Publications
Publications
Show Results For
- All HBS Web
(67)
- Faculty Publications (21)
Page 1 of 21
Results →
- 2023
- Article
M4: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities, and Models
By: Himabindu Lakkaraju, Xuhong Li, Mengnan Du, Jiamin Chen, Yekun Chai and Haoyi Xiong
While Explainable Artificial Intelligence (XAI) techniques have been widely studied to explain predictions made by deep neural networks, the way to evaluate the faithfulness of explanation results remains challenging, due to the heterogeneity of explanations for... View Details
Keywords: AI and Machine Learning
- September 2023 (Revised April 2024)
- Case
Atomwise: Strategic Opportunities in AI for Pharma
By: Satish Tadikonda
Abraham Heifets and his co-founder, Izhar Wallach, had founded Atomwise to develop i) an AI engine to transform drug discovery by creating better medicines faster, and ii) a machine learning-based discovery engine that combined the power of convolutional neural... View Details
- July 2023 (Revised July 2023)
- Background Note
Generative AI Value Chain
By: Andy Wu and Matt Higgins
Generative AI refers to a type of artificial intelligence (AI) that can create new content (e.g., text, image, or audio) in response to a prompt from a user. ChatGPT, Bard, and Claude are examples of text generating AIs, and DALL-E, Midjourney, and Stable Diffusion are... View Details
- 2023
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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)
- 2020
- Working Paper
Machine Learning for Pattern Discovery in Management Research
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
- 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
- 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
- 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