Fast federated machine unlearning with nonlinear functional theory
Federated machine unlearning (FMU) aims to remove the influence of a specified subset of
training data upon request from a trained federated learning model. Despite achieving …
training data upon request from a trained federated learning model. Despite achieving …
Prompt certified machine unlearning with randomized gradient smoothing and quantization
The right to be forgotten calls for efficient machine unlearning techniques that make trained
machine learning models forget a cohort of data. The combination of training and unlearning …
machine learning models forget a cohort of data. The combination of training and unlearning …
Expressive 1-lipschitz neural networks for robust multiple graph learning against adversarial attacks
Recent findings have shown multiple graph learning models, such as graph classification
and graph matching, are highly vulnerable to adversarial attacks, ie small input …
and graph matching, are highly vulnerable to adversarial attacks, ie small input …
Federated fingerprint learning with heterogeneous architectures
Recent studies on federated learning (FL) have sought to solve the system heterogeneity
issue by designing customized local models for different clients. However, public dataset …
issue by designing customized local models for different clients. However, public dataset …
Integrated defense for resilient graph matching
A recent study has shown that graph matching models are vulnerable to adversarial
manipulation of their input which is intended to cause a mismatching. Nevertheless, there is …
manipulation of their input which is intended to cause a mismatching. Nevertheless, there is …
Unsupervised adversarial network alignment with reinforcement learning
Network alignment, which aims at learning a matching between the same entities across
multiple information networks, often suffers challenges from feature inconsistency, high …
multiple information networks, often suffers challenges from feature inconsistency, high …
Adversarial attack against cross-lingual knowledge graph alignment
Recent literatures have shown that knowledge graph (KG) learning models are highly
vulnerable to adversarial attacks. However, there is still a paucity of vulnerability analyses of …
vulnerable to adversarial attacks. However, there is still a paucity of vulnerability analyses of …
Dimension-independent certified neural network watermarks via mollifier smoothing
Certified_Watermarks is the first to provide a watermark certificate against $ l_2 $-norm
watermark removal attacks, by leveraging the randomized smoothing techniques for certified …
watermark removal attacks, by leveraging the randomized smoothing techniques for certified …
Leveraging multi-modal information for cross-lingual entity matching across knowledge graphs
In recent years, the scale of knowledge graphs and the number of entities have grown
rapidly. Entity matching across different knowledge graphs has become an urgent problem …
rapidly. Entity matching across different knowledge graphs has become an urgent problem …
A survey: knowledge graph entity alignment research based on graph embedding
B Zhu, R Wang, J Wang, F Shao, K Wang - Artificial Intelligence Review, 2024 - Springer
Entity alignment (EA) aims to automatically match entities in different knowledge graphs,
which is beneficial to the development of knowledge-driven applications. Representation …
which is beneficial to the development of knowledge-driven applications. Representation …