AI Paper Atlas

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

Attention-over-Attention Field-Aware Factorization Machine

Zhibo Wang, Jinxin Ma, Yongquan Zhang, Qian Wang, Ju Ren, Peng Sun

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 11 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
replace AFM attention with attention-over-attention (ablation)FM embeddings (AFM) · Movielens validationRMSE: 0.4339 -> 0.4248Improved
replace AFM attention with attention-over-attention (ablation)FM embeddings (AFM) · Frappe validationRMSE: 0.3089 -> 0.3068Improved
replace AFM attention with attention-over-attention (ablation)FFM embeddings (AFFM) · Movielens validationRMSE: 0.4178 -> 0.4128Improved
replace AFM attention with attention-over-attention (ablation)FFM embeddings (AFFM) · Frappe validationRMSE: 0.3130 -> 0.3116Improved
use field-aware embeddings (FFM) instead of FM embeddings under AoA attention (ablation)AoAFM · Movielens testRMSE: 0.4234 -> 0.4126Improved
use field-aware embeddings (FFM) instead of FM embeddings under AoA attention (ablation)AoAFM · Frappe testRMSE: 0.3112 -> 0.3141Hurt
AoAFFM vs FFM (add AoA attention)FFM · Criteo testRMSE: 0.3851 -> 0.3808Improved
AoAFFM vs FFM (add AoA attention)FFM · Movielens testRMSE: 0.4478 -> 0.4126Improved
AoAFFM vs FFM (add AoA attention)FFM · Frappe testRMSE: 0.3345 -> 0.3141Improved
increase regularization strength from 1 to 10 (ablation)AoAFFM/AFM · Movielens validationRMSEHurt
add dropout at proper ratio (ablation)AFM, AoAFFM, FM, FFM · Movielens/Frappe validationRMSEImproved

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