Assessing Robustness to Noise: Low-Cost Head CT Triage

Automated medical image classification with convolutional neural networks (CNNs) has great potential to impact healthcare, particularly in resource-constrained healthcare systems where fewer trained radiologists are available. However, little is known about how well a trained CNN can perform on images with the increased noise levels, different acquisition protocols, or additional artifacts that may arise when using low-cost scanners, which can be underrepresented in datasets collected from well-funded hospitals. In this work, we investigate how a model trained to triage head computed tomography (CT) scans performs on images acquired with reduced x-ray tube current, fewer projections per gantry rotation, and limited angle scans. These changes can reduce the cost of the scanner and demands on electrical power but come at the expense of increased image noise and artifacts. We first develop a model to triage head CTs and report an area under the receiver operating characteristic curve (AUROC) of 0.77. We then show that the trained model is robust to reduced tube current and fewer projections, with the AUROC dropping only 0.65% for images acquired with a 16x reduction in tube current and 0.22% for images acquired with 8x fewer projections. Finally, for significantly degraded images acquired by a limited angle scan, we show that a model trained specifically to classify such images can overcome the technological limitations to reconstruction and maintain an AUROC within 0.09% of the original model.

Understanding the Downstream Instability of Word Embeddings

Many industrial machine learning (ML) systems require frequent retraining to keep up-to-date with constantly changing data. This retraining exacerbates a large challenge facing ML systems today: model training is unstable, i.e., small changes in training data can cause significant changes in the model's predictions. In this paper, we work on developing a deeper understanding of this instability, with a focus on how a core building block of modern natural language processing (NLP) pipelines---pre-trained word embeddings---affects the instability of downstream NLP models. We first empirically reveal a tradeoff between stability and memory: increasing the embedding memory 2x can reduce the disagreement in predictions due to small changes in training data by 5% to 37% (relative). To theoretically explain this tradeoff, we introduce a new measure of embedding instability---the eigenspace instability measure---which we prove bounds the disagreement in downstream predictions introduced by the change in word embeddings. Practically, we show that the eigenspace instability measure can be a cost-effective way to choose embedding parameters to minimize instability without training downstream models, outperforming other embedding distance measures and performing competitively with a nearest neighbor-based measure. Finally, we demonstrate that the observed stability-memory tradeoffs extend to other types of embeddings as well, including knowledge graph and contextual word embeddings.

Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods

Weak supervision is a popular method for building machine learning models without relying on ground truth annotations. Instead, it generates probabilistic training labels by estimating the accuracies of multiple noisy labeling sources (e.g., heuristics, crowd workers). Existing approaches use latent variable estimation to model the noisy sources, but these methods can be computationally expensive, scaling superlinearly in the data. In this work, we show that, for a class of latent variable models highly applicable to weak supervision, we can find a closed-form solution to model parameters, obviating the need for iterative solutions like stochastic gradient descent (SGD). We use this insight to build FlyingSquid, a weak supervision framework that runs orders of magnitude faster than previous weak supervision approaches and requires fewer assumptions. In particular, we prove bounds on generalization error without assuming that the latent variable model can exactly parameterize the underlying data distribution. Empirically, we validate FlyingSquid on benchmark weak supervision datasets and find that it achieves the same or higher quality compared to previous approaches without the need to tune an SGD procedure, recovers model parameters 170 times faster on average, and enables new video analysis and online learning applications.

Hyperbolic Graph Convolutional Neural Networks

Graph convolutional neural networks (GCNs) embed nodes in a graph into Euclidean space, which has been shown to incur a large distortion when embedding real-world graphs with scale-free or hierarchical structure. Hyperbolic geometry offers an exciting alternative, as it enables embeddings with much smaller distortion. However, extending GCNs to hyperbolic geometry presents several unique challenges because it is not clear how to define neural network operations, such as feature transformation and aggregation, in hyperbolic space. Furthermore, since input features are often Euclidean, it is unclear how to transform the features into hyperbolic embeddings with the right amount of curvature. Here we propose Hyperbolic Graph Convolutional Neural Network (HGCN), the first inductive hyperbolic GCN that leverages both the expressiveness of GCNs and hyperbolic geometry to learn inductive node representations for hierarchical and scale-free graphs. We derive GCN operations in the hyperboloid model of hyperbolic space and map Euclidean input features to embeddings in hyperbolic spaces with different trainable curvature at each layer. Experiments demonstrate that HGCN learns embeddings that preserve hierarchical structure, and leads to improved performance when compared to Euclidean analogs, even with very low dimensional embeddings: compared to state-of-the-art GCNs, HGCN achieves an error reduction of up to 63.1% in ROC AUC for link prediction and of up to 47.5% in F1 score for node classification, also improving state-of-the art on the Pubmed dataset.

Multi-Resolution Weak Supervision for Sequential Data

Since manually labeling training data is slow and expensive, recent industrial and scientific research efforts have turned to weaker or noisier forms of supervision sources. However, existing weak supervision approaches fail to model multi-resolution sources for sequential data, like video, that can assign labels to individual elements or collections of elements in a sequence. A key challenge in weak supervision is estimating the unknown accuracies and correlations of these sources without using labeled data. Multi-resolution sources exacerbate this challenge due to complex correlations and sample complexity that scales in the length of the sequence. We propose Dugong, the first framework to model multi-resolution weak supervision sources with complex correlations to assign probabilistic labels to training data. Theoretically, we prove that Dugong, under mild conditions, can uniquely recover the unobserved accuracy and correlation parameters and use parameter sharing to improve sample complexity. Our method assigns clinician-validated labels to population-scale biomedical video repositories, helping outperform traditional supervision by 36.8 F1 points and addressing a key use case where machine learning has been severely limited by the lack of expert labeled data. On average, Dugong improves over traditional supervision by 16.0 F1 points and existing weak supervision approaches by 24.2 F1 points across several video and sensor classification tasks.

PipeMare: Asynchronous Pipeline Parallel DNN Training

Recently there has been a flurry of interest around using pipeline parallelism while training neural networks. Pipeline parallelism enables larger models to be partitioned spatially across chips and within a chip, leading to both lower network communication and overall higher hardware utilization. Unfortunately, to preserve statistical efficiency, existing pipeline-parallelism techniques sacrifice hardware efficiency by introducing bubbles into the pipeline and/or incurring extra memory costs. In this paper, we investigate to what extent these sacrifices are necessary. Theoretically, we derive a simple but robust training method, called PipeMare, that tolerates asynchronous updates during pipeline-parallel execution. Using this, we show empirically, on a ResNet network and a Transformer network, that PipeMare can achieve final model qualities that match those of synchronous training techniques (at most 0.9% worse test accuracy and 0.3 better test BLEU score) while either using up to 2.0X less weight and optimizer memory or being up to 3.3X faster than other pipeline parallel training techniques. To the best of our knowledge we are the first to explore these techniques and fine-grained pipeline parallelism (e.g. the number of pipeline stages equals to the number of layers) during neural network training.

Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels

Many real-world video analysis applications require the ability to identify domain-specific events in video, such as interviews and commercials in TV news broadcasts, or action sequences in film. Unfortunately, pre-trained models to detect all the events of interest in video may not exist, and training new models from scratch can be costly and labor-intensive. In this paper, we explore the utility of specifying new events in video in a more traditional manner: by writing queries that compose outputs of existing, pre-trained models. To write these queries, we have developed Rekall, a library that exposes a data model and programming model for compositional video event specification. Rekall represents video annotations from different sources (object detectors, transcripts, etc.) as spatiotemporal labels associated with continuous volumes of spacetime in a video, and provides operators for composing labels into queries that model new video events. We demonstrate the use of Rekall in analyzing video from cable TV news broadcasts, films, static-camera vehicular video streams, and commercial autonomous vehicle logs. In these efforts, domain experts were able to quickly (in a few hours to a day) author queries that enabled the accurate detection of new events (on par with, and in some cases much more accurate than, learned approaches) and to rapidly retrieve video clips for human-in-the-loop tasks such as video content curation and training data curation. Finally, in a user study, novice users of Rekall were able to author queries to retrieve new events in video given just one hour of query development time.

Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging

Machine learning models for medical image analysis often suffer from poor performance on important subsets of a population that are not identified during training or testing. For example, overall performance of a cancer detection model may be high, but the model still consistently misses a rare but aggressive cancer subtype. We refer to this problem as hidden stratification, and observe that it results from incompletely describing the meaningful variation in a dataset. While hidden stratification can substantially reduce the clinical efficacy of machine learning models, its effects remain difficult to measure. In this work, we assess the utility of several possible techniques for measuring and describing hidden stratification effects, and characterize these effects both on multiple medical imaging datasets and via synthetic experiments on the well-characterised CIFAR-100 benchmark dataset. We find evidence that hidden stratification can occur in unidentified imaging subsets with low prevalence, low label quality, subtle distinguishing features, or spurious correlates, and that it can result in relative performance differences of over 20% on clinically important subsets. Finally, we explore the clinical implications of our findings, and suggest that evaluation of hidden stratification should be a critical component of any machine learning deployment in medical imaging.

Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices

In real-world machine learning applications, data subsets correspond to especially critical outcomes: vulnerable cyclist detections are safety-critical in an autonomous driving task, and "question" sentences might be important to a dialogue agent's language understanding for product purposes. While machine learning models can achieve high quality performance on coarse-grained metrics like F1-score and overall accuracy, they may underperform on critical subsets---we define these as slices, the key abstraction in our approach. To address slice-level performance, practitioners often train separate "expert" models on slice subsets or use multi-task hard parameter sharing. We propose Slice-based Learning, a new programming model in which the slicing function (SF), a programming interface, specifies critical data subsets for which the model should commit additional capacity. Any model can leverage SFs to learn slice expert representations, which are combined with an attention mechanism to make slice-aware predictions. We show that our approach maintains a parameter-efficient representation while improving over baselines by up to 19.0 F1 on slices and 4.6 F1 overall on datasets spanning language understanding (e.g. SuperGLUE), computer vision, and production-scale industrial systems.

Overton: A Data System for Monitoring and Improving Machine-Learned Products

We describe a system called Overton, whose main design goal is to support engineers in building, monitoring, and improving production machine learning systems. Key challenges engineers face are monitoring fine-grained quality, diagnosing errors in sophisticated applications, and handling contradictory or incomplete supervision data. Overton automates the life cycle of model construction, deployment, and monitoring by providing a set of novel high-level, declarative abstractions. Overton's vision is to shift developers to these higher-level tasks instead of lower-level machine learning tasks. In fact, using Overton, engineers can build deep-learning-based applications without writing any code in frameworks like TensorFlow. For over a year, Overton has been used in production to support multiple applications in both near-real-time applications and back-of-house processing. In that time, Overton-based applications have answered billions of queries in multiple languages and processed trillions of records reducing errors 1.7-2.9 times versus production systems.