Print Email Facebook Twitter A Comparison of Instance Attribution Methods Title A Comparison of Instance Attribution Methods: Comparing Instance Attribution Methods to Baseline k-Nearest Neighbors Method Author de Kruif, Evan (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Anand, Avishek (mentor) Corti, L. (graduation committee) Lyu, Lijun (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2023-02-03 Abstract In this research, a comparison between different Instance Attribution (IA) methods and k-Nearest Neighbors (kNN) via cosine similarity is conducted on a Natural Language Processing (NLP) machine learning model. The format in which the comparison is made is by way of a human survey and automated similarity comparisons of representative vectors. The goal of this is to judge and compare the effectiveness of each method’s results in the context of a human’s language understanding and ability to determine if a fact is true or not. Through this research, it was found that for results obtained on the same input, IA methods were preferred 32.5% more often than kNN. It is also shown that this preference is not linked to the similarity between the IA results and the kNN results. Through these findings, it can be seen that when understood through the lens of human comprehension, IA methods are much more effective at generating a set of influential training points from the model’s training dataset. Subject Instance AttributionExplainable AINatural Language ProcessingFact Checking To reference this document use: http://resolver.tudelft.nl/uuid:4864c74b-3e6c-41a8-bfce-f07e8deaa5fc Part of collection Student theses Document type bachelor thesis Rights © 2023 Evan de Kruif Files PDF A_Comparison_of_Instance_ ... Method.pdf 388.27 KB Close viewer /islandora/object/uuid:4864c74b-3e6c-41a8-bfce-f07e8deaa5fc/datastream/OBJ/view