TrustLOG: The Second Workshop on Trustworthy Learning on Graphs

Jingrui He, Jian Kang, Fatemeh Nargesian, Haohui Wang, An Zhang, Dawei Zhou

Abstract: Learning on graphs (LOG) has a profound impact on various high-impact domains, such as information retrieval, social network analysis, computational chemistry and transportation. Despite decades of theoretical development, algorithmic advancements, and open-source systems that answers what the optimal learning results are, concerns about the trustworthiness of state-of-the-art LOG techniques have emerged in practical applications. Consequently, crucial research questions arise: why are LOG techniques untrustworthy with respect to critical social aspects like fairness, transparency, privacy, and security? How can we ensure the trustworthiness of learning algorithms on graphs? To address the increasingly important safety and ethical challenges in learning on graphs, it is essential to achieve a paradigm shift from solely addressing what questions to understanding how and why questions. Building upon the success of the first TrustLOG workshop in 2022, the second TrustLOG workshop aims to bring together researchers and practitioners to present, discuss, and advance cutting-edge research in the realm of trustworthy learning on graphs. The workshop serves as a platform to stimulate the TrustLOG community, fostering the identification of new research challenges, and shedding light on potential future directions.