📊 Results from the reproducibility and benchmarking studies presented in "Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework" (http://arxiv.org/abs/2006.13365)
Not every 'study.json' file has the entry 'create_inverse_triples', e.g.:
ablation/results/rotate/wn18rr/random/adam/2020-04-25-19-04_217bcf38-2101-461b-9593-b133b4201e6a/0000_wn18rr_rotate/study.json
which distorts the configuration. The correct information can be extracted from 'pipeline_config.json' which is contained in the 'best_pipeline' directory
Not every 'study.json' file has the entry 'create_inverse_triples', e.g.: ablation/results/rotate/wn18rr/random/adam/2020-04-25-19-04_217bcf38-2101-461b-9593-b133b4201e6a/0000_wn18rr_rotate/study.json
But a default value is set:
https://github.com/mali-git/pykeen_experimental_results/blob/cd2f6a3a58faf8ffdfaf049b1d0755984fef473d/ablation/collate.py#L117
which distorts the configuration. The correct information can be extracted from 'pipeline_config.json' which is contained in the 'best_pipeline' directory