Hiroyuki Ishihara

Hideki Nishizawa, Kazuya Anazawa, Tetsuro Inui et al.

This paper presents a data center exchange (Data Center Xchange, DCX) architecture for all-photonics networks-as-a-service in distributed data center infrastructures, enabling the creation of a virtual large-scale data center by directly interconnecting distributed data centers in metropolitan areas. Key requirements for such an architecture are identified: support for low-latency operations, scalability, reliability, and flexibility within a single network architecture; the ability to add new operator-driven automation functionalities based on an open networking approach; and the ability to control and manage remotely deployed transponders connected via access links with unknown physical parameters. We propose a set of technologies that enable digital twin operations for optical networks, including a cloud-native architecture for coherent transceivers, remote transponder control, fast end-to-end optical path provisioning, transceiver-based physical-parameter estimation incorporating digital longitudinal monitoring, and optical line system calibration, demonstrating their feasibility through field validations.

Thomas Henn, Yasukazu Sakamoto, Clément Jacquet et al.

Machine learning models commonly exhibit unexpected failures post-deployment due to either data shifts or uncommon situations in the training environment. Domain experts typically go through the tedious process of inspecting the failure cases manually, identifying failure modes and then attempting to fix the model. In this work, we aim to standardise and bring principles to this process through answering two critical questions: (i) how do we know that we have identified meaningful and distinct failure types?; (ii) how can we validate that a model has, indeed, been repaired? We suggest that the quality of the identified failure types can be validated through measuring the intra- and inter-type generalisation after fine-tuning and introduce metrics to compare different subtyping methods. Furthermore, we argue that a model can be considered repaired if it achieves high accuracy on the failure types while retaining performance on the previously correct data. We combine these two ideas into a principled framework for evaluating the quality of both the identified failure subtypes and model repairment. We evaluate its utility on a classification and an object detection tasks. Our code is available at https://github.com/Rokken-lab6/Failure-Analysis-and-Model-Repairment