How AdaSparse Boosts Multi‑Scenario CTR Prediction with Adaptive Sparse Networks

AdaSparse introduces an adaptive sparse network that learns a dedicated sub‑network for each advertising scenario, balancing shared and specific knowledge while keeping computational cost low, and achieves +4.63% CTR and -3.82% CPC improvements in Alibaba’s external ad system, as validated on both public and massive production datasets.

AdvertisingCTR predictionDeep Learning

0 likes · 20 min read

How AdaSparse Boosts Multi‑Scenario CTR Prediction with Adaptive Sparse Networks

AntTech

Feb 13, 2020 · Artificial Intelligence

Ant Group’s Six AI Papers Presented at AAAI 2020

At AAAI 2020, Ant Group showcased six peer‑reviewed papers covering dynamic network pruning, pruning without pre‑training, video‑based auto‑insurance damage assessment, long‑short‑term sample distillation, a span‑based neural buffer for long‑range context, and cost‑effective counterfactual incentive allocation, highlighting the company’s active research in artificial intelligence.

AAAI 2020Ant Groupcounterfactual learning

0 likes · 10 min read

Ant Group’s Six AI Papers Presented at AAAI 2020