Mitigating Emergent Robustness Degradation while Scaling Graph Learning

X Yuan, C Zhang, Y Tian, Y Ye… - The Twelfth International …, 2024 - openreview.net
Although graph neural networks have exhibited remarkable performance in various graph
tasks, a significant concern is their vulnerability to adversarial attacks. Consequently, many …

How to Improve Representation Alignment and Uniformity in Graph-based Collaborative Filtering?

Z Ouyang, C Zhang, S Hou, C Zhang… - Proceedings of the …, 2024 - ojs.aaai.org
Collaborative filtering (CF) is a prevalent technique utilized in recommender systems (RSs),
and has been extensively deployed in various real-world applications. A recent study in CF …

Graph Cross Supervised Learning via Generalized Knowledge

X Yuan, Y Tian, C Zhang, Y Ye, NV Chawla… - Proceedings of the 30th …, 2024 - dl.acm.org
The success of GNNs highly relies on the accurate labeling of data. Existing methods of
ensuring accurate labels, such as weakly-supervised learning, mainly focus on the existing …

Symbolic Prompt Tuning Completes the App Promotion Graph

Z Ouyang, C Zhang, S Hou, S Ma, C Chen, T Li… - … Conference on Machine …, 2024 - Springer
Recent mobile applications (ie, apps) have been extensively implanted with paid
advertisements that promote other mobile apps, including malware that raises alarming …

[PDF][PDF] Knowledge-centric Machine Learning on Graphs

Y Tian - 2024 - curate.nd.edu
Relational data, especially graphs where entities are represented as nodes and the
relations connecting them are denoted as edges, have become a common language for …