253 citations · 691 across the 17 of their papers we have counts for
17 papers
Removing Spurious Correlation from Neural Network Interpretations
Milad Fotouhi, Mohammad Taha Bahadori, Oluwaseyi Feyisetan +2
The existing algorithms for identification of neurons responsible for undesired and harmful behaviors do not consider the effects of confounders such as topic of the conversation.…
Fast Training Dataset Attribution via In-Context Learning
Milad Fotouhi, Mohammad Taha Bahadori, Oluwaseyi Feyisetan +2
We investigate the use of in-context learning and prompt engineering to estimate the contributions of training data in the outputs of instruction-tuned large language models (LLMs)…
Multiply-Robust Causal Change Attribution
Victor Quintas-Martinez, Mohammad Taha Bahadori, Eduardo Santiago +3
Comparing two samples of data, we observe a change in the distribution of an outcome variable. In the presence of multiple explanatory variables, how much of the change can be expl…
End-to-End Balancing for Causal Continuous Treatment-Effect Estimation
Mohammad Taha Bahadori, Eric Tchetgen Tchetgen, David E. Heckerman
We study the problem of observational causal inference with continuous treatments in the framework of inverse propensity-score weighting. To obtain stable weights, we design a new…
Debiasing Concept-based Explanations with Causal Analysis
Mohammad Taha Bahadori, David E. Heckerman
Concept-based explanation approach is a popular model interpertability tool because it expresses the reasons for a model's predictions in terms of concepts that are meaningful for…
Discovering Invariances in Healthcare Neural Networks
Mohammad Taha Bahadori, Layne C. Price
We study the invariance characteristics of pre-trained predictive models by empirically learning transformations on the input that leave the prediction function approximately uncha…
Causal Regularization
Dominik Janzing
I argue that regularizing terms in standard regression methods not only help against overfitting finite data, but sometimes also yield better causal models in the infinite sample r…
Temporal-Clustering Invariance in Irregular Healthcare Time Series
Mohammad Taha Bahadori, Zachary Chase Lipton
Electronic records contain sequences of events, some of which take place all at once in a single visit, and others that are dispersed over multiple visits, each with a different ti…
Improving Hospital Mortality Prediction with Medical Named Entities and Multimodal Learning
Mengqi Jin, Mohammad Taha Bahadori, Aaron Colak +11
Clinical text provides essential information to estimate the acuity of a patient during hospital stays in addition to structured clinical data. In this study, we explore how clinic…
Causal Regularization
Mohammad Taha Bahadori, Krzysztof Chalupka, Edward Choi +3
In application domains such as healthcare, we want accurate predictive models that are also causally interpretable. In pursuit of such models, we propose a causal regularizer to st…
GRAM: Graph-based Attention Model for Healthcare Representation Learning
Edward Choi, Mohammad Taha Bahadori, Le Song +2
Deep learning methods exhibit promising performance for predictive modeling in healthcare, but two important challenges remain: -Data insufficiency:Often in healthcare predictive m…
Scalable Interpretable Multi-Response Regression via SEED
Mohammad Taha Bahadori, Zemin Zheng, Yan Liu +1
Sparse reduced-rank regression is an important tool to uncover meaningful dependence structure between large numbers of predictors and responses in many big data applications such…
RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism
Edward Choi, Mohammad Taha Bahadori, Joshua A. Kulas +3
Accuracy and interpretability are two dominant features of successful predictive models. Typically, a choice must be made in favor of complex black box models such as recurrent neu…
Multi-layer Representation Learning for Medical Concepts
Edward Choi, Mohammad Taha Bahadori, Elizabeth Searles +2
Learning efficient representations for concepts has been proven to be an important basis for many applications such as machine translation or document classification. Proper repres…
FLASH: Fast Bayesian Optimization for Data Analytic Pipelines
Yuyu Zhang, Mohammad Taha Bahadori, Hang Su +1
Modern data science relies on data analytic pipelines to organize interdependent computational steps. Such analytic pipelines often involve different algorithms across multiple ste…
Doctor AI: Predicting Clinical Events via Recurrent Neural Networks
Edward Choi, Mohammad Taha Bahadori, Andy Schuetz +2
Leveraging large historical data in electronic health record (EHR), we developed Doctor AI, a generic predictive model that covers observed medical conditions and medication uses.…
Sparse-GEV: Sparse Latent Space Model for Multivariate Extreme Value Time Serie Modeling
Yan Liu, Taha Bahadori, Hongfei Li
In many applications of time series models, such as climate analysis and social media analysis, we are often interested in extreme events, such as heatwave, wind gust, and burst of…