The field of Few-Shot Learning (FSL), or learning from very few (typically $1$ or $5$) examples per novel class (unseen during training), has received a lot of attention and significant performance advances in the recent literature. While number of techniques have been proposed for FSL, several factors have emerged as most important for FSL performance, awarding SOTA even to the simplest of techniques. These are: the backbone architecture (bigger is better), type of pre-training on the base classes (meta-training vs regular multi-class, currently regular wins), quantity and diversity of the base classes set (the more the merrier, resulting in richer and better adaptive features), and the use of self-supervised tasks during pre-training (serving as a proxy for increasing the diversity of the base set). In this paper we propose yet another simple technique that is important for the few shot learning performance - a search for a compact feature sub-space that is discriminative for a given few-shot test task. We show that the Task-Adaptive Feature Sub-Space Learning (TAFSSL) can significantly boost the performance in FSL scenarios when some additional unlabeled data accompanies the novel few-shot task, be it either the set of unlabeled queries (transductive FSL) or some additional set of unlabeled data samples (semi-supervised FSL). Specifically, we show that on the challenging miniImageNet and tieredImageNet benchmarks, TAFSSL can improve the current state-of-the-art in both transductive and semi-supervised FSL settings by more than $5\%$, while increasing the benefit of using unlabeled data in FSL to above $10\%$ performance gain.
The hypothesis that sub-network initializations (lottery) exist within the initializations of over-parameterized networks, which when trained in isolation produce highly generalizable models, has led to crucial insights into network initialization and has enabled computationally efficient inferencing. In order to realize the full potential of these pruning strategies, particularly when utilized in transfer learning scenarios, it is necessary to understand the behavior of winning tickets when they might overfit to the dataset characteristics. In supervised and semi-supervised learning, prediction calibration is a commonly adopted strategy to handle such inductive biases in models. In this paper, we study the impact of incorporating calibration strategies during model training on the quality of the resulting lottery tickets, using several evaluation metrics. More specifically, we incorporate a suite of calibration strategies to different combinations of architectures and datasets, and evaluate the fidelity of sub-networks retrained based on winning tickets. Furthermore, we report the generalization performance of tickets across distributional shifts, when the inductive biases are explicitly controlled using calibration mechanisms. Finally, we provide key insights and recommendations for obtaining reliable lottery tickets, which we demonstrate to achieve improved generalization.
More than 200 generic drugs approved by the U.S. Food and Drug Administration for non-cancer indications have shown promise for treating cancer. Due to their long history of safe patient use, low cost, and widespread availability, repurposing of generic drugs represents a major opportunity to rapidly improve outcomes for cancer patients and reduce healthcare costs worldwide. Evidence on the efficacy of non-cancer generic drugs being tested for cancer exists in scientific publications, but trying to manually identify and extract such evidence is intractable. In this paper, we introduce a system to automate this evidence extraction from PubMed abstracts. Our primary contribution is to define the natural language processing pipeline required to obtain such evidence, comprising the following modules: querying, filtering, cancer type entity extraction, therapeutic association classification, and study type classification. Using the subject matter expertise on our team, we create our own datasets for these specialized domain-specific tasks. We obtain promising performance in each of the modules by utilizing modern language modeling techniques and plan to treat them as baseline approaches for future improvement of individual components.
Recent advances in computer vision and deep learning have led to breakthroughs in the development of automated skin image analysis. In particular, skin cancer classification models have achieved performance higher than trained expert dermatologists. However, no attempt has been made to evaluate the consistency in performance of machine learning models across populations with varying skin tones. In this paper, we present an approach to estimate skin tone in benchmark skin disease datasets, and investigate whether model performance is dependent on this measure. Specifically, we use individual typology angle (ITA) to approximate skin tone in dermatology datasets. We look at the distribution of ITA values to better understand skin color representation in two benchmark datasets: 1) the ISIC 2018 Challenge dataset, a collection of dermoscopic images of skin lesions for the detection of skin cancer, and 2) the SD-198 dataset, a collection of clinical images capturing a wide variety of skin diseases. To estimate ITA, we first develop segmentation models to isolate non-diseased areas of skin. We find that the majority of the data in the the two datasets have ITA values between 34.5{\deg} and 48{\deg}, which are associated with lighter skin, and is consistent with under-representation of darker skinned populations in these datasets. We also find no measurable correlation between performance of machine learning model and ITA values, though more comprehensive data is needed for further validation.
As artificial intelligence and machine learning algorithms make further inroads into society, calls are increasing from multiple stakeholders for these algorithms to explain their outputs. At the same time, these stakeholders, whether they be affected citizens, government regulators, domain experts, or system developers, present different requirements for explanations. Toward addressing these needs, we introduce AI Explainability 360 (http://aix360.mybluemix.net/), an open-source software toolkit featuring eight diverse and state-of-the-art explainability methods and two evaluation metrics. Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of explanation methods, not only those in the toolkit but also in the broader literature on explainability. For data scientists and other users of the toolkit, we have implemented an extensible software architecture that organizes methods according to their place in the AI modeling pipeline. We also discuss enhancements to bring research innovations closer to consumers of explanations, ranging from simplified, more accessible versions of algorithms, to tutorials and an interactive web demo to introduce AI explainability to different audiences and application domains. Together, our toolkit and taxonomy can help identify gaps where more explainability methods are needed and provide a platform to incorporate them as they are developed.
With rapid adoption of deep learning in high-regret applications, the question of when and how much to trust these models often arises, which drives the need to quantify the inherent uncertainties. While identifying all sources that account for the stochasticity of learned models is challenging, it is common to augment predictions with confidence intervals to convey the expected variations in a model's behavior. In general, we require confidence intervals to be well-calibrated, reflect the true uncertainties, and to be sharp. However, most existing techniques for obtaining confidence intervals are known to produce unsatisfactory results in terms of at least one of those criteria. To address this challenge, we develop a novel approach for building calibrated estimators. More specifically, we construct separate models for predicting the target variable, and for estimating the confidence intervals, and pose a bi-level optimization problem that allows the predictive model to leverage estimates from the interval estimator through an \textit{uncertainty matching} strategy. Using experiments in regression, time-series forecasting, and object localization, we show that our approach achieves significant improvements over existing uncertainty quantification methods, both in terms of model fidelity and calibration error.
Explaining decisions of deep neural networks is a hot research topic with applications in medical imaging, video surveillance, and self driving cars. Many methods have been proposed in literature to explain these decisions by identifying relevance of different pixels. In this paper, we propose a method that can generate contrastive explanations for such data where we not only highlight aspects that are in themselves sufficient to justify the classification by the deep model, but also new aspects which if added will change the classification. One of our key contributions is how we define "addition" for such rich data in a formal yet humanly interpretable way that leads to meaningful results. This was one of the open questions laid out in Dhurandhar et.al. (2018) [5], which proposed a general framework for creating (local) contrastive explanations for deep models. We showcase the efficacy of our approach on CelebA and Fashion-MNIST in creating intuitive explanations that are also quantitatively superior compared with other state-of-the-art interpretability methods.
Recent work shows unequal performance of commercial face classification services in the gender classification task across intersectional groups defined by skin type and gender. Accuracy on dark-skinned females is significantly worse than on any other group. In this paper, we conduct several analyses to try to uncover the reason for this gap. The main finding, perhaps surprisingly, is that skin type is not the driver. This conclusion is reached via stability experiments that vary an image's skin type via color-theoretic methods, namely luminance mode-shift and optimal transport. A second suspect, hair length, is also shown not to be the driver via experiments on face images cropped to exclude the hair. Finally, using contrastive post-hoc explanation techniques for neural networks, we bring forth evidence suggesting that differences in lip, eye and cheek structure across ethnicity lead to the differences. Further, lip and eye makeup are seen as strong predictors for a female face, which is a troubling propagation of a gender stereotype.