Kasun Amarasinghe

Kasun Amarasinghe, Kit T. Rodolfa, Sérgio Jesus et al. · cmu

Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in their design, resulting in limited conclusions of methods' real-world utility. In this work, we seek to bridge this gap by conducting a study that evaluates three popular explainable ML methods in a setting consistent with the intended deployment context. We build on a previous study on e-commerce fraud detection and make crucial modifications to its setup relaxing the simplifying assumptions made in the original work that departed from the deployment context. In doing so, we draw drastically different conclusions from the earlier work and find no evidence for the incremental utility of the tested methods in the task. Our results highlight how seemingly trivial experimental design choices can yield misleading conclusions, with lessons about the necessity of not only evaluating explainable ML methods using tasks, data, users, and metrics grounded in the intended deployment contexts but also developing methods tailored to specific applications. In addition, we believe the design of this experiment can serve as a template for future study designs evaluating explainable ML methods in other real-world contexts.

Oscar Giles, Kasra Hosseini, Grigorios Mingas et al.

Synthetic datasets are often presented as a silver-bullet solution to the problem of privacy-preserving data publishing. However, for many applications, synthetic data has been shown to have limited utility when used to train predictive models. One promising potential application of these data is in the exploratory phase of the machine learning workflow, which involves understanding, engineering and selecting features. This phase often involves considerable time, and depends on the availability of data. There would be substantial value in synthetic data that permitted these steps to be carried out while, for example, data access was being negotiated, or with fewer information governance restrictions. This paper presents an empirical analysis of the agreement between the feature importance obtained from raw and from synthetic data, on a range of artificially generated and real-world datasets (where feature importance represents how useful each feature is when predicting a the outcome). We employ two differentially-private methods to produce synthetic data, and apply various utility measures to quantify the agreement in feature importance as this varies with the level of privacy. Our results indicate that synthetic data can sometimes preserve several representations of the ranking of feature importance in simple settings but their performance is not consistent and depends upon a number of factors. Particular caution should be exercised in more nuanced real-world settings, where synthetic data can lead to differences in ranked feature importance that could alter key modelling decisions. This work has important implications for developing synthetic versions of highly sensitive data sets in fields such as finance and healthcare.

Chanuka Algama, Kasun Amarasinghe

In the domain of computer vision, optical flow stands as a cornerstone for unraveling dynamic visual scenes. However, the challenge of accurately estimating optical flow under conditions of large nonlinear motion patterns remains an open question. The image flow constraint is vulnerable to substantial displacements, and rapid spatial transformations. Inaccurate approximations inherent in numerical differentiation techniques can further amplify such intricacies. In response, this research proposes an innovative algorithm for optical flow computation, utilizing the higher precision of second-order Taylor series approximation within the differential estimation framework. By embracing this mathematical underpinning, the research seeks to extract more information about the behavior of the function under complex real-world scenarios and estimate the motion of areas with a lack of texture. An impressive showcase of the algorithm's capabilities emerges through its performance on renowned optical flow benchmarks such as KITTI (2015) and Middlebury. The average endpoint error (AEE), which computes the Euclidian distance between the calculated flow field and the ground truth flow field, stands notably diminished, validating the effectiveness of the algorithm in handling complex motion patterns.

Catalina Vajiac, Arun Frey, Joachim Baumann et al.

Rental assistance programs provide individuals with financial assistance to prevent housing instabilities caused by evictions and avert homelessness. Since these programs operate under resource constraints, they must decide who to prioritize. Typically, funding is distributed by a reactive or first-come-first serve allocation process that does not systematically consider risk of future homelessness. We partnered with Allegheny County, PA to explore a proactive allocation approach that prioritizes individuals facing eviction based on their risk of future homelessness. Our ML system that uses state and county administrative data to accurately identify individuals in need of support outperforms simpler prioritization approaches by at least 20% while being fair and equitable across race and gender. Furthermore, our approach would identify 28% of individuals who are overlooked by the current process and end up homeless. Beyond improvements to the rental assistance program in Allegheny County, this study can inform the development of evidence-based decision support tools in similar contexts, including lessons about data needs, model design, evaluation, and field validation.

Kasun Amarasinghe, Kit Rodolfa, Hemank Lamba et al.

Explainability is highly-desired in Machine Learning (ML) systems supporting high-stakes policy decisions in areas such as health, criminal justice, education, and employment. While the field of explainable ML has expanded in recent years, much of this work has not taken real-world needs into account. A majority of proposed methods are designed with \textit{generic} explainability goals without well-defined use-cases or intended end-users and evaluated on simplified tasks, benchmark problems/datasets, or with proxy users (e.g., AMT). We argue that these simplified evaluation settings do not capture the nuances and complexities of real-world applications. As a result, the applicability and effectiveness of this large body of theoretical and methodological work in real-world applications are unclear. In this work, we take steps toward addressing this gap for the domain of public policy. First, we identify the primary use-cases of explainable ML within public policy problems. For each use case, we define the end-users of explanations and the specific goals the explanations have to fulfill. Finally, we map existing work in explainable ML to these use-cases, identify gaps in established capabilities, and propose research directions to fill those gaps to have a practical societal impact through ML. The contribution is 1) a methodology for explainable ML researchers to identify use cases and develop methods targeted at them and 2) using that methodology for the domain of public policy and giving an example for the researchers on developing explainable ML methods that result in real-world impact.

Daniel L. Marino, Kasun Amarasinghe, Milos Manic

Ensuring sustainability demands more efficient energy management with minimized energy wastage. Therefore, the power grid of the future should provide an unprecedented level of flexibility in energy management. To that end, intelligent decision making requires accurate predictions of future energy demand/load, both at aggregate and individual site level. Thus, energy load forecasting have received increased attention in the recent past, however has proven to be a difficult problem. This paper presents a novel energy load forecasting methodology based on Deep Neural Networks, specifically Long Short Term Memory (LSTM) algorithms. The presented work investigates two variants of the LSTM: 1) standard LSTM and 2) LSTM-based Sequence to Sequence (S2S) architecture. Both methods were implemented on a benchmark data set of electricity consumption data from one residential customer. Both architectures where trained and tested on one hour and one-minute time-step resolution datasets. Experimental results showed that the standard LSTM failed at one-minute resolution data while performing well in one-hour resolution data. It was shown that S2S architecture performed well on both datasets. Further, it was shown that the presented methods produced comparable results with the other deep learning methods for energy forecasting in literature.