Search Results for author:
Found 15 papers, 12 papers with code
DAGnosis: Localized Identification of Data Inconsistencies using Structures
Identification and appropriate handling of inconsistencies in data at deployment time is crucial to reliably use machine learning models.
Time Series Diffusion in the Frequency Domain
We explain this observation by showing that time series from these datasets tend to be more localized in the frequency domain than in the time domain, which makes them easier to model in the former case.
MatterGen: a generative model for inorganic materials design
We further introduce adapter modules to enable fine-tuning towards any given property constraints with a labeled dataset.
TRIAGE: Characterizing and auditing training data for improved regression
Data quality is crucial for robust machine learning algorithms, with the recent interest in data-centric AI emphasizing the importance of training data characterization.
Robust multimodal models have outlier features and encode more concepts
In this work, we bridge this gap by probing the representation spaces of 12 robust multimodal models with various backbones (ResNets and ViTs) and pretraining sets (OpenAI, LAION-400M, LAION-2B, YFCC15M, CC12M and DataComp).
Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance
Through this rigorous formalism, we derive (1) two metrics to measure the robustness of any interpretability method with respect to the model symmetry group; (2) theoretical robustness guarantees for some popular interpretability methods and (3) a systematic approach to increase the invariance of any interpretability method with respect to a symmetry group.
TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization
In this work, we introduce Tabular Neural Gradient Orthogonalization and Specialization (TANGOS), a novel framework for regularization in the tabular setting built on latent unit attributions.
Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data
High model performance, on average, can hide that models may systematically underperform on subgroups of the data.
Concept Activation Regions: A Generalized Framework For Concept-Based Explanations
We further demonstrate empirically that CARs offer (1) more accurate descriptions of how concepts are scattered in the DNN's latent space; (2) global explanations that are closer to human concept annotations and (3) concept-based feature importance that meaningfully relate concepts with each other.
Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability
This allows us to evaluate treatment effect estimators along a new and important dimension that has been overlooked in previous work: We construct a benchmarking environment to empirically investigate the ability of personalized treatment effect models to identify predictive covariates -- covariates that determine differential responses to treatment.
Label-Free Explainability for Unsupervised Models
Unsupervised black-box models are challenging to interpret.
Data-SUITE: Data-centric identification of in-distribution incongruous examples
These estimators can be used to evaluate the congruence of test instances with respect to the training set, to answer two practically useful questions: (1) which test instances will be reliably predicted by a model trained with the training instances?
Explaining Latent Representations with a Corpus of Examples
SimplEx uses the corpus to improve the user's understanding of the latent space with post-hoc explanations answering two questions: (1) Which corpus examples explain the prediction issued for a given test example?
Explaining Time Series Predictions with Dynamic Masks
How can we explain the predictions of a machine learning model?
Learning outside the Black-Box: The pursuit of interpretable models
Machine Learning has proved its ability to produce accurate models but the deployment of these models outside the machine learning community has been hindered by the difficulties of interpreting these models.
