148 citations · 346 across the 16 of their papers we have counts for
17 papers
The four-fifths rule is not disparate impact: a woeful tale of epistemic trespassing in algorithmic fairness
Elizabeth Anne Watkins, Michael McKenna, Jiahao Chen
Computer scientists are trained to create abstractions that simplify and generalize. However, a premature abstraction that omits crucial contextual details creates the risk of epis…
DuVisor: a User-level Hypervisor Through Delegated Virtualization
Jiahao Chen, Dingji Li, Zeyu Mi +4
Today's mainstream virtualization systems comprise of two cooperative components: a kernel-resident driver that accesses virtualization hardware and a user-level helper process tha…
On the Current and Emerging Challenges of Developing Fair and Ethical AI Solutions in Financial Services
Eren Kurshan, Jiahao Chen, Victor Storchan +1
Artificial intelligence (AI) continues to find more numerous and more critical applications in the financial services industry, giving rise to fair and ethical AI as an industry-wi…
Adversarial Attacks on Machinery Fault Diagnosis
Jiahao Chen, Diqun Yan
Despite the great progress of neural network-based (NN-based) machinery fault diagnosis methods, their robustness has been largely neglected, for they can be easily fooled through…
Beyond Fairness Metrics: Roadblocks and Challenges for Ethical AI in Practice
Jiahao Chen, Victor Storchan, Eren Kurshan
We review practical challenges in building and deploying ethical AI at the scale of contemporary industrial and societal uses. Apart from the purely technical concerns that are the…
Ontology drift is a challenge for explainable data governance
Jiahao Chen
We introduce the needs for explainable AI that arise from Standard No. 239 from the Basel Committee on Banking Standards (BCBS 239), which outlines 11 principles for effective risk…
Seven challenges for harmonizing explainability requirements
Jiahao Chen, Victor Storchan
Regulators have signalled an interest in adopting explainable AI(XAI) techniques to handle the diverse needs for model governance, operational servicing, and compliance in the fina…
Counterfactual Explanations for Arbitrary Regression Models
Thomas Spooner, Danial Dervovic, Jason Long +3
We present a new method for counterfactual explanations (CFEs) based on Bayesian optimisation that applies to both classification and regression models. Our method is a globally co…
Model-Based Counterfactual Synthesizer for Interpretation
Fan Yang, Sahan Suresh Alva, Jiahao Chen +1
Counterfactuals, serving as one of the emerging type of model interpretations, have recently received attention from both researchers and practitioners. Counterfactual explanations…
Provable Multi-Objective Reinforcement Learning with Generative Models
Dongruo Zhou, Jiahao Chen, Quanquan Gu
Multi-objective reinforcement learning (MORL) is an extension of ordinary, single-objective reinforcement learning (RL) that is applicable to many real-world tasks where multiple o…
Debiasing classifiers: is reality at variance with expectation?
Ashrya Agrawal, Florian Pfisterer, Bernd Bischl +5
We present an empirical study of debiasing methods for classifiers, showing that debiasers often fail in practice to generalize out-of-sample, and can in fact make fairness worse r…
Towards Self-Regulating AI: Challenges and Opportunities of AI Model Governance in Financial Services
Eren Kurshan, Hongda Shen, Jiahao Chen
AI systems have found a wide range of application areas in financial services. Their involvement in broader and increasingly critical decisions has escalated the need for complianc…
FACT: A Diagnostic for Group Fairness Trade-offs
Joon Sik Kim, Jiahao Chen, Ameet Talwalkar
Group fairness, a class of fairness notions that measure how different groups of individuals are treated differently according to their protected attributes, has been shown to conf…
Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved
Jiahao Chen, Nathan Kallus, Xiaojie Mao +2
Assessing the fairness of a decision making system with respect to a protected class, such as gender or race, is challenging when class membership labels are unavailable. Probabili…
Fair lending needs explainable models for responsible recommendation
Jiahao Chen
The financial services industry has unique explainability and fairness challenges arising from compliance and ethical considerations in credit decisioning. These challenges complic…
Linguistic Relativity and Programming Languages
Jiahao Chen
The use of programming languages can wax and wane across the decades. We examine the split-apply- combine pattern that is common in statistical computing, and consider how its invo…
Robust benchmarking in noisy environments
Jiahao Chen, Jarrett Revels
We propose a benchmarking strategy that is robust in the presence of timer error, OS jitter and other environmental fluctuations, and is insensitive to the highly nonideal statisti…