AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Feature Interactions with Lorentzian Factorization Machine

Canran Xu, Ming Wu

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 33 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use Lorentz triangle-inequality feature interaction pooling instead of conventional deep feature-interaction layersLorentzFM · SteamMRR: 0.1284 -> 0.1362Improved
Use Lorentz triangle-inequality feature interaction pooling instead of conventional deep feature-interaction layersLorentzFM · KKBoxMRR: 0.0644 -> 0.0733Improved
Use Lorentz triangle-inequality feature interaction pooling instead of conventional deep feature-interaction layersLorentzFM · AvazuAUC: 0.7677 -> 0.7775Improved
Use Lorentz triangle-inequality feature interaction pooling instead of conventional deep feature-interaction layersLorentzFM · MovieLensMRR: 0.0791 -> 0.0780Hurt
Increase embedding sizeLorentzFM · SteamperformanceImproved
Remove the deep learning layers above feature interactions by using LorentzFM's lightweight architectureLorentzFM · MovieLenstraining parameters: 82.9%Improved
Remove the deep learning layers above feature interactions by using LorentzFM's lightweight architectureLorentzFM · MovieLenstraining time per epoch: 69.7%Improved
Use LorentzFM's lightweight architectureLorentzFM · Steamtraining time per epoch: -8.1%Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy