Measuring Distributional Shifts in Text: The Advantage of Language Model-Based Embeddings

An essential part of monitoring machine learning models in production is measuring input and output data drift. In this paper, we present a system for measuring distributional shifts in natural language data and highlight and investigate the potential advantage of using large language models (LLMs) for this problem. Recent advancements in LLMs and their successful adoption in different domains indicate their effectiveness in capturing semantic relationships for solving various natural language processing problems. The power of LLMs comes largely from the encodings (embeddings) generated in the hidden layers of the corresponding neural network. First we propose a clustering-based algorithm for measuring distributional shifts in text data by exploiting such embeddings. Then we study the effectiveness of our approach when applied to text embeddings generated by both LLMs and classical embedding algorithms. Our experiments show that general-purpose LLM-based embeddings provide a high sensitivity to data drift compared to other embedding methods. We propose drift sensitivity as an important evaluation metric to consider when comparing language models. Finally, we present insights and lessons learned from deploying our framework as part of the Fiddler ML Monitoring platform over a period of 18 months.

Designing Closed-Loop Models for Task Allocation

Automatically assigning tasks to people is challenging because human performance can vary across tasks for many reasons. This challenge is further compounded in real-life settings in which no oracle exists to assess the quality of human decisions and task assignments made. Instead, we find ourselves in a "closed" decision-making loop in which the same fallible human decisions we rely on in practice must also be used to guide task allocation. How can imperfect and potentially biased human decisions train an accurate allocation model? Our key insight is to exploit weak prior information on human-task similarity to bootstrap model training. We show that the use of such a weak prior can improve task allocation accuracy, even when human decision-makers are fallible and biased. We present both theoretical analysis and empirical evaluation over synthetic data and a social media toxicity detection task. Results demonstrate the efficacy of our approach.

Towards the Use of Saliency Maps for Explaining Low-Quality Electrocardiograms to End Users

When using medical images for diagnosis, either by clinicians or artificial intelligence (AI) systems, it is important that the images are of high quality. When an image is of low quality, the medical exam that produced the image often needs to be redone. In telemedicine, a common problem is that the quality issue is only flagged once the patient has left the clinic, meaning they must return in order to have the exam redone. This can be especially difficult for people living in remote regions, who make up a substantial portion of the patients at Portal Telemedicina, a digital healthcare organization based in Brazil. In this paper, we report on ongoing work regarding (i) the development of an AI system for flagging and explaining low-quality medical images in real-time, (ii) an interview study to understand the explanation needs of stakeholders using the AI system at OurCompany, and, (iii) a longitudinal user study design to examine the effect of including explanations on the workflow of the technicians in our clinics. To the best of our knowledge, this would be the first longitudinal study on evaluating the effects of XAI methods on end-users -- stakeholders that use AI systems but do not have AI-specific expertise. We welcome feedback and suggestions on our experimental setup.

Visual Auditor: Interactive Visualization for Detection and Summarization of Model Biases

As machine learning (ML) systems become increasingly widespread, it is necessary to audit these systems for biases prior to their deployment. Recent research has developed algorithms for effectively identifying intersectional bias in the form of interpretable, underperforming subsets (or slices) of the data. However, these solutions and their insights are limited without a tool for visually understanding and interacting with the results of these algorithms. We propose Visual Auditor, an interactive visualization tool for auditing and summarizing model biases. Visual Auditor assists model validation by providing an interpretable overview of intersectional bias (bias that is present when examining populations defined by multiple features), details about relationships between problematic data slices, and a comparison between underperforming and overperforming data slices in a model. Our open-source tool runs directly in both computational notebooks and web browsers, making model auditing accessible and easily integrated into current ML development workflows. An observational user study in collaboration with domain experts at Fiddler AI highlights that our tool can help ML practitioners identify and understand model biases.

A Human-Centric Take on Model Monitoring

Predictive models are increasingly used to make various consequential decisions in high-stakes domains such as healthcare, finance, and policy. It becomes critical to ensure that these models make accurate predictions, are robust to shifts in the data, do not rely on spurious features, and do not unduly discriminate against minority groups. To this end, several approaches spanning various areas such as explainability, fairness, and robustness have been proposed in recent literature. Such approaches need to be human-centered as they cater to the understanding of the models to their users. However, there is a research gap in understanding the human-centric needs and challenges of monitoring machine learning (ML) models once they are deployed. To fill this gap, we conducted an interview study with 13 practitioners who have experience at the intersection of deploying ML models and engaging with customers spanning domains such as financial services, healthcare, hiring, online retail, computational advertising, and conversational assistants. We identified various human-centric challenges and requirements for model monitoring in real-world applications. Specifically, we found the need and the challenge for the model monitoring systems to clarify the impact of the monitoring observations on outcomes. Further, such insights must be actionable, robust, customizable for domain-specific use cases, and cognitively considerate to avoid information overload.

Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks

We show that deep neural networks that satisfy demographic parity do so through a form of race or gender awareness, and that the more we force a network to be fair, the more accurately we can recover race or gender from the internal state of the network. Based on this observation, we propose a simple two-stage solution for enforcing fairness. First, we train a two-headed network to predict the protected attribute (such as race or gender) alongside the original task, and second, we enforce demographic parity by taking a weighted sum of the heads. In the end, this approach creates a single-headed network with the same backbone architecture as the original network. Our approach has near identical performance compared to existing regularization-based or preprocessing methods, but has greater stability and higher accuracy where near exact demographic parity is required. To cement the relationship between these two approaches, we show that an unfair and optimally accurate classifier can be recovered by taking a weighted sum of a fair classifier and a classifier predicting the protected attribute. We use this to argue that both the fairness approaches and our explicit formulation demonstrate disparate treatment and that, consequentially, they are likely to be unlawful in a wide range of scenarios under the US law.

Diverse Counterfactual Explanations for Anomaly Detection in Time Series

Data-driven methods that detect anomalies in times series data are ubiquitous in practice, but they are in general unable to provide helpful explanations for the predictions they make. In this work we propose a model-agnostic algorithm that generates counterfactual ensemble explanations for time series anomaly detection models. Our method generates a set of diverse counterfactual examples, i.e, multiple perturbed versions of the original time series that are not considered anomalous by the detection model. Since the magnitude of the perturbations is limited, these counterfactuals represent an ensemble of inputs similar to the original time series that the model would deem normal. Our algorithm is applicable to any differentiable anomaly detection model. We investigate the value of our method on univariate and multivariate real-world datasets and two deep-learning-based anomaly detection models, under several explainability criteria previously proposed in other data domains such as Validity, Plausibility, Closeness and Diversity. We show that our algorithm can produce ensembles of counterfactual examples that satisfy these criteria and thanks to a novel type of visualisation, can convey a richer interpretation of a model's internal mechanism than existing methods. Moreover, we design a sparse variant of our method to improve the interpretability of counterfactual explanations for high-dimensional time series anomalies. In this setting, our explanation is localised on only a few dimensions and can therefore be communicated more efficiently to the model's user.

COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

As reinforcement learning (RL) has achieved near human-level performance in a variety of tasks, its robustness has raised great attention. While a vast body of research has explored test-time (evasion) attacks in RL and corresponding defenses, its robustness against training-time (poisoning) attacks remains largely unanswered. In this work, we focus on certifying the robustness of offline RL in the presence of poisoning attacks, where a subset of training trajectories could be arbitrarily manipulated. We propose the first certification framework, COPA, to certify the number of poisoning trajectories that can be tolerated regarding different certification criteria. Given the complex structure of RL, we propose two certification criteria: per-state action stability and cumulative reward bound. To further improve the certification, we propose new partition and aggregation protocols to train robust policies. We further prove that some of the proposed certification methods are theoretically tight and some are NP-Complete problems. We leverage COPA to certify three RL environments trained with different algorithms and conclude: (1) The proposed robust aggregation protocols such as temporal aggregation can significantly improve the certifications; (2) Our certification for both per-state action stability and cumulative reward bound are efficient and tight; (3) The certification for different training algorithms and environments are different, implying their intrinsic robustness properties. All experimental results are available at https://copa-leaderboard.github.io.

Human-Algorithm Collaboration: Achieving Complementarity and Avoiding Unfairness

Much of machine learning research focuses on predictive accuracy: given a task, create a machine learning model (or algorithm) that maximizes accuracy. In many settings, however, the final prediction or decision of a system is under the control of a human, who uses an algorithm's output along with their own personal expertise in order to produce a combined prediction. One ultimate goal of such collaborative systems is "complementarity": that is, to produce lower loss (equivalently, greater payoff or utility) than either the human or algorithm alone. However, experimental results have shown that even in carefully-designed systems, complementary performance can be elusive. Our work provides three key contributions. First, we provide a theoretical framework for modeling simple human-algorithm systems and demonstrate that multiple prior analyses can be expressed within it. Next, we use this model to prove conditions where complementarity is impossible, and give constructive examples of where complementarity is achievable. Finally, we discuss the implications of our findings, especially with respect to the fairness of a classifier. In sum, these results deepen our understanding of key factors influencing the combined performance of human-algorithm systems, giving insight into how algorithmic tools can best be designed for collaborative environments.

Designing Closed Human-in-the-loop Deferral Pipelines

In hybrid human-machine deferral frameworks, a classifier can defer uncertain cases to human decision-makers (who are often themselves fallible). Prior work on simultaneous training of such classifier and deferral models has typically assumed access to an oracle during training to obtain true class labels for training samples, but in practice there often is no such oracle. In contrast, we consider a "closed" decision-making pipeline in which the same fallible human decision-makers used in deferral also provide training labels. How can imperfect and biased human expert labels be used to train a fair and accurate deferral framework? Our key insight is that by exploiting weak prior information, we can match experts to input examples to ensure fairness and accuracy of the resulting deferral framework, even when imperfect and biased experts are used in place of ground truth labels. The efficacy of our approach is shown both by theoretical analysis and by evaluation on two tasks.