all AI news
Knowing Your Nonlinearities: Shapley Interactions Reveal the Underlying Structure of Data
March 21, 2024, 4:41 a.m. | Divyansh Singhvi, Andrej Erkelens, Raghav Jain, Diganta Misra, Naomi Saphra
cs.LG updates on arXiv.org arxiv.org
Abstract: Measuring nonlinear feature interaction is an established approach to understanding complex patterns of attribution in many models. In this paper, we use Shapley Taylor interaction indices (STII) to analyze the impact of underlying data structure on model representations in a variety of modalities, tasks, and architectures. Considering linguistic structure in masked and auto-regressive language models (MLMs and ALMs), we find that STII increases within idiomatic expressions and that MLMs scale STII with syntactic distance, relying …
abstract analyze arxiv attribution cs.ai cs.cl cs.cv cs.lg data feature impact interactions measuring paper patterns tasks taylor type understanding
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
AI Engineering Manager
@ M47 Labs | Barcelona, Catalunya [Cataluña], Spain