• Publications
  • Influence
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
This work empirically demonstrates that its algorithms significantly reduce gender bias in embeddings while preserving the its useful properties such as the ability to cluster related concepts and to solve analogy tasks. Expand
Word embeddings quantify 100 years of gender and ethnic stereotypes
A framework to demonstrate how the temporal dynamics of the embedding helps to quantify changes in stereotypes and attitudes toward women and ethnic minorities in the 20th and 21st centuries in the United States is developed. Expand
Interpretation of Neural Networks is Fragile
This paper systematically characterize the fragility of several widely-used feature-importance interpretation methods (saliency maps, relevance propagation, and DeepLIFT) on ImageNet and CIFAR-10 and extends these results to show that interpretations based on exemplars (e.g. influence functions) are similarly fragile. Expand
Data Shapley: Equitable Valuation of Data for Machine Learning
This work develops a principled framework to address data valuation in the context of supervised machine learning by proposing data Shapley as a metric to quantify the value of each training datum to the predictor performance. Expand
MOPO: Model-based Offline Policy Optimization
A new model-based offline RL algorithm is proposed that applies the variance of a Lipschitz-regularized model as a penalty to the reward function, and it is found that this algorithm outperforms both standard model- based RL methods and existing state-of-the-art model-free offline RL approaches on existing offline RL benchmarks, as well as two challenging continuous control tasks. Expand
Exploring patterns enriched in a dataset with contrastive principal component analysis
This paper proposes a method, contrastive principal component analysis (cPCA), which identifies low-dimensional structures that are enriched in a dataset relative to comparison data and enables visualization of dataset-specific patterns. Expand
Concrete Autoencoders for Differentiable Feature Selection and Reconstruction
We introduce the concrete autoencoder, an end-to-end differentiable method for global feature selection, which efficiently identifies a subset of the most informative features and simultaneouslyExpand
Genome-wide analysis reveals conserved and divergent features of Notch1/RBPJ binding in human and murine T-lymphoblastic leukemia cells.
  • H. Wang, J. Zou, +10 authors J. Aster
  • Biology, Medicine
  • Proceedings of the National Academy of Sciences…
  • 6 September 2011
Notch1 regulates gene expression by associating with the DNA-binding factor RBPJ and is oncogenic in murine and human T-cell progenitors. Using ChIP-Seq, we find that in human and murineExpand
Towards Automatic Concept-based Explanations
This work proposes principles and desiderata for concept based explanation, which goes beyond per-sample features to identify higher-level human-understandable concepts that apply across the entire dataset. Expand
Making AI Forget You: Data Deletion in Machine Learning
This paper proposes two provably efficient deletion algorithms which achieve an average of over 100X improvement in deletion efficiency across 6 datasets, while producing clusters of comparable statistical quality to a canonical k-means++ baseline. Expand