Selected Projects:

1. Fairness Auditing Through the Lens of Counterfactual Explanation. (Under Review: IPM journal (IF:7.466)
   Abstract:  A wide variety of fairness metrics and eXplainable Artificial Intelligence (XAI) approaches have been proposed in the literature to identify bias in machine learning (ML) models that are used in critical real-life contexts. We present an approach that ties the evaluation of the fairness of the machine learning model to the expense (or conversely the simplicity) of generating counterfactual explanations (CFE). Given that each change in a feature value puts a cost on the user when creating CFEs, the costs associated with different feature classes vary. Specifically, we propose the Qualification and Effort variables, which, respectively, indicate the candidate's strength and the adjustments that must be made to the candidate's profile in order to alter the classifier's output. To ensure a fair comparison, we condition candidates based on their Qualification scores and evaluate fairness among sensitive group members and different classifiers. We empirically analyze our method on two real-world datasets (Adults Income and Census Income datasets) and utilize KL-divergence to evaluate the fairness of provided classifiers based on the distributions of the CFE effort for several classes of classifiers.
   
   

2. Comparative Explanations for Recommendation: Research Directions

Abstract: Explanations have a long history in recommender systems. Researchers have studied the different roles explanations can play, the value of explanations for users, and different techniques for generating explanations for a given output. To date, we have rarely seen recommender systems make use of comparative explanations, a technique that social scientists emphasize as important in human explanatory behavior. We believe that comparative explanation could be a very powerful tool to augment explanations that recommender systems currently provide and to offer new types of transparency. In this paper, we provide a taxonomy of different types of comparative explanations for recommender systems, emphasizing in particular the potential value of comparative explanations for recommender system providers. We suggest directions for future research to realize this potential rather than providing solutions.

3.  Designing a Sequential Recommendation System for Heterogeneous Interactions Using Transformers.

Abstract:  While many production-ready and robust algorithms are available for the task of recommendation systems, many of these systems do not take the order of user's consumption into account. The order of consumption can be very useful and matters in many scenarios. One such scenario is an educational content recommendation, where users generally follow a progressive path towards more advanced courses. Researchers have used RNNs to build sequential recommendation systems and other models that deal with sequences. Sequential Recommendation systems try to predict the next event for the user by reading their history. With the massive success of Transformers in Natural Language Processing and their usage of Attention Mechanism to better deal with sequences, there have been attempts to use this family of models as a base for a new generation of sequential recommendation systems. In this work, by converting each user's interactions with items into a series of events and basing our architecture on Transformers, we try to enable the use of such a model that takes different types of events into account. Furthermore, by recognizing that some events have to occur before some other types of events take place, we try to modify the architecture to reflect this dependency relationship and enhance the model's performance.

Select Publication: 

M. S. Nejad, M. Varasteh, H. Moradi and M. A. Sadeghi, ‘Designing a sequential recommendation system for heterogeneous interactions using transformers,’ arXiv preprint arXiv:2205.00265, 2022. 

[Full Paper][Code]

4.  An Improved Hybrid Recommender System: Integrating Document Context-Based and Behavior-Base Methods.

Abstract: One of the main challenges in recommender systems is data sparsity, which leads to high variance. Several attempts have been made to improve the bias-variance trade-off using auxiliary information. In particular, document modeling-based methods have improved the model's accuracy by using textual data such as reviews, abstracts, and storylines when the user-to-item rating matrix is sparse. However, such models are insufficient to learn optimal representation for users and items. For building recommender systems, user-based and item-based collaborative filtering have long been used due to their efficiency. A user and item profile are created based on their historically interacted items and the users who interacted with the target item. In spite of the fact that these two approaches have been studied separately, there has been little research into combining them.

    The purpose of this study is to combine these two approaches by considering the opinions of users on these items. Each user is represented by their historical behavior, while each item is represented by the users who have interacted with it before, combined with contextual information, which is processed with NLP. The proposed algorithm is implemented and tested on three real-world datasets that demonstrate our model's effectiveness over the baseline methods.

Select Publication: 

M. Varasteh, M. S. Nejad, H. Moradi, M. A. Sadeghi and A. Kalhor, ‘An improved hybrid recommender system: Integrating document context-based  and behavior-based methods,’ arXiv preprint   arXiv:2109.05516 , 2021.
[Full Paper][Code]

5. Designing a Content-Based Book Recommender System For an Iranian e-Book store named Taghche.

6. Designing a Sequential Recommendation System for Course-Selection based on Natural Language Processing For an Iranian Course Selection Provider named Maktabkhooneh.