Model Prediction

Model prediction research focuses on improving the accuracy and interpretability of machine learning models across diverse applications, from climate science to medical diagnosis. Current efforts concentrate on enhancing explainability through techniques like counterfactual analysis and feature attribution, often employing deep learning architectures (e.g., CNNs) alongside simpler, more interpretable models. This work is crucial for building trust in model predictions, improving decision-making in high-stakes domains, and fostering scientific understanding by bridging the gap between model outputs and human comprehension.

Papers

July 12, 2023

Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes
Connor Toups, Rishi Bommasani, Kathleen A. Creel, Sarah H. Bana, Dan Jurafsky, Percy Liang
Machine Learning Multiple Outcome Model Prediction Single Model Societal Impact Ecosystem Level Analysis

June 24, 2023

Are Good Explainers Secretly Human-in-the-Loop Active Learners?
Emma Thuong Nguyen, Abhishek Ghose
Active Learning Explainable AI Human in the Loop Model Prediction Quality Explanation Active Learner

May 26, 2023

Theoretical and Practical Perspectives on what Influence Functions Do
Andrea Schioppa, Katja Filippova, Ivan Titov, Polina Zablotskaia
Human Prediction Large Scale Theoretical Analysis Influence Function Model Prediction

May 24, 2023

Annotation Imputation to Individualize Predictions: Initial Studies on Distribution Dynamics and Model Predictions
London Lowmanstone, Ruyuan Wan, Risako Owan, Jaehyung Kim, Dongyeop Kang
Imputation Algorithm Imputation Method Initial Study Model Prediction Data Annotation Annotation Budget Personalized Prediction Dynamic Distribution

May 23, 2023

What Else Do I Need to Know? The Effect of Background Information on Users' Reliance on QA Systems
Navita Goyal, Eleftheria Briakou, Amanda Liu, Connor Baumler, Claire Bonial, Jeffrey Micher, Clare R. Voss, Marine Carpuat, Hal Daumé
Mixed Effect User Base Conditional Reasoning Background Knowledge Model Prediction QA System

May 12, 2023

Asymmetric feature interaction for interpreting model predictions
Xiaolei Lu, Jianghong Ma, Haode Zhang
Feature Interaction Model Prediction

February 4, 2023

How Many and Which Training Points Would Need to be Removed to Flip this Prediction?
Jinghan Yang, Sarthak Jain, Byron C. Wallace
Native Robustness Training Data Human Prediction Model Prediction Convex Machine Learning Training Point

January 25, 2023

Backward Compatibility During Data Updates by Weight Interpolation
Raphael Schumann, Elman Mansimov, Yi-An Lai, Nikolaos Pappas, Xibin Gao, Yi Zhang
Training Data Model Prediction Incremental Data Software Defect Weight Interpolation

January 17, 2023

Outlier-Based Domain of Applicability Identification for Materials Property Prediction Models
Gihan Panapitiya, Emily Saldanha
Machine Learning Model Feature Space Internet Service Domain Prediction Accuracy Model Prediction Material Property Prediction Applicability Study

December 16, 2022

Do Not Trust a Model Because It is Confident: Uncovering and Characterizing Unknown Unknowns to Student Success Predictors in Online-Based Learning
Roberta Galici, Tanja Käser, Gianni Fenu, Mirko Marras
Full Model Online Learning Model Prediction Student Performance Prediction Unknown Unknown

December 13, 2022

Localized Latent Updates for Fine-Tuning Vision-Language Models
Moritz Ibing, Isaak Lim, Leif Kobbelt
Vision Language Model Fine Tuning Shot Learning Pre Trained Vision Language Model Model Prediction Generalization Capability

December 8, 2022

Mitigating Memorization of Noisy Labels by Clipping the Model Prediction
Hongxin Wei, Huiping Zhuang, Renchunzi Xie, Lei Feng, Gang Niu, Bo An, Yixuan Li
Noisy Label Cross Entropy Model Prediction Robust Loss Robust Loss Function Verbatim Memorization

October 17, 2022

RbX: Region-based explanations of prediction models
Ismael Lemhadri, Harrison H. Li, Trevor Hastie
Human Prediction Line by Line Explanation Black Box Local Explanation Prediction Model Model Prediction

September 28, 2022

Variance Tolerance Factors For Interpreting ALL Neural Networks
Sichao Li, Amanda Barnard
Neural Network Black Box Model Feature Importance Influence Function Model Prediction Variance Tolerance Factor

August 26, 2022

GHN-Q: Parameter Prediction for Unseen Quantized Convolutional Architectures via Graph Hypernetworks
Stone Yun, Alexander Wong
Convolutional Neural Network Architecture Model Prediction Graph Hypernetworks Quantization Robust Parameter

February 28, 2022

Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten
Quoc Phong Nguyen, Ryutaro Oikawa, Dinil Mon Divakaran, Mun Choon Chan, Bryan Kian Hsiang Low
Machine Learning Training Data Machine Learning Model Machine Unlearning Markov Chain Monte Carlo Model Prediction Adversarial Data

December 9, 2021

Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers
Zunlei Feng, Jiacong Hu, Sai Wu, Xiaotian Yu, Jie Song, Mingli Song
Convolutional Neural Network Model Prediction Aggregated Gradient CNN Classifier

November 24, 2021

ModelPred: A Framework for Predicting Trained Model from Training Data
Yingyan Zeng, Jiachen T. Wang, Si Chen, Hoang Anh Just, Ran Jin, Ruoxi Jia
Machine Learning Training Data Full Model New Framework Model Prediction Set Function

November 13, 2021

Image Classification with Consistent Supporting Evidence
Peiqi Wang, Ruizhi Liao, Daniel Moyer, Seth Berkowitz, Steven Horng, Polina Golland
Machine Learning Model Image Classification Strong Consistency Evidence Piece Model Prediction Consistent Model

November 11, 2021

The Science of Rejection: A Research Area for Human Computation
Burcu Sayin, Jie Yang, Andrea Passerini, Fabio Casati
Machine Learning Science Journalism Model Prediction Manual Effort Risky Prompt Rejection Research Topic