Parinaz Naghizadeh

Yiqiao Liao, Parinaz Naghizadeh

Although many fairness criteria have been proposed to ensure that machine learning algorithms do not exhibit or amplify our existing social biases, these algorithms are trained on datasets that can themselves be statistically biased. In this paper, we investigate the robustness of a number of existing (demographic) fairness criteria when the algorithm is trained on biased data. We consider two forms of dataset bias: errors by prior decision makers in the labeling process, and errors in measurement of the features of disadvantaged individuals. We analytically show that some constraints (such as Demographic Parity) can remain robust when facing certain statistical biases, while others (such as Equalized Odds) are significantly violated if trained on biased data. We also analyze the sensitivity of these criteria and the decision maker's utility to biases. We provide numerical experiments based on three real-world datasets (the FICO, Adult, and German credit score datasets) supporting our analytical findings. Our findings present an additional guideline for choosing among existing fairness criteria, or for proposing new criteria, when available datasets may be biased.

Yifan Yang, Ali Payani, Parinaz Naghizadeh

Federated Learning (FL) has been a pivotal paradigm for collaborative training of machine learning models across distributed datasets. In heterogeneous settings, it has been observed that a single shared FL model can lead to low local accuracy, motivating personalized FL algorithms. In parallel, fair FL algorithms have been proposed to enforce group fairness on the global models. Again, in heterogeneous settings, global and local fairness do not necessarily align, motivating the recent literature on locally fair FL. In this paper, we propose new FL algorithms for heterogeneous settings, spanning the space between personalized and locally fair FL. Building on existing clustering-based personalized FL methods, we incorporate a new fairness metric into cluster assignment, enabling a tunable balance between local accuracy and fairness. Our methods match or exceed the performance of existing locally fair FL approaches, without explicit fairness intervention. We further demonstrate (numerically and analytically) that personalization alone can improve local fairness and that our methods exploit this alignment when present.

Md Ferdous Alam, Parinaz Naghizadeh, David Hoelzle

Reinforcement learning (RL) enables sequential decision-making in complex and high-dimensional environments through interaction with the environment. In most real-world applications, however, a high number of interactions are infeasible. In these environments, transfer RL algorithms, which can be used for the transfer of knowledge from one or multiple source environments to a target environment, have been shown to increase learning speed and improve initial and asymptotic performance. However, most existing transfer RL algorithms are on-policy and sample inefficient, fail in adversarial target tasks, and often require heuristic choices in algorithm design. This paper proposes an off-policy Advantage-based Policy Transfer algorithm, APT-RL, for fixed domain environments. Its novelty is in using the popular notion of ``advantage'' as a regularizer, to weigh the knowledge that should be transferred from the source, relative to new knowledge learned in the target, removing the need for heuristic choices. Further, we propose a new transfer performance measure to evaluate the performance of our algorithm and unify existing transfer RL frameworks. Finally, we present a scalable, theoretically-backed task similarity measurement algorithm to illustrate the alignments between our proposed transferability measure and similarities between source and target environments. We compare APT-RL with several baselines, including existing transfer-RL algorithms, in three high-dimensional continuous control tasks. Our experiments demonstrate that APT-RL outperforms existing transfer RL algorithms and is at least as good as learning from scratch in adversarial tasks.

Raman Ebrahimi, Kristen Vaccaro, Parinaz Naghizadeh

When humans are subject to an algorithmic decision system, they can strategically adjust their behavior accordingly (``game'' the system). While a growing line of literature on strategic classification has used game-theoretic modeling to understand and mitigate such gaming, these existing works consider standard models of fully rational agents. In this paper, we propose a strategic classification model that considers behavioral biases in human responses to algorithms. We show how misperceptions of a classifier (specifically, of its feature weights) can lead to different types of discrepancies between biased and rational agents' responses, and identify when behavioral agents over- or under-invest in different features. We also show that strategic agents with behavioral biases can benefit or (perhaps, unexpectedly) harm the firm compared to fully rational strategic agents. We complement our analytical results with user studies, which support our hypothesis of behavioral biases in human responses to the algorithm. Together, our findings highlight the need to account for human (cognitive) biases when designing AI systems, and providing explanations of them, to strategic human in the loop.

Ruey-An Shiu, Parinaz Naghizadeh

This paper studies opinion dynamics in multilayer social networks. Extending a single-layer model, we formulate opinion updates as a synchronous coordination game in which agents minimize a local cost to stay close to their neighbors' opinions. We propose two coupling mechanisms: (i) a merged model that aggregates layers through weighted influences, and (ii) a switching model that periodically alternates across layers. Using random-walk and spectral analysis, we derive sufficient conditions for consensus, characterize convergence rates, and analyze stability under network perturbations. We show that multilayer interactions can induce or accelerate global consensus even when no single layer achieves it alone, and conversely, that individually coordinated layers may lose consensus once interconnected. Numerical experiments validate the theory and highlight the impact of layer weights and switching periods. These results clarify how cross-network interactions shape coordination and information diffusion across interconnected systems.

Yifan Yang, Yang Liu, Parinaz Naghizadeh

The performance of algorithmic decision rules is largely dependent on the quality of training datasets available to them. Biases in these datasets can raise economic and ethical concerns due to the resulting algorithms' disparate treatment of different groups. In this paper, we propose algorithms for sequentially debiasing the training dataset through adaptive and bounded exploration in a classification problem with costly and censored feedback. Our proposed algorithms balance between the ultimate goal of mitigating the impacts of data biases -- which will in turn lead to more accurate and fairer decisions, and the exploration risks incurred to achieve this goal. Specifically, we propose adaptive bounds to limit the region of exploration, and leverage intermediate actions which provide noisy label information at a lower cost. We analytically show that such exploration can help debias data in certain distributions, investigate how {algorithmic fairness interventions} can work in conjunction with our proposed algorithms, and validate the performance of these algorithms through numerical experiments on synthetic and real-world data.

Yiqiao Liao, Farinaz Koushanfar, Parinaz Naghizadeh

Unsupervised neural combinatorial optimization (NCO) enables learning powerful solvers without access to ground-truth solutions. Existing approaches fall into two disjoint paradigms: models trained for generalization across instances, and instance-specific models optimized independently at test time. While the former are efficient during inference, they lack effective instance-wise adaptability; the latter are flexible but fail to exploit learned inductive structure and are prone to poor local optima. This motivates the central question of our work: how can we leverage the inductive bias learned through generalization while unlocking the flexibility required for effective instance-wise adaptation? We first identify a challenge in bridging these two paradigms: generalization-focused models often constitute poor warm starts for instance-wise optimization, potentially underperforming even randomly initialized models when fine-tuned at test time. To resolve this incompatibility, we propose TACO, a model-agnostic test-time adaptation framework that unifies and extends the two existing paradigms for unsupervised NCO. TACO applies strategic warm-starting to partially relax trained parameters while preserving inductive bias, enabling rapid and effective unsupervised adaptation. Crucially, compared to naively fine-tuning a trained generalizable model or optimizing an instance-specific model from scratch, TACO achieves better solution quality while incurring negligible additional computational cost. Experiments on canonical CO problems, Minimum Vertex Cover and Maximum Clique, demonstrate the effectiveness and robustness of TACO across static, distribution-shifted, and dynamic combinatorial optimization problems, establishing it as a practical bridge between generalizable and instance-specific unsupervised NCO.

Yiqiao Liao, Farinaz Koushanfar, Parinaz Naghizadeh

We introduce DyCO-GNN, a novel unsupervised learning framework for Dynamic Combinatorial Optimization that requires no training data beyond the problem instance itself. DyCO-GNN leverages structural similarities across time-evolving graph snapshots to accelerate optimization while maintaining solution quality. We evaluate DyCO-GNN on dynamic maximum cut, maximum independent set, and the traveling salesman problem across diverse datasets of varying sizes, demonstrating its superior performance under tight and moderate time budgets. DyCO-GNN consistently outperforms the baseline methods, achieving high-quality solutions up to 3-60x faster, highlighting its practical effectiveness in rapidly evolving resource-constrained settings.

Sura Alhanouti, Parinaz Naghizadeh

As machine learning algorithms increasingly influence critical decision making in different application areas, understanding human strategic behavior in response to these systems becomes vital. We explore individuals' choice between genuinely improving their qualifications (``improvement'') vs. attempting to deceive the algorithm by manipulating their features (``manipulation'') in response to an algorithmic decision system. We further investigate an algorithm designer's ability to shape these strategic responses, and its fairness implications. Specifically, we formulate these interactions as a Stackelberg game, where a firm deploys a (fair) classifier, and individuals strategically respond. Our model incorporates both different costs and stochastic efficacy for manipulation and improvement. The analysis reveals different potential classes of agent responses, and characterizes optimal classifiers accordingly. Based on these, we highlight the impact of the firm's anticipation of strategic behavior, identifying when and why a (fair) strategic policy can not only prevent manipulation, but also incentivize agents to opt for improvement.

Yifan Yang, Ali Payani, Parinaz Naghizadeh

Generalization error bounds from learning theory provide statistical guarantees on how well an algorithm will perform on previously unseen data. In this paper, we characterize the impacts of data non-IIDness due to censored feedback (a.k.a. selective labeling bias) on such bounds. Censored feedback is ubiquitous in many real-world online selection and classification tasks (e.g., hiring, lending, recommendation systems) where the true label of a data point is only revealed if a favorable decision is made (e.g., accepting a candidate, approving a loan, displaying an ad), and remains unknown otherwise. We first derive an extension of the well-known Dvoretzky-Kiefer-Wolfowitz (DKW) inequality, which characterizes the gap between empirical and theoretical data distribution CDFs learned from IID data, to problems with non-IID data due to censored feedback. We then use this CDF error bound to provide a bound on the generalization error guarantees of a classifier trained on such non-IID data. We show that existing generalization error bounds (which do not account for censored feedback) fail to correctly capture the model's generalization guarantees, verifying the need for our bounds. We further analyze the effectiveness of (pure and bounded) exploration techniques, proposed by recent literature as a way to alleviate censored feedback, on improving our error bounds. Together, our findings illustrate how a decision maker should account for the trade-off between strengthening the generalization guarantees of an algorithm and the costs incurred in data collection when future data availability is limited by censored feedback.

Yifan Yang, Yang Liu, Parinaz Naghizadeh

Biases in existing datasets used to train algorithmic decision rules can raise ethical and economic concerns due to the resulting disparate treatment of different groups. We propose an algorithm for sequentially debiasing such datasets through adaptive and bounded exploration in a classification problem with costly and censored feedback. Exploration in this context means that at times, and to a judiciously-chosen extent, the decision maker deviates from its (current) loss-minimizing rule, and instead accepts some individuals that would otherwise be rejected, so as to reduce statistical data biases. Our proposed algorithm includes parameters that can be used to balance between the ultimate goal of removing data biases -- which will in turn lead to more accurate and fair decisions, and the exploration risks incurred to achieve this goal. We analytically show that such exploration can help debias data in certain distributions. We further investigate how fairness criteria can work in conjunction with our data debiasing algorithm. We illustrate the performance of our algorithm using experiments on synthetic and real-world datasets.

Mustafa Abdallah, Daniel Woods, Parinaz Naghizadeh et al.

We model the behavioral biases of human decision-making in securing interdependent systems and show that such behavioral decision-making leads to a suboptimal pattern of resource allocation compared to non-behavioral (rational) decision-making. We provide empirical evidence for the existence of such behavioral bias model through a controlled subject study with 145 participants. We then propose three learning techniques for enhancing decision-making in multi-round setups. We illustrate the benefits of our decision-making model through multiple interdependent real-world systems and quantify the level of gain compared to the case in which the defenders are behavioral. We also show the benefit of our learning techniques against different attack models. We identify the effects of different system parameters on the degree of suboptimality of security outcomes due to behavioral decision-making.

Mustafa Abdallah, Daniel Woods, Parinaz Naghizadeh et al.

We study the security of large-scale cyber-physical systems (CPS) consisting of multiple interdependent subsystems, each managed by a different defender. Defenders invest their security budgets with the goal of thwarting the spread of cyber attacks to their critical assets. We model the security investment decisions made by the defenders as a security game. While prior work has used security games to analyze such scenarios, we propose behavioral security games, in which defenders exhibit characteristics of human decision making that have been identified in behavioral economics as representing typical human cognitive biases. This is important as many of the critical security decisions in our target class of systems are made by humans. We provide empirical evidence for our behavioral model through a controlled subject experiment. We then show that behavioral decision making leads to a suboptimal pattern of resource allocation compared to non-behavioral decision making. We illustrate the effects of behavioral decision making using two representative real-world interdependent CPS. In particular, we identify the effects of the defenders' security budget availability and distribution, the degree of interdependency among defenders, and collaborative defense strategies, on the degree of suboptimality of security outcomes due to behavioral decision making. In this context, the adverse effects of behavioral decision making are most severe with moderate defense budgets. Moreover, the impact of behavioral suboptimal decision making is magnified as the degree of the interdependency between subnetworks belonging to different defenders increases. We also observe that selfish defense decisions together with behavioral decisions significantly increase security risk.

Parinaz Naghizadeh, Mingyan Liu

Information sharing among organizations has been gaining attention as a method for improving cybersecurity. However, the associated disclosure costs act as deterrents for firms' voluntary cooperation. In this work, we take a game-theoretic approach to understanding firms' incentives in these agreements. We propose the design of inter-temporal incentives (i.e. conditioning future cooperation on past interactions). Specifically, we show that incentives for full cooperation can be designed if firms share their private assessments of other firms' disclosure decisions through a common communication platform. We further show that similar incentives can be designed based on outcomes of a public rating/assessment system.

Parinaz Naghizadeh, Mingyan Liu

The reliability and security of a user in an interconnected system depends on all users' collective effort in security. Consequently, investments in security technologies by strategic users is typically modeled as a public good problem, known as the Interdependent Security (IDS) game. The equilibria for such games are often inefficient, as selfish users free-ride on positive externalities of others' contributions. In this paper, we present a mechanism that implements the socially optimal equilibrium in an IDS game through a message exchange process, in which users submit proposals about the security investment and tax/price profiles of one another. This mechanism is different from existing solutions in that (1) it results in socially optimal levels of investment, closing the Price of Anarchy gap in the IDS game, (2) it is applicable to a general model of user interdependencies. We further consider the issue of individual rationality, often a trivial condition to satisfy in many resource allocation problems, and argue that with positive externality, the incentive to stay out and free-ride on others' investment can make individual rationality much harder to satisfy in designing a mechanism.