AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction

Bencheng Yan, Pengjie Wang, Kai Zhang, Feng Li, Hongbo Deng, Jian Xu, Bo Zheng

NeurIPS 2022 · Architectures and efficiency › RNNs and normalization · approach: Dataset distillation and data-efficient training · 14 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
add APG to deep CTR models (WDL,PNN,FIBINET,DIFM,DeepFM,DCN,AutoInt)7 deep CTR models · MovieLens/Amazon/IAACAUC: avg 79.46 -> 79.70, 69.06 -> 69.34, 65.26 -> 66.15Improved
generate full per-instance weights (basic APG) (ablation)WDL · 3 datasets avgAUC: 71.18 -> 71.45Improved
low-rank parameterization of generated weights (ablation)basic APG · 3 datasets avgAUC: 71.45 -> 71.45No clear effect
share U,V and generate only center matrix S_i (ablation)low-rank APG · 3 datasets avgAUC: 71.45 -> 71.58Improved
add over-parameterization of shared U,V (ablation)APG v4 · 3 datasets avgAUC: 71.58 -> 71.70Improved
decomposed feed-forwarding and parameter sharing for efficiency (ablation)basic APG · IAAC large MLPtraining time / memory: time -38.7%, memory -96.6% vs BaseImproved
self-wise condition instead of group-wise or mix-wise (ablation)APG · 3 datasetsAUC: e.g. IAAC 65.90 -> 65.94 over mix-wiseImproved
input aggregation instead of output aggregation for mix-wise (ablation)APG mix-wise · 3 datasetsAUC: IAAC 65.70 -> 65.90 (attention)Improved
APG instead of Star/MMoE coarse-grained allocationBase WDL · MovieLens, Amazon, IAACAUC and memory: MovieLens fg 79.28 -> 79.58 (Star vs APG)Improved
enlarge specific-parameter rank K from small to large (beyond 256 no extra gain) (ablation)APG · 3 datasetsAUCMixed
use small P (2-16) instead of large P (32-512) (ablation)APG · 3 datasetsAUCHurt
deploy APG in industrial sponsored searchonline model · IndusDataAUC / CTR / RPM: +0.2% AUC, 3% CTR, 1% RPMImproved

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