Search Results for author: Guanghui Zhu

Found 8 papers, 5 papers with code

Simple and Efficient Partial Graph Adversarial Attack: A New Perspective

1 code implementation15 Aug 2023 Guanghui Zhu, Mengyu Chen, Chunfeng Yuan, Yihua Huang

To this end, we propose a totally new method named partial graph attack (PGA), which selects the vulnerable nodes as attack targets.

Adversarial Attack

HAGNN: Hybrid Aggregation for Heterogeneous Graph Neural Networks

no code implementations4 Jul 2023 Guanghui Zhu, Zhennan Zhu, Hongyang Chen, Chunfeng Yuan, Yihua Huang

Then, we propose a novel framework to utilize the rich type semantic information in heterogeneous graphs comprehensively, namely HAGNN (Hybrid Aggregation for Heterogeneous GNNs).

Link Prediction Node Classification +1

AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network

1 code implementation8 Jan 2023 Guanghui Zhu, Zhennan Zhu, Wenjie Wang, Zhuoer Xu, Chunfeng Yuan, Yihua Huang

Moreover, to improve the performance of the downstream graph learning task, attribute completion and the training of the heterogeneous GNN should be jointly optimized rather than viewed as two separate processes.

Graph Learning Node Clustering

A2: Efficient Automated Attacker for Boosting Adversarial Training

1 code implementation7 Oct 2022 Zhuoer Xu, Guanghui Zhu, Changhua Meng, Shiwen Cui, ZhenZhe Ying, Weiqiang Wang, Ming Gu, Yihua Huang

In this paper, we propose an efficient automated attacker called A2 to boost AT by generating the optimal perturbations on-the-fly during training.

Adversarial Defense

Knowledge-enhanced Black-box Attacks for Recommendations

no code implementations21 Jul 2022 Jingfan Chen, Wenqi Fan, Guanghui Zhu, Xiangyu Zhao, Chunfeng Yuan, Qing Li, Yihua Huang

Recent studies have shown that deep neural networks-based recommender systems are vulnerable to adversarial attacks, where attackers can inject carefully crafted fake user profiles (i. e., a set of items that fake users have interacted with) into a target recommender system to achieve malicious purposes, such as promote or demote a set of target items.

Recommendation Systems

Transition Relation Aware Self-Attention for Session-based Recommendation

no code implementations12 Mar 2022 Guanghui Zhu, Haojun Hou, Jingfan Chen, Chunfeng Yuan, Yihua Huang

Specifically, TRASA first converts the session to a graph and then encodes the shortest path between items through the gated recurrent unit as their transition relation.

Session-Based Recommendations

DIFER: Differentiable Automated Feature Engineering

1 code implementation17 Oct 2020 Guanghui Zhu, Zhuoer Xu, Xu Guo, Chunfeng Yuan, Yihua Huang

Extensive experiments on classification and regression datasets demonstrate that DIFER can significantly improve the performance of various machine learning algorithms and outperform current state-of-the-art AutoFE methods in terms of both efficiency and performance.

Automated Feature Engineering BIG-bench Machine Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.