Alert button
Picture for Sahil Verma

Sahil Verma

Alert button

Effective Backdoor Mitigation Depends on the Pre-training Objective

Add code
Bookmark button
Alert button
Dec 05, 2023
Sahil Verma, Gantavya Bhatt, Avi Schwarzschild, Soumye Singhal, Arnav Mohanty Das, Chirag Shah, John P Dickerson, Jeff Bilmes

Viaarxiv icon

Unveiling the Power of Self-Attention for Shipping Cost Prediction: The Rate Card Transformer

Add code
Bookmark button
Alert button
Nov 20, 2023
P Aditya Sreekar, Sahil Verma, Varun Madhavan, Abhishek Persad

Viaarxiv icon

RecRec: Algorithmic Recourse for Recommender Systems

Add code
Bookmark button
Alert button
Aug 28, 2023
Sahil Verma, Ashudeep Singh, Varich Boonsanong, John P. Dickerson, Chirag Shah

Figure 1 for RecRec: Algorithmic Recourse for Recommender Systems
Figure 2 for RecRec: Algorithmic Recourse for Recommender Systems
Figure 3 for RecRec: Algorithmic Recourse for Recommender Systems
Figure 4 for RecRec: Algorithmic Recourse for Recommender Systems
Viaarxiv icon

RecXplainer: Post-Hoc Attribute-Based Explanations for Recommender Systems

Add code
Bookmark button
Alert button
Nov 27, 2022
Sahil Verma, Anurag Beniwal, Narayanan Sadagopan, Arjun Seshadri

Figure 1 for RecXplainer: Post-Hoc Attribute-Based Explanations for Recommender Systems
Figure 2 for RecXplainer: Post-Hoc Attribute-Based Explanations for Recommender Systems
Figure 3 for RecXplainer: Post-Hoc Attribute-Based Explanations for Recommender Systems
Figure 4 for RecXplainer: Post-Hoc Attribute-Based Explanations for Recommender Systems
Viaarxiv icon

BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence

Add code
Bookmark button
Alert button
Jul 12, 2022
Isha Hameed, Samuel Sharpe, Daniel Barcklow, Justin Au-Yeung, Sahil Verma, Jocelyn Huang, Brian Barr, C. Bayan Bruss

Figure 1 for BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence
Figure 2 for BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence
Figure 3 for BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence
Figure 4 for BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence
Viaarxiv icon

Pitfalls of Explainable ML: An Industry Perspective

Add code
Bookmark button
Alert button
Jun 14, 2021
Sahil Verma, Aditya Lahiri, John P. Dickerson, Su-In Lee

Viaarxiv icon

Counterfactual Explanations for Machine Learning: Challenges Revisited

Add code
Bookmark button
Alert button
Jun 14, 2021
Sahil Verma, John Dickerson, Keegan Hines

Figure 1 for Counterfactual Explanations for Machine Learning: Challenges Revisited
Viaarxiv icon

Amortized Generation of Sequential Counterfactual Explanations for Black-box Models

Add code
Bookmark button
Alert button
Jun 07, 2021
Sahil Verma, Keegan Hines, John P. Dickerson

Figure 1 for Amortized Generation of Sequential Counterfactual Explanations for Black-box Models
Figure 2 for Amortized Generation of Sequential Counterfactual Explanations for Black-box Models
Figure 3 for Amortized Generation of Sequential Counterfactual Explanations for Black-box Models
Figure 4 for Amortized Generation of Sequential Counterfactual Explanations for Black-box Models
Viaarxiv icon

Removing biased data to improve fairness and accuracy

Add code
Bookmark button
Alert button
Feb 05, 2021
Sahil Verma, Michael Ernst, Rene Just

Figure 1 for Removing biased data to improve fairness and accuracy
Figure 2 for Removing biased data to improve fairness and accuracy
Figure 3 for Removing biased data to improve fairness and accuracy
Figure 4 for Removing biased data to improve fairness and accuracy
Viaarxiv icon

ShapeFlow: Dynamic Shape Interpreter for TensorFlow

Add code
Bookmark button
Alert button
Nov 26, 2020
Sahil Verma, Zhendong Su

Figure 1 for ShapeFlow: Dynamic Shape Interpreter for TensorFlow
Figure 2 for ShapeFlow: Dynamic Shape Interpreter for TensorFlow
Figure 3 for ShapeFlow: Dynamic Shape Interpreter for TensorFlow
Figure 4 for ShapeFlow: Dynamic Shape Interpreter for TensorFlow
Viaarxiv icon