Skip to yearly menu bar Skip to main content


Spotlight Poster

Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community

Arman Isajanyan · Artur Shatveryan · David Kocharian · Zhangyang Wang · Humphrey Shi

Halle B #45
[ ]
Fri 10 May 1:45 a.m. PDT — 3:45 a.m. PDT

Abstract:

Social reward as a form of community recognition provides a strong source ofmotivation for users of online platforms to actively engage and contribute withcontent to accumulate peers approval. In the realm of text-conditioned imagesynthesis, the recent surge in progress has ushered in a collaborative era whereusers and AI systems coalesce to refine visual creations. This co-creative pro-cess in the landscape of online social networks empowers users to craft originalvisual artworks seeking for community validation. Nevertheless, assessing thesemodels in the context of collective community preference introduces distinct chal-lenges. Existing evaluation methods predominantly center on limited size userstudies guided by image quality and alignment with prompts. This work pio-neers a paradigm shift, unveiling Social Reward - an innovative reward modelingframework that leverages implicit feedback from social network users engagedin creative editing of generated images. We embark on an extensive journey ofdataset curation and refinement, drawing from Picsart: an online visual creationand editing platform, yielding a first million-user-scale dataset of implicit humanpreferences for user-generated visual art named Picsart Image-Social. Our anal-ysis exposes the shortcomings of current metrics in modeling community creativepreference of text-to-image models’ outputs, compelling us to introduce a novelpredictive model explicitly tailored to address these limitations. Rigorous quan-titative experiments and user study show that our Social Reward model alignsbetter with social popularity than existing metrics. Furthermore, we utilize So-cial Reward to fine-tune text-to-image models, yielding images that are more fa-vored by not only Social Reward, but also other established metrics. These find-ings highlight the relevance and effectiveness of Social Reward in assessing com-munity appreciation for AI-generated artworks, establishing a closer alignmentwith users’ creative goals: creating popular visual art. Codes can be accessed athttps://github.com/Picsart-AI-Research/Social-Reward

Chat is not available.