Amirata Ghorbani

Mark Mazumder, Colby Banbury, Xiaozhe Yao et al.

Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithfulness of the underlying problems. Neglecting the fundamental importance of data has given rise to inaccuracy, bias, and fragility in real-world applications, and research is hindered by saturation across existing dataset benchmarks. In response, we present DataPerf, a community-led benchmark suite for evaluating ML datasets and data-centric algorithms. We aim to foster innovation in data-centric AI through competition, comparability, and reproducibility. We enable the ML community to iterate on datasets, instead of just architectures, and we provide an open, online platform with multiple rounds of challenges to support this iterative development. The first iteration of DataPerf contains five benchmarks covering a wide spectrum of data-centric techniques, tasks, and modalities in vision, speech, acquisition, debugging, and diffusion prompting, and we support hosting new contributed benchmarks from the community. The benchmarks, online evaluation platform, and baseline implementations are open source, and the MLCommons Association will maintain DataPerf to ensure long-term benefits to academia and industry.

Amirata Ghorbani, Dina Berenbaum, Maor Ivgi et al.

Interpretability is becoming an active research topic as machine learning (ML) models are more widely used to make critical decisions. Tabular data is one of the most commonly used modes of data in diverse applications such as healthcare and finance. Much of the existing interpretability methods used for tabular data only report feature-importance scores -- either locally (per example) or globally (per model) -- but they do not provide interpretation or visualization of how the features interact. We address this limitation by introducing Feature Vectors, a new global interpretability method designed for tabular datasets. In addition to providing feature-importance, Feature Vectors discovers the inherent semantic relationship among features via an intuitive feature visualization technique. Our systematic experiments demonstrate the empirical utility of this new method by applying it to several real-world datasets. We further provide an easy-to-use Python package for Feature Vectors.

Amirata Ghorbani, James Zou, Andre Esteva

Annotating the right set of data amongst all available data points is a key challenge in many machine learning applications. Batch active learning is a popular approach to address this, in which batches of unlabeled data points are selected for annotation, while an underlying learning algorithm gets subsequently updated. Increasingly larger batches are particularly appealing in settings where data can be annotated in parallel, and model training is computationally expensive. A key challenge here is scale - typical active learning methods rely on diversity techniques, which select a diverse set of data points to annotate, from an unlabeled pool. In this work, we introduce Active Data Shapley (ADS) -- a filtering layer for batch active learning that significantly increases the efficiency of active learning by pre-selecting, using a linear time computation, the highest-value points from an unlabeled dataset. Using the notion of the Shapley value of data, our method estimates the value of unlabeled data points with regards to the prediction task at hand. We show that ADS is particularly effective when the pool of unlabeled data exhibits real-world caveats: noise, heterogeneity, and domain shift. We run experiments demonstrating that when ADS is used to pre-select the highest-ranking portion of an unlabeled dataset, the efficiency of state-of-the-art batch active learning methods increases by an average factor of 6x, while preserving performance effectiveness.

Ramin Ansari, Amirata Ghorbani

Deep learning based methods have been widely applied to predict various kinds of molecular properties in the pharmaceutical industry with increasingly more success. Solvation free energy is an important index in the field of organic synthesis, medicinal chemistry, drug delivery, and biological processes. However, accurate solvation free energy determination is a time-consuming experimental process. Furthermore, it could be useful to assess solvation free energy in the absence of a physical sample. In this study, we propose two novel models for the problem of free solvation energy predictions, based on the Graph Neural Network (GNN) architectures: Message Passing Neural Network (MPNN) and Graph Attention Network (GAT). GNNs are capable of summarizing the predictive information of a molecule as low-dimensional features directly from its graph structure without relying on an extensive amount of intra-molecular descriptors. As a result, these models are capable of making accurate predictions of the molecular properties without the time consuming process of running an experiment on each molecule. We show that our proposed models outperform all quantum mechanical and molecular dynamics methods in addition to existing alternative machine learning based approaches in the task of solvation free energy prediction. We believe such promising predictive models will be applicable to enhancing the efficiency of the screening of drug molecules and be a useful tool to promote the development of molecular pharmaceutics.

Siyi Tang, Amirata Ghorbani, Rikiya Yamashita et al.

The reliability of machine learning models can be compromised when trained on low quality data. Many large-scale medical imaging datasets contain low quality labels extracted from sources such as medical reports. Moreover, images within a dataset may have heterogeneous quality due to artifacts and biases arising from equipment or measurement errors. Therefore, algorithms that can automatically identify low quality data are highly desired. In this study, we used data Shapley, a data valuation metric, to quantify the value of training data to the performance of a pneumonia detection algorithm in a large chest X-ray dataset. We characterized the effectiveness of data Shapley in identifying low quality versus valuable data for pneumonia detection. We found that removing training data with high Shapley values decreased the pneumonia detection performance, whereas removing data with low Shapley values improved the model performance. Furthermore, there were more mislabeled examples in low Shapley value data and more true pneumonia cases in high Shapley value data. Our results suggest that low Shapley value indicates mislabeled or poor quality images, whereas high Shapley value indicates data that are valuable for pneumonia detection. Our method can serve as a framework for using data Shapley to denoise large-scale medical imaging datasets.

Linjun Zhang, Zhun Deng, Kenji Kawaguchi et al.

Mixup is a popular data augmentation technique based on taking convex combinations of pairs of examples and their labels. This simple technique has been shown to substantially improve both the robustness and the generalization of the trained model. However, it is not well-understood why such improvement occurs. In this paper, we provide theoretical analysis to demonstrate how using Mixup in training helps model robustness and generalization. For robustness, we show that minimizing the Mixup loss corresponds to approximately minimizing an upper bound of the adversarial loss. This explains why models obtained by Mixup training exhibits robustness to several kinds of adversarial attacks such as Fast Gradient Sign Method (FGSM). For generalization, we prove that Mixup augmentation corresponds to a specific type of data-adaptive regularization which reduces overfitting. Our analysis provides new insights and a framework to understand Mixup.

Zhun Deng, Linjun Zhang, Amirata Ghorbani et al.

Data augmentation by incorporating cheap unlabeled data from multiple domains is a powerful way to improve prediction especially when there is limited labeled data. In this work, we investigate how adversarial robustness can be enhanced by leveraging out-of-domain unlabeled data. We demonstrate that for broad classes of distributions and classifiers, there exists a sample complexity gap between standard and robust classification. We quantify to what degree this gap can be bridged via leveraging unlabeled samples from a shifted domain by providing both upper and lower bounds. Moreover, we show settings where we achieve better adversarial robustness when the unlabeled data come from a shifted domain rather than the same domain as the labeled data. We also investigate how to leverage out-of-domain data when some structural information, such as sparsity, is shared between labeled and unlabeled domains. Experimentally, we augment two object recognition datasets (CIFAR-10 and SVHN) with easy to obtain and unlabeled out-of-domain data and demonstrate substantial improvement in the model's robustness against $\ell_\infty$ adversarial attacks on the original domain.

Amirata Ghorbani, Michael P. Kim, James Zou

Shapley value is a classic notion from game theory, historically used to quantify the contributions of individuals within groups, and more recently applied to assign values to data points when training machine learning models. Despite its foundational role, a key limitation of the data Shapley framework is that it only provides valuations for points within a fixed data set. It does not account for statistical aspects of the data and does not give a way to reason about points outside the data set. To address these limitations, we propose a novel framework -- distributional Shapley -- where the value of a point is defined in the context of an underlying data distribution. We prove that distributional Shapley has several desirable statistical properties; for example, the values are stable under perturbations to the data points themselves and to the underlying data distribution. We leverage these properties to develop a new algorithm for estimating values from data, which comes with formal guarantees and runs two orders of magnitude faster than state-of-the-art algorithms for computing the (non-distributional) data Shapley values. We apply distributional Shapley to diverse data sets and demonstrate its utility in a data market setting.

Amirata Ghorbani, James Zou

We develop Neuron Shapley as a new framework to quantify the contribution of individual neurons to the prediction and performance of a deep network. By accounting for interactions across neurons, Neuron Shapley is more effective in identifying important filters compared to common approaches based on activation patterns. Interestingly, removing just 30 filters with the highest Shapley scores effectively destroys the prediction accuracy of Inception-v3 on ImageNet. Visualization of these few critical filters provides insights into how the network functions. Neuron Shapley is a flexible framework and can be applied to identify responsible neurons in many tasks. We illustrate additional applications of identifying filters that are responsible for biased prediction in facial recognition and filters that are vulnerable to adversarial attacks. Removing these filters is a quick way to repair models. Enabling all these applications is a new multi-arm bandit algorithm that we developed to efficiently estimate Neuron Shapley values.

Amirata Ghorbani, Vivek Natarajan, David Coz et al.

Despite the recent success in applying supervised deep learning to medical imaging tasks, the problem of obtaining large and diverse expert-annotated datasets required for the development of high performant models remains particularly challenging. In this work, we explore the possibility of using Generative Adverserial Networks (GAN) to synthesize clinical images with skin condition. We propose DermGAN, an adaptation of the popular Pix2Pix architecture, to create synthetic images for a pre-specified skin condition while being able to vary its size, location and the underlying skin color. We demonstrate that the generated images are of high fidelity using objective GAN evaluation metrics. In a Human Turing test, we note that the synthetic images are not only visually similar to real images, but also embody the respective skin condition in dermatologists' eyes. Finally, when using the synthetic images as a data augmentation technique for training a skin condition classifier, we observe that the model performs comparably to the baseline model overall while improving on rare but malignant conditions.

Gal Yona, Amirata Ghorbani, James Zou

A learning algorithm $A$ trained on a dataset $D$ is revealed to have poor performance on some subpopulation at test time. Where should the responsibility for this lay? It can be argued that the data is responsible, if for example training $A$ on a more representative dataset $D'$ would have improved the performance. But it can similarly be argued that $A$ itself is at fault, if training a different variant $A'$ on the same dataset $D$ would have improved performance. As ML becomes widespread and such failure cases more common, these types of questions are proving to be far from hypothetical. With this motivation in mind, in this work we provide a rigorous formulation of the joint credit assignment problem between a learning algorithm $A$ and a dataset $D$. We propose Extended Shapley as a principled framework for this problem, and experiment empirically with how it can be used to address questions of ML accountability.

Amirata Ghorbani, James Zou

As data becomes the fuel driving technological and economic growth, a fundamental challenge is how to quantify the value of data in algorithmic predictions and decisions. For example, in healthcare and consumer markets, it has been suggested that individuals should be compensated for the data that they generate, but it is not clear what is an equitable valuation for individual data. In this work, we develop a principled framework to address data valuation in the context of supervised machine learning. Given a learning algorithm trained on $n$ data points to produce a predictor, we propose data Shapley as a metric to quantify the value of each training datum to the predictor performance. Data Shapley value uniquely satisfies several natural properties of equitable data valuation. We develop Monte Carlo and gradient-based methods to efficiently estimate data Shapley values in practical settings where complex learning algorithms, including neural networks, are trained on large datasets. In addition to being equitable, extensive experiments across biomedical, image and synthetic data demonstrate that data Shapley has several other benefits: 1) it is more powerful than the popular leave-one-out or leverage score in providing insight on what data is more valuable for a given learning task; 2) low Shapley value data effectively capture outliers and corruptions; 3) high Shapley value data inform what type of new data to acquire to improve the predictor.

Amirata Ghorbani, James Wexler, James Zou et al.

Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions. Most of the current explanation methods provide explanations through feature importance scores, which identify features that are important for each individual input. However, how to systematically summarize and interpret such per sample feature importance scores itself is challenging. In this work, we propose principles and desiderata for \emph{concept} based explanation, which goes beyond per-sample features to identify higher-level human-understandable concepts that apply across the entire dataset. We develop a new algorithm, ACE, to automatically extract visual concepts. Our systematic experiments demonstrate that \alg discovers concepts that are human-meaningful, coherent and important for the neural network's predictions.

Jaime Roquero Gimenez, Amirata Ghorbani, James Zou

An important problem in machine learning and statistics is to identify features that causally affect the outcome. This is often impossible to do from purely observational data, and a natural relaxation is to identify features that are correlated with the outcome even conditioned on all other observed features. For example, we want to identify that smoking really is correlated with cancer conditioned on demographics. The knockoff procedure is a recent breakthrough in statistics that, in theory, can identify truly correlated features while guaranteeing that the false discovery is limited. The idea is to create synthetic data -- knockoffs -- that captures correlations amongst the features. However there are substantial computational and practical challenges to generating and using knockoffs. This paper makes several key advances that enable knockoff application to be more efficient and powerful. We develop an efficient algorithm to generate valid knockoffs from Bayesian Networks. Then we systematically evaluate knockoff test statistics and develop new statistics with improved power. The paper combines new mathematical guarantees with systematic experiments on real and synthetic data.

Michael P. Kim, Amirata Ghorbani, James Zou

Prediction systems are successfully deployed in applications ranging from disease diagnosis, to predicting credit worthiness, to image recognition. Even when the overall accuracy is high, these systems may exhibit systematic biases that harm specific subpopulations; such biases may arise inadvertently due to underrepresentation in the data used to train a machine-learning model, or as the result of intentional malicious discrimination. We develop a rigorous framework of *multiaccuracy* auditing and post-processing to ensure accurate predictions across *identifiable subgroups*. Our algorithm, MULTIACCURACY-BOOST, works in any setting where we have black-box access to a predictor and a relatively small set of labeled data for auditing; importantly, this black-box framework allows for improved fairness and accountability of predictions, even when the predictor is minimally transparent. We prove that MULTIACCURACY-BOOST converges efficiently and show that if the initial model is accurate on an identifiable subgroup, then the post-processed model will be also. We experimentally demonstrate the effectiveness of the approach to improve the accuracy among minority subgroups in diverse applications (image classification, finance, population health). Interestingly, MULTIACCURACY-BOOST can improve subpopulation accuracy (e.g. for "black women") even when the sensitive features (e.g. "race", "gender") are not given to the algorithm explicitly.

Amirata Ghorbani, Abubakar Abid, James Zou

In order for machine learning to be deployed and trusted in many applications, it is crucial to be able to reliably explain why the machine learning algorithm makes certain predictions. For example, if an algorithm classifies a given pathology image to be a malignant tumor, then the doctor may need to know which parts of the image led the algorithm to this classification. How to interpret black-box predictors is thus an important and active area of research. A fundamental question is: how much can we trust the interpretation itself? In this paper, we show that interpretation of deep learning predictions is extremely fragile in the following sense: two perceptively indistinguishable inputs with the same predicted label can be assigned very different interpretations. We systematically characterize the fragility of several widely-used feature-importance interpretation methods (saliency maps, relevance propagation, and DeepLIFT) on ImageNet and CIFAR-10. Our experiments show that even small random perturbation can change the feature importance and new systematic perturbations can lead to dramatically different interpretations without changing the label. We extend these results to show that interpretations based on exemplars (e.g. influence functions) are similarly fragile. Our analysis of the geometry of the Hessian matrix gives insight on why fragility could be a fundamental challenge to the current interpretation approaches.