AI Paper Atlas

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

NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendation

Jiaqi Zhang, Yu Cheng, Yongxin Ni, Yunzhu Pan, Zheng Yuan, Junchen Fu, Youhua Li, Jie Wang, Fajie Yuan

TPAMI 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 29 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
pre-train on the Bili_500K source dataset before fine-tuning (HasPT vs NoPT)SASRec TransRec · Bili_Food (text)HR@10 (%): 18.03 -> 19.59Improved
pre-train on source dataset (HasPT vs NoPT)BERT4Rec TransRec · Bili_Food (text)HR@10 (%): 16.70 -> 20.00Improved
train modality encoder end-to-end instead of two-stage frozen features (ablation)TransRec with BERT · Bili_Movie (text)HR@10 (%): 5.73 -> 12.63Improved
train modality encoder end-to-end instead of two-stage frozen features (ablation)TransRec with BERT · Bili_500K (source)HR@10 (%): 0.57 -> 4.69Improved
train modality encoder end-to-end instead of two-stage frozen features (ablation)TransRec with Swin-B · Bili_Food (image)HR@10 (%): 14.20 -> 18.72Improved
replace item IDs with a text encoder (TransRec NoPT) vs IDRecSASRec · KU (text)HR@10 (%): 28.36 -> 30.77Improved
replace item IDs with a pre-trained image encoder vs IDRecSASRec TransRec HasPT · Bili_Dance (image)HR@10 (%): 23.46 -> 22.16Hurt
jointly learn BERT4Rec with Swin Transformer image encoderBERT4Rec TransRec NoPT · Bili_Food (image)HR@10 (%): 17.07 -> 2.15Hurt
pre-train ResNet50 TransRec on Bili_500K (HasPT) instead of directly training (NoPT) (ablation)ResNet50 TransRec · image recommendationHR@10 (%)No clear effect
remove ImageNet pre-training of ResNet50 (TFS) (ablation)ResNet50 TransRec · image recommendationHR@10 (%)Hurt
use multimodal (text and image) features instead of a single modalitySASRec TransRec · target datasetsHR@10 (%)No clear effect
zero-shot transfer of pre-trained TransRec instead of random rankingZeroRec · Bili_Music (text)HR@10 (%): 0.16 -> 11.30Improved

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