AI Paper Atlas

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

Little Is Much: Bridging Cross-Platform Behaviors through Overlapped Crowds

Meng Jiang, Peng Cui, Nicholas Jing Yuan, Xing Xie, Shiqiang Yang

AAAI 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 66 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 pairwise-similarity supervision from overlapping users instead of hard-aligned latent spaces (ablation)XPTRANS · Tweet entity -> Douban movie, non-overlappingRMSE: 1.164 -> 0.722Improved
use pairwise-similarity constraints instead of aligned latent features (ablation)XPTRANS · Tweet entity -> Douban movie, non-overlappingMAP: 0.702 -> 0.820Improved
use XPTRANS vs CBT for non-overlapping userscross-platform transfer · Tweet entity -> Douban movieRMSE: 1.290 -> 0.722Improved
use XPTRANS vs CBT for overlapping userscross-platform transfer · Tweet entity -> Douban movieRMSE: 0.767 -> 0.715Improved
use XPTRANS vs CBT for non-overlapping userscross-platform transfer · Douban book -> Weibo tagMAP: 0.477 -> 0.533Improved
use XPTRANS vs CBTcross-platform transfer · Douban movie newcomersRMSE: 1.737 -> 1.569Improved
transfer auxiliary platform data (XPTRANS vs no transfer CMF)matrix factorization · Tweet entity -> Douban movie, non-overlappingRMSE: 1.439 -> 0.722Improved
use XPTRANS vs CBT for overlapping userscross-platform transfer · Douban book -> Weibo tagMAP: 0.675 -> 0.705Improved
increase fraction of overlapping users/behaviors used for training (ablation)XPTRANS · Tweet entity -> Douban movieRMSE and MAP: 26% active users or 60% behaviors reach overlapped-user accuracyImproved

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