
Project directory structure The base profiling folder contains all the files related to the result of training dynamics profiling for all the models tested across the seeds The source folder contains all code related to this project Scheduler_Simple.py: contains the code of the DEBA scheduler with its core mechanism Common.py: contains utility functions and code used to initialize the model tested in this study logger.py: code to log training metrics train.py: the main code used to test and compare DEBA against fixed baselines and profile training dynamics The results folder contains the results of the study, i.e the result of DEBA on the model used for this and the results of each ablation study conducted.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
