ryan Allen, and Michael G. Endres. "Machine Learning for Pattern Discovery in Management Research." Strategic Management Journal 42, no. 1 (January 2021): 30–57.
      • Article

      Incorporating Interpretable Output Constraints in Bayesian Neural Networks

      By: Wanqian Yang, Lars Lorch, Moritz Graule, Himabindu Lakkaraju and Finale Doshi-Velez
      Domains where supervised models are deployed often come with task-specific constraints, such as prior expert knowledge on the ground-truth function, or desiderata like safety and fairness. We introduce a novel probabilistic framework for reasoning with such constraints...  View Details
      Citation
      Read Now
      Related
      Yang, Wanqian, Lars Lorch, Moritz Graule, Himabindu Lakkaraju, and Finale Doshi-Velez. "Incorporating Interpretable Output Constraints in Bayesian Neural Networks." Advances in Neural Information Processing Systems (NeurIPS) 33 (2020).
      • Article

      Detecting Adversarial Attacks via Subset Scanning of Autoencoder Activations and Reconstruction Error

      By: Celia Cintas, Skyler Speakman, Victor Akinwande, William Ogallo, Komminist Weldemariam, Srihari Sridharan and Edward McFowland III
      Reliably detecting attacks in a given set of inputs is of high practical relevance because of the vulnerability of neural networks to adversarial examples. These altered inputs create a security risk in applications with real-world consequences, such as self-driving...  View Details
      Keywords: Autoencoder Networks; Pattern Detection; Subset Scanning; Computer Vision; Statistical Methods And Machine Learning; Machine Learning; Deep Learning; Data Mining; Big Data; Large-scale Systems; Mathematical Methods; Analytics and Data Science
      Citation
      Read Now
      Related
      Cintas, Celia, Skyler Speakman, Victor Akinwande, William Ogallo, Komminist Weldemariam, Srihari Sridharan, and Edward McFowland III. "Detecting Adversarial Attacks via Subset Scanning of Autoencoder Activations and Reconstruction Error." Proceedings of the International Joint Conference on Artificial Intelligence 29th (2020).
      • Article

      Machine Learning Approaches to Facial and Text Analysis: Discovering CEO Oral Communication Styles

      By: Prithwiraj Choudhury, Dan Wang, Natalie A. Carlson and Tarun Khanna
      We demonstrate how a novel synthesis of three methods—(1) unsupervised topic modeling of text data to generate new measures of textual variance, (2) sentiment analysis of text data, and (3) supervised ML coding of facial images with a cutting-edge convolutional neural...  View Details
      Keywords: CEOs; Communication Style; Machine Learning; Spoken Communication; Nonverbal Communication; Personal Characteristics; Analysis; Performance
      Citation
      Find at Harvard
      Related
      Choudhury, Prithwiraj, Dan Wang, Natalie A. Carlson, and Tarun Khanna. "Machine Learning Approaches to Facial and Text Analysis: Discovering CEO Oral Communication Styles." Strategic Management Journal 40, no. 11 (November 2019): 1705–1732.
      • December 2018
      • Case

      Choosy

      By: Jeffrey J. Bussgang and Julia Kelley
      Founded in 2017, Choosy is a data-driven fashion startup that uses algorithms to identify styles trending on social media. After manufacturing similar items using a China-based supply chain, Choosy sells them to consumers through its website and social media pages....  View Details
      Keywords: Artificial Intelligence; Algorithms; Machine Learning; Neural Networks; Instagram; Influencer; Fast Fashion; Design; Customer Satisfaction; Customer Focus and Relationships; Decision Making; Cost vs Benefits; Innovation and Invention; Brands and Branding; Product Positioning; Demand and Consumers; Supply Chain; Production; Logistics; Business Model; Expansion; Internet and the Web; Mobile and Wireless Technology; Digital Platforms; Social Media; Technology Industry; Fashion Industry; North and Central America; United States; New York (state, US); New York (city, NY)
      Citation
      Educators
      Purchase
      Related
      Bussgang, Jeffrey J., and Julia Kelley. "Choosy." Harvard Business School Case 819-054, December 2018.
      • 2020
      • Working Paper

      Machine Learning for Pattern Discovery in Management Research

      By: Prithwiraj Choudhury
      Supervised machine learning (ML) methods are a powerful toolkit for discovering robust patterns in quantitative data. The patterns identified by ML could be used as an observation for further inductive or abductive research, but should not be treated as the result of a...  View Details
      Keywords: Machine Learning; Theory Building; Induction; Decision Trees; Random Forests; K-nearest Neighbors; Neural Network; P-hacking; Analytics and Data Science; Analysis
      Citation
      SSRN
      Related
      Choudhury, Prithwiraj, Ryan Allen, and Michael G. Endres. "Machine Learning for Pattern Discovery in Management Research." Harvard Business School Working Paper, No. 19-032, September 2018. (Revised June 2020.)
      • 2018
      • Working Paper

      Some Facts of High-Tech Patenting

      By: Michael Webb, Nick Short, Nicholas Bloom and Josh Lerner
      Patenting in software, cloud computing, and artificial intelligence has grown rapidly in recent years. Such patents are acquired primarily by large U.S. technology firms such as IBM, Microsoft, Google, and HP, as well as by Japanese multinationals such as Sony, Canon,...  View Details
      Keywords: Patents; Applications and Software; Technological Innovation; United States
      Citation
      SSRN
      Read Now
      Related
      Webb, Michael, Nick Short, Nicholas Bloom, and Josh Lerner. "Some Facts of High-Tech Patenting." Harvard Business School Working Paper, No. 19-014, August 2018. (NBER Working Paper Series, No. 24793, July 2018.)
      • 2019
      • Working Paper

      Machine Learning Approaches to Facial and Text Analysis: Discovering CEO Oral Communication Styles

      By: Prithwiraj Choudhury, Dan Wang, Natalie A. Carlson and Tarun Khanna
      We demonstrate how a novel synthesis of three methods—(1) unsupervised topic modeling of text data to generate new measures of textual variance, (2) sentiment analysis of text data, and (3) supervised ML coding of facial images with a cutting-edge convolutional neural...  View Details
      Keywords: Spoken Communication; Business History; Analytics and Data Science; Finance; Performance
      Citation
      Read Now
      Related
      Choudhury, Prithwiraj, Dan Wang, Natalie A. Carlson, and Tarun Khanna. "Machine Learning Approaches to Facial and Text Analysis: Discovering CEO Oral Communication Styles." Harvard Business School Working Paper, No. 18-064, January 2018. (Revised May 2019.)
      • 2015
      • Article

      Scalable Detection of Anomalous Patterns With Connectivity Constraints

      By: Skyler Speakman, Edward McFowland III and Daniel B. Neill
      We present GraphScan, a novel method for detecting arbitrarily shaped connected clusters in graph or network data. Given a graph structure, data observed at each node, and a score function defining the anomalousness of a set of nodes, GraphScan can efficiently and...  View Details
      Keywords: Biosurveillance; Event Detection; Graph Mining; Scan Statistics; Spatial Scan Statistic
      Citation
      Find at Harvard
      Purchase
      Related
      Speakman, Skyler, Edward McFowland III, and Daniel B. Neill. "Scalable Detection of Anomalous Patterns With Connectivity Constraints." Journal of Computational and Graphical Statistics 24, no. 4 (2015): 1014–1033.
      • 2011
      • Article

      Scalable Detection of Anomalous Patterns With Connectivity Constraints

      By: Skyler Speakman, Edward McFowland III and Daniel B. Neill
      We present GraphScan, a novel method for detecting arbitrarily shaped connected clusters in graph or network data. Given a graph structure, data observed at each node, and a score function defining the anomalousness of a set of nodes, GraphScan can efficiently and...  View Details
      Keywords: Biosurveillance; Event Detection; Graph Mining; Scan Statistics; Spatial Scan Statistic
      Citation
      Related
      Speakman, Skyler, Edward McFowland III, and Daniel B. Neill. "Scalable Detection of Anomalous Patterns With Connectivity Constraints." Emerging Health Threats Journal 4 (2011): 11121.
      • Forthcoming
      • Article

      Evaluating Explainability for Graph Neural Networks

      By: Chirag Agarwal, Owen Queen, Himabindu Lakkaraju and Marinka Zitnik
      As explanations are increasingly used to understand the behavior of graph neural networks (GNNs), evaluating the quality and reliability of GNN explanations is crucial. However, assessing the quality of GNN explanations is challenging as existing graph datasets have no...  View Details
      Keywords: Analytics and Data Science
      Citation
      Read Now
      Related
      Agarwal, Chirag, Owen Queen, Himabindu Lakkaraju, and Marinka Zitnik. "Evaluating Explainability for Graph Neural Networks." Scientific Data (forthcoming).
      • 1

      Are you looking for?

      → Search All HBS Web
      ǁ
      Campus Map
      Harvard Business School
      Soldiers Field
      Boston, MA 02163
      →Map & Directions
      →More Contact Information
      • Make a Gift
      • Site Map
      • Jobs
      • Harvard University
      • Trademarks
      • Policies
      • Accessibility
      • Digital Accessibility
      Copyright © President & Fellows of Harvard College