Mitigating Emergent Robustness Degradation while Scaling Graph Learning
Although graph neural networks have exhibited remarkable performance in various graph
tasks, a significant concern is their vulnerability to adversarial attacks. Consequently, many …
tasks, a significant concern is their vulnerability to adversarial attacks. Consequently, many …
How to Improve Representation Alignment and Uniformity in Graph-based Collaborative Filtering?
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 …
and has been extensively deployed in various real-world applications. A recent study in CF …
Graph Cross Supervised Learning via Generalized Knowledge
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 …
ensuring accurate labels, such as weakly-supervised learning, mainly focus on the existing …
Symbolic Prompt Tuning Completes the App Promotion Graph
Recent mobile applications (ie, apps) have been extensively implanted with paid
advertisements that promote other mobile apps, including malware that raises alarming …
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 …
relations connecting them are denoted as edges, have become a common language for …