@article{liu_mei_peng_vatsavai_2023, title={Context Retrieval via Normalized Contextual Latent Interaction for Conversational Agent}, ISSN={["2375-9232"]}, DOI={10.1109/ICDMW60847.2023.00196}, abstractNote={Conversational agents leveraging AI, particularly deep learning, are emerging in both academic research and real-world applications. However, these applications still face challenges, including disrespecting knowledge and facts, not personalizing to user preferences, and enormous demand for computational resources during training and inference. Recent research efforts have been focused on addressing these challenges from various aspects, including supplementing various types of auxiliary information to the conversational agents. However, existing methods are still not able to effectively and efficiently exploit relevant information from these auxiliary supplements to further unleash the power of the conversational agents and the language models they use. In this paper, we present a novel method, PK-NCLI, that is able to accurately and efficiently identify relevant auxiliary information to improve the quality of conversational responses by learning the relevance among persona, chat history, and knowledge background through lowlevel normalized contextual latent interaction. Our experimental results indicate that PK-NCLI outperforms the state-of-theart method, PK-FoCus, by 47.80%/30.61%/24.14% in terms of perplexity, knowledge grounding, and training efficiency, respectively, and maintained the same level of persona grounding performance. We also provide a detailed analysis of how different factors, including language model choices and trade-offs on training weights, would affect the performance of PK-NCLI.}, journal={2023 23RD IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS, ICDMW 2023}, author={Liu, Junfeng and Mei, Zhuocheng and Peng, Kewen and Vatsavai, Ranga Raju}, year={2023}, pages={1543–1550} }
 @article{peng_chakraborty_menzies_2023, title={FairMask: Better Fairness via Model-Based Rebalancing of Protected Attributes}, volume={49}, ISSN={["1939-3520"]}, url={https://doi.org/10.1109/TSE.2022.3220713}, DOI={10.1109/TSE.2022.3220713}, abstractNote={<italic>Context</italic>: Machine learning software can generate models that inappropriately discriminate against specific protected social groups (e.g., groups based on gender, ethnicity, etc.). Motivated by those results, software engineering researchers have proposed many methods for mitigating those discriminatory effects. While those methods are effective in mitigating bias, few of them can provide explanations on what is the root cause of bias. <italic>Objective</italic>: We aim to better detect and mitigate algorithmic discrimination in machine learning software problems. <italic>Method</italic>: Here we propose <inline-formula><tex-math notation="LaTeX">${{\sf FairMask}}$</tex-math><alternatives><mml:math><mml:mi mathvariant="sans-serif">FairMask</mml:mi></mml:math><inline-graphic xlink:href="peng-ieq1-3220713.gif"/></alternatives></inline-formula>, a <italic>model-based</italic> extrapolation method that is capable of both mitigating bias and explaining the cause. In our <inline-formula><tex-math notation="LaTeX">${{\sf FairMask}}$</tex-math><alternatives><mml:math><mml:mi mathvariant="sans-serif">FairMask</mml:mi></mml:math><inline-graphic xlink:href="peng-ieq2-3220713.gif"/></alternatives></inline-formula> approach, protected attributes are represented by models learned from the other independent variables (and these models offer extrapolations over the space between existing examples). We then use the extrapolation models to relabel protected attributes later seen in testing data or deployment time. Our approach aims to offset the biased predictions of the classification model by rebalancing the distribution of protected attributes. <italic>Results</italic>: The experiments of this paper show that, without compromising (original) model performance, <inline-formula><tex-math notation="LaTeX">${{\sf FairMask}}$</tex-math><alternatives><mml:math><mml:mi mathvariant="sans-serif">FairMask</mml:mi></mml:math><inline-graphic xlink:href="peng-ieq3-3220713.gif"/></alternatives></inline-formula> can achieve significantly better group and individual fairness (as measured in different metrics) than benchmark methods. Moreover, compared to another instance-based rebalancing method, our model-based approach shows faster runtime and thus better scalability. <italic>Conclusion</italic>: Algorithmic decision bias can be removed via extrapolation that corrects the misleading latent correlation between the protected attributes and other non-protected ones. As evidence for this, our proposed <inline-formula><tex-math notation="LaTeX">${{\sf FairMask}}$</tex-math><alternatives><mml:math><mml:mi mathvariant="sans-serif">FairMask</mml:mi></mml:math><inline-graphic xlink:href="peng-ieq4-3220713.gif"/></alternatives></inline-formula> is not only performance-wise better (measured by fairness and performance metrics) than two state-of-the-art fairness algorithms. <italic>Reproduction Package</italic>: In order to better support open science, all scripts and data used in this study are available online at <uri>https://github.com/anonymous12138/biasmitigation</uri>.}, number={4}, journal={IEEE TRANSACTIONS ON SOFTWARE ENGINEERING}, author={Peng, Kewen and Chakraborty, Joymallya and Menzies, Tim}, year={2023}, month={Apr}, pages={2426–2439} }
 @article{peng_kaltenecker_siegmund_apel_menzies_2023, title={VEER: enhancing the interpretability of model-based optimizations}, volume={28}, ISSN={["1573-7616"]}, DOI={10.1007/s10664-023-10296-w}, abstractNote={Many software systems can be tuned for multiple objectives (e.g., faster runtime, less required memory, less network traffic or energy consumption, etc.). Such systems can suffer from “disagreement” where different models have different (or even opposite) insights and tactics on how to optimize a system. For configuration problems, we show that (a) model disagreement is rampant; yet (b) prior to this paper, it has barely been explored. We aim at helping practitioners and researchers better solve multi-objective configuration optimization problems, by resolving model disagreement. We propose a dimension reduction method called VEER that builds a useful one-dimensional approximation to the original N-objective space. Traditional model-based optimizers use Pareto search to locate Pareto-optimal solutions to a multi-objective problem, which is computationally heavy on large-scale systems. VEER builds a surrogate that can replace the Pareto sorting step after deployment. Compared to the prior state-of-the-art, for 11 configurable systems, VEER significantly reduces disagreement and execution time, without compromising the optimization performance in most cases. For our largest problem (with tens of thousands of possible configurations), optimizing with VEER finds as good or better optimizations with zero model disagreements, three orders of magnitude faster. When employing model-based optimizers for multi-objective optimization, we recommend to apply VEER, which not only improves the execution time, but also resolves the potential model disagreement problem.}, number={3}, journal={EMPIRICAL SOFTWARE ENGINEERING}, author={Peng, Kewen and Kaltenecker, Christian and Siegmund, Norbert and Apel, Sven and Menzies, Tim}, year={2023}, month={Jun} }
 @article{peng_menzies_2021, title={Documenting Evidence of a Reuse of "'Why Should I Trust You?": Explaining the Predictions of Any Classifier'}, url={https://doi.org/10.1145/3468264.3477217}, DOI={10.1145/3468264.3477217}, abstractNote={We report here the following example of reuse. LIME is a local instance-based explanation generation framework that was originally proposed by Ribeiro et al. in their paper "'Why Should I Trust You?': Explaining the Predictions of Any Classifier". The framework was reused by Peng et al. in their paper "Defect Reduction Planning (using TimeLIME)". The paper used the original implementation of LIME as one of the core components in the proposed framework.}, journal={PROCEEDINGS OF THE 29TH ACM JOINT MEETING ON EUROPEAN SOFTWARE ENGINEERING CONFERENCE AND SYMPOSIUM ON THE FOUNDATIONS OF SOFTWARE ENGINEERING (ESEC/FSE '21)}, author={Peng, Kewen and Menzies, Tim}, year={2021}, pages={1600–1600} }
 @article{peng_menzies_2021, title={Documenting Evidence of a Reuse of 'What is a Feature? A Qualitative Study of Features in Industrial Software Product Lines'}, url={https://doi.org/10.1145/3468264.3477216}, DOI={10.1145/3468264.3477216}, abstractNote={We report here the following example of reuse. The original paper is a prior work about features in product lines by Berger et al. The paper "Dimensions of software configuration: on the configuration context in modern software development" by Siegmund et al. reused definitions and theories about configuration features in the original paper.}, journal={PROCEEDINGS OF THE 29TH ACM JOINT MEETING ON EUROPEAN SOFTWARE ENGINEERING CONFERENCE AND SYMPOSIUM ON THE FOUNDATIONS OF SOFTWARE ENGINEERING (ESEC/FSE '21)}, author={Peng, Kewen and Menzies, Tim}, year={2021}, pages={1599–1599} }
 @article{ferraro_kirkman_moore_peng_2021, title={ON THE NOETHER BOUND FOR NONCOMMUTATIVE RINGS}, volume={149}, ISSN={["1088-6826"]}, DOI={10.1090/proc/15092}, abstractNote={We present two noncommutative algebras over a field of characteristic zero that each posses a family of actions by cyclic groups of order $2n$, represented in $n \times n$ matrices, requiring generators of degree $3n$.}, number={7}, journal={PROCEEDINGS OF THE AMERICAN MATHEMATICAL SOCIETY}, author={Ferraro, Luigi and Kirkman, Ellen and Moore, W. Frank and Peng, Kewen}, year={2021}, month={Jul}, pages={2711–2725} }
 @article{chakraborty_peng_menzies_2020, title={Making Fair ML Software using Trustworthy Explanation}, ISSN={["1527-1366"]}, DOI={10.1145/3324884.3418932}, abstractNote={Machine learning software is being used in many applications (finance, hiring, admissions, criminal justice) having huge social impact. But sometimes the behavior of this software is biased and it shows discrimination based on some sensitive attributes such as sex, race etc. Prior works concentrated on finding and mitigating bias in ML models. A recent trend is using instance-based model-agnostic explanation methods such as LIME[36] to find out bias in the model prediction. Our work concentrates on finding shortcomings of current bias measures and explanation methods. We show how our proposed method based on K nearest neighbors can overcome those shortcomings and find the underlying bias of black box models. Our results are more trustworthy and helpful for the practitioners. Finally, We describe our future framework combining explanation and planning to build fair software.}, journal={2020 35TH IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMATED SOFTWARE ENGINEERING (ASE 2020)}, author={Chakraborty, Joymallya and Peng, Kewen and Menzies, Tim}, year={2020}, pages={1229–1233} }