2022 Fiscal Year Research-status Report
Advanced deep graph neural networks for explainable anomaly detection study
| Project/Area Number |
22K17961
|
|---|
| Research Institution | National Institute of Advanced Industrial Science and Technology |
|---|
Principal Investigator |
Ouyang Tinghui 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 研究員 (80870849)
|
|---|
| Project Period (FY) |
2022-04-01 – 2025-03-31
|
| Keywords | granular computing / data mining / anomaly data detection / information graph / structure description / explanation / graph neural network |
|---|
| Outline of Annual Research Achievements |
In this fiscal year, there are totally three achievements achieved, including granular data description, granular ADD algorithms and its application.
The first achievement is about granular data description, we have developed advanced granular computing for data description, aiming to reduce the computation cost of big data analysis. Especially, structural granules are constructed for data distribution description and data structure mining in this task.
The second one is about anomaly data detection algorithms. By making use of the constructed granules, especially ones having the ability of describing data structure, a primary anomaly data detection method via rule-based modeling method was built. Its performance was evaluated good on both supervised scenarios with noise and unsupervised scenarios.
The third achievement is about completing some industrial applications related to anomaly data detection. Through these applications, it is verified useful by considering data structure information in anomaly data detection.
|
| Current Status of Research Progress |
Current Status of Research Progress
1: Research has progressed more than it was originally planned.
Reason
According to the proposal, our current progress is going well, well match the planned timeline without any delays. There are several journal and conference papers have been published based on the work in this fiscal year. Therefore, in the next step, we can successfully make use of the current results to the second part of research, such as the data structure information for information graph learning and GNN-based anomaly detection algorithm.
|
| Strategy for Future Research Activity |
According to the plan in the proposal, we will focus on leveraging the constructed structural granules for developing advanced anomaly data detection algorithms. It will contain the following three topics, 1) how to make use of granular structure descriptors to learn data structure information, especially information graph with data structure information. 2) how to make use of information graph in graph neural networks development, especially GNN algorithms for anomaly data detection. 3) We will continue solving various practical problems and applications related to anomaly data detection
|
| Causes of Carryover |
In this fiscal year, the funding would be used for the support of buying some storage and computing devices, like GPU for large database and graph computing. Moreover, support fee for some on-site conferences will be used.
|
