Exploring metadiscourse in university lectures in Hong Kong

Abstract

Federated Graph Neural Network (FedGNN) has recently emerged as a rapidly growing research topic, as it integrates the strengths of graph neural networks and federated learning to enable advanced machine learning applications without direct access to sensitive data. Despite its advantages, the distributed nature of FedGNN introduces additional vulnerabilities, particularly backdoor attacks stemming from malicious participants. Although graph backdoor attacks have been explored, the compounded complexity introduced by the combination of GNNs and federated learning has hindered a comprehensive understanding of these attacks, as existing research lacks extensive benchmark coverage and in-depth analysis of critical factors. To address these limitations, we propose Bkd-FedGNN, a benchmark for backdoor attacks on FedGNN. Specifically, Bkd-FedGNN decomposes the graph backdoor attack into trigger generation and injection steps, and extending the attack to the node-level federated setting, resulting in a unified framework that covers both node-level and graph-level classification tasks. Moreover, we thoroughly investigate the impact of multiple critical factors in backdoor attacks on FedGNN. These factors are categorized into global-level and local-level factors, including data distribution, the number of malicious attackers, attack time, overlapping rate, trigger size, trigger type, trigger position, and poisoning rate. Finally, we conduct comprehensive evaluations on 13 benchmark datasets and 13 critical factors, comprising 1,725 experimental configurations for node-level and graphlevel tasks from six domains. These experiments encompass over 8,000 individual tests, allowing us to provide a thorough evaluation and insightful observations that advance our understanding of backdoor attacks on FedGNN. The Bkd-FedGNN benchmark is publicly available at https://github.com/usail-hkust/ BkdFedGCN.Preprint. Under review.

Intelligent Error Compensation in CNC Machining through Synergistic Interactions Among Modeling, Sensing and Learning

“…Finally, the new error compensation methodology on a variety of workpiece profiles (cylindrical as well as complex curved profiles) machined with the same tool/work material combination and machining set up were tested. In each case, the diametral error was smaller than ± 5 µm after compensation, which is close to the same order of the repeatability of the machine [5].…”

“…It is common knowledge that dimensional errors on parts produced by machine are usually several times larger than the axis positioning repeatability of the machines. For instance, when a CNC turning center was tested, it was found that the maximum error was often in the range 50 to 100 µm although the positioning repeatability was only about 4 µm [5]. Thus, it appears that most industrial machines are working well below their accuracy potential today.…”

“…Initially, post-process measurement using a coordinate measuring machine (CMM) was performed. However, the post-process measurement was too elaborate and a novel method of on-machine inspection [5] was applied in this research. Then, the inspection data obtained from the CMM with those from on-machine inspection were critically compared.…”