To this end, we propose a totally new method named partial graph attack (PGA), which selects the vulnerable nodes as attack targets.
Then, we propose a novel framework to utilize the rich type semantic information in heterogeneous graphs comprehensively, namely HAGNN (Hybrid Aggregation for Heterogeneous GNNs).
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.
In this paper, we propose an efficient automated attacker called A2 to boost AT by generating the optimal perturbations on-the-fly during training.
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.
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.
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.
Bayesian optimization is a broadly applied methodology to optimize the expensive black-box function.