Recent progress in Text-to-Image (T2I) models promises transformative applications in art, design, education, medicine, and entertainment. These models, exemplified by Dall-e, Imagen, and Stable Diffusion, have the potential to revolutionize various industries. However, a primary concern is their operation as a ‘black-box’ for many users. Without understanding the underlying mechanics, users are unable to harness the full potential of these models. This study focuses on bridging this gap by developing and evaluating explanation techniques for T2I models, targeting inexperienced end users. While prior works have delved into Explainable AI (XAI) methods for classification or regression tasks, T2I generation poses distinct challenges. Through formative studies with experts, we identified unique explanation goals and subsequently designed tailored explanation strategies. We then empirically evaluated these methods with a cohort of 473 participants from Amazon Mechanical Turk (AMT) across three tasks. Our results highlight users’ ability to learn new keywords through explanations, a preference for example-based explanations, and challenges in comprehending explanations that significantly shift the image’s theme. Moreover, findings suggest users benefit from a limited set of concurrent explanations. Our main contributions include a curated dataset for evaluating T2I explainability techniques, insights from a comprehensive AMT user study, and observations critical for future T2I model explainability research.

Generative adversarial networks (GANs) have many application areas including image editing, domain translation, missing data imputation, and support for creative work. However, GANs are considered ‘black boxes’. Specifically, the end-users have little control over how to improve editing directions through disentanglement. Prior work focused on new GAN architectures to disentangle editing directions. Alternatively, we propose GANravel—a user-driven direction disentanglement tool that complements the existing GAN architectures and allows users to improve editing directions iteratively. In two user studies with 16 participants each, GANravel users were able to disentangle directions and outperformed the state-of-the-art direction discovery baselines in disentanglement performance. In the second user study, GANravel was used in a creative task of creating dog memes and was able to create high-quality edited images and GIFs.

Generative Adversarial Network (GAN) is widely adopted in numerous application areas, such as data preprocessing, image editing, and creativity support. However, GAN’s ‘black box’ nature prevents non-expert users from controlling what data a model generates, spawning a plethora of prior work that focused on algorithm-driven approaches to extract editing directions to control GAN. Complementarily, we propose a GANzilla—a user-driven tool that empowers a user with the classic scatter/gather technique to iteratively discover directions to meet their editing goals. In a study with 12 participants, GANzilla users were able to discover directions that (i) edited images to match provided examples (closed-ended tasks) and that (ii) met a high-level goal, e.g., making the face happier, while showing diversity across individuals (open-ended tasks).

In this article, we address the scheduling problem in wireless ad hoc networks by exploiting the computational advantage that comes when scheduling problems can be represented by claw-free conflict graphs where we consider a wireless broadcast medium. It is possible to formulate a scheduling problem of broadcast transmissions as finding the maximum weighted independent set (MWIS) in the conflict graph of the network. Finding the MWIS of a general graph is NP-hard leading to an NP-hard complexity of scheduling. In a claw-free conflict graph, MWIS may be found in polynomial time leading to a throughput-optimal scheduling. We show that the conflict graphs of certain wireless ad hoc networks are claw-free. In order to obtain claw-free conflict graphs in general networks, we suggest introducing additional conflicts (edges) with the aim of keeping the decrease in MWIS size minimal. To this end, we introduce an iterative optimization problem to decide where to introduce edges and investigate its efficient implementation. We conclude that the claw breaking method by adding extra edges can perform very close to optimal scenario and better than the polynomial time maximal independent set scheduling benchmark under the necessary assumptions.

We consider decentralized stochastic multi-armed bandit problem with multiple players in the case of different communication probabilities between players. Each player makes a decision of pulling an arm without cooperation while aiming to maximize his or her reward but informs his or her neighbors in the end of every turn about the arm he or she pulled and the reward he or she got. Neighbors of players are determined according to an Erdos-Rényi graph with connectivity α which is reproduced in the beginning of every turn. We consider i.i.d. rewards generated by a Bernoulli distribution and assume that players are unaware about the arms' probability distributions and their mean values. In case of a collision, we assume that only one of the players who is randomly chosen gets the reward where the others get zero reward. We study the effects of α, the degree of communication between players, on the cumulative regret using well-known algorithms UCB1, εGreedy and Thompson Sampling.

In this paper, our goal is to compare performances of three different algorithms to predict the ratings that will be given to movies by potential users where we are given a user-movie rating matrix based on the past observations. To this end, we evaluate User-Based Collaborative Filtering, Iterative Matrix Factorization and Yehuda Koren's Integrated model using neighborhood and factorization where we use root mean square error (RMSE) as the performance evaluation metric. In short, we do not observe significant differences between performances, especially when the complexity increase is considered. We can conclude that Iterative Matrix Factorization performs fairly well despite its simplicity.