Ashkan Rezaei

Abtin TorabNezhad, Azam Bastanfard, Ashkan Rezaei

This paper introduces the Data-Driven Animation Controller (DDAC), a specialized Godot component that achieves robust decoupling of animation logic from core gameplay scripts through a data-driven approach. Animation control is typically centralized and imperatively defined within core character scripts, often relying on implicit Finite State Machines (FSMs). This practice leads to tightly coupled and difficult-to-maintain codebases. The DDAC component externalizes these instructions into easily inspector-editable resources, effectively making the animation logic declarative. Rules are defined by reading Conditions from any variable on any external node and executing Actions (setting the target animation). The DDAC also manages secondary visual state settings, such as Animation Speed Scaling and Horizontal/Vertical Sprite Flipping, using the same simple rule-based setup. The highest contribution of this work is the use of a Prioritized Resolution Algorithm to enforce mutual exclusion, ensuring that when multiple rules match, only the highest-priority rule executes. This framework allows designers to quickly iterate on character-state visualization without modifying code, while significantly improving maintainability and reducing cognitive load on core developers.

Omid Memarrast, Ashkan Rezaei, Rizal Fathony et al.

While conventional ranking systems focus solely on maximizing the utility of the ranked items to users, fairness-aware ranking systems additionally try to balance the exposure for different protected attributes such as gender or race. To achieve this type of group fairness for ranking, we derive a new ranking system based on the first principles of distributional robustness. We formulate a minimax game between a player choosing a distribution over rankings to maximize utility while satisfying fairness constraints against an adversary seeking to minimize utility while matching statistics of the training data. We show that our approach provides better utility for highly fair rankings than existing baseline methods.

Ashkan Rezaei, Anqi Liu, Omid Memarrast et al.

Making predictions that are fair with regard to protected group membership (race, gender, age, etc.) has become an important requirement for classification algorithms. Existing techniques derive a fair model from sampled labeled data relying on the assumption that training and testing data are identically and independently drawn (iid) from the same distribution. In practice, distribution shift can and does occur between training and testing datasets as the characteristics of individuals interacting with the machine learning system change. We investigate fairness under covariate shift, a relaxation of the iid assumption in which the inputs or covariates change while the conditional label distribution remains the same. We seek fair decisions under these assumptions on target data with unknown labels. We propose an approach that obtains the predictor that is robust to the worst-case in terms of target performance while satisfying target fairness requirements and matching statistical properties of the source data. We demonstrate the benefits of our approach on benchmark prediction tasks.

Ashkan Rezaei, Rizal Fathony, Omid Memarrast et al.

Developing classification methods with high accuracy that also avoid unfair treatment of different groups has become increasingly important for data-driven decision making in social applications. Many existing methods enforce fairness constraints on a selected classifier (e.g., logistic regression) by directly forming constrained optimizations. We instead re-derive a new classifier from the first principles of distributional robustness that incorporates fairness criteria into a worst-case logarithmic loss minimization. This construction takes the form of a minimax game and produces a parametric exponential family conditional distribution that resembles truncated logistic regression. We present the theoretical benefits of our approach in terms of its convexity and asymptotic convergence. We then demonstrate the practical advantages of our approach on three benchmark fairness datasets.

Rizal Fathony, Ashkan Rezaei, Mohammad Ali Bashiri et al.

In many structured prediction problems, complex relationships between variables are compactly defined using graphical structures. The most prevalent graphical prediction methods---probabilistic graphical models and large margin methods---have their own distinct strengths but also possess significant drawbacks. Conditional random fields (CRFs) are Fisher consistent, but they do not permit integration of customized loss metrics into their learning process. Large-margin models, such as structured support vector machines (SSVMs), have the flexibility to incorporate customized loss metrics, but lack Fisher consistency guarantees. We present adversarial graphical models (AGM), a distributionally robust approach for constructing a predictor that performs robustly for a class of data distributions defined using a graphical structure. Our approach enjoys both the flexibility of incorporating customized loss metrics into its design as well as the statistical guarantee of Fisher consistency. We present exact learning and prediction algorithms for AGM with time complexity similar to existing graphical models and show the practical benefits of our approach with experiments.

Hong Wang, Ashkan Rezaei, Brian D. Ziebart

Many predicted structured objects (e.g., sequences, matchings, trees) are evaluated using the F-score, alignment error rate (AER), or other multivariate performance measures. Since inductively optimizing these measures using training data is typically computationally difficult, empirical risk minimization of surrogate losses is employed, using, e.g., the hinge loss for (structured) support vector machines. These approximations often introduce a mismatch between the learner's objective and the desired application performance, leading to inconsistency. We take a different approach: adversarially approximate training data while optimizing the exact F-score or AER. Structured predictions under this formulation result from solving zero-sum games between a predictor seeking the best performance and an adversary seeking the worst while required to (approximately) match certain structured properties of the training data. We explore this approach for word alignment (AER evaluation) and named entity recognition (F-score evaluation) with linear-chain constraints.