Work

On Interpretability of Linear Autoencoders

Year: 2024

Type: conference-paper

Abstract: We derive a novel graph-based interpretation of linear autoencoder models easer, slim, and their approximate variants. Contrary to popular belief, we reveal that the weights of these models should not be interpreted as dichotomic item similarity but merely as its magnitude. Consequently, we propose a simple modification that considerably improves retrieval ability in sparse domains and yields interpretable inference with negative inputs, as demonstrated by both offline and online experiments. Experiment codes and extended results are available at https://osf.io/bjmuv/.

Source: ACM Conference on Recommender Systems (RecSys)

DOI: 10.1145/3640457.3688179

Authors: Martin Spišák, Radek Bartyzal, Antonín Hoskovec, Ladislav Peška

Institutions: Czech Technical University in Prague, Charles University

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W4403220874

FWCI: 0.588

Cites: 27

Cited by: 2

Related to: 10