Llmrec: Large language models with graph augmentation for recommendation

W Wei, X Ren, J Tang, Q Wang, L Su, S Cheng… - Proceedings of the 17th …, 2024 - dl.acm.org
The problem of data sparsity has long been a challenge in recommendation systems, and
previous studies have attempted to address this issue by incorporating side information …

A survey of graph prompting methods: techniques, applications, and challenges

X Wu, K Zhou, M Sun, X Wang, N Liu - arXiv preprint arXiv:2303.07275, 2023 - arxiv.org
The recent" pre-train, prompt, predict training" paradigm has gained popularity as a way to
learn generalizable models with limited labeled data. The approach involves using a pre …

Graph neural prompting with large language models

Y Tian, H Song, Z Wang, H Wang, Z Hu… - Proceedings of the …, 2024 - ojs.aaai.org
Large language models (LLMs) have shown remarkable generalization capability with
exceptional performance in various language modeling tasks. However, they still exhibit …

Logit standardization in knowledge distillation

S Sun, W Ren, J Li, R Wang… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Abstract Knowledge distillation involves transferring soft labels from a teacher to a student
using a shared temperature-based softmax function. However the assumption of a shared …

Graph neural networks: a survey on the links between privacy and security

F Guan, T Zhu, W Zhou, KKR Choo - Artificial Intelligence Review, 2024 - Springer
Graph neural networks (GNNs) are models that capture the dependencies between graph
data by passing messages between graph nodes and they have been widely used to …

Fair graph representation learning via diverse mixture-of-experts

Z Liu, C Zhang, Y Tian, E Zhang, C Huang… - Proceedings of the …, 2023 - dl.acm.org
Graph Neural Networks (GNNs) have demonstrated a great representation learning
capability on graph data and have been utilized in various downstream applications …

[PDF][PDF] VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs

L Yang, Y Tian, M Xu, Z Liu, S Hong, W Qu… - arXiv preprint arXiv …, 2023 - researchgate.net
Abstract Graph Neural Networks (GNNs) conduct message passing which aggregates local
neighbors to update node representations. Such message passing leads to scalability …

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 …

[PDF][PDF] Chasing all-round graph representation robustness: Model, training, and optimization

C Zhang, Y Tian, M Ju, Z Liu, Y Ye… - The Eleventh …, 2022 - drive.google.com
ABSTRACT Graph Neural Networks (GNNs) have achieved state-of-the-art results on a
variety of graph learning tasks, however, it has been demonstrated that they are vulnerable …

Aligning relational learning with lipschitz fairness

Y Jia, C Zhang, S Vosoughi - The Twelfth International Conference …, 2024 - openreview.net
Relational learning has gained significant attention, led by the expressiveness of Graph
Neural Networks (GNNs) on graph data. While the inherent biases in common graph data …