westlake-repl/IDvs.MoRec

End-to-end Training for Multimodal Recommendation Systems

42
/ 100
Emerging

Compares ID-based versus modality-based (text/vision) recommendation architectures through end-to-end training with foundation models like BERT and vision transformers (ResNet, Swin, MAE). Supports sequential recommendation via SASRec integration and includes in-batch debiased cross-entropy loss optimization for improved convergence. Provides reproducible benchmarks across three large-scale datasets (MIND news, H&M fashion, Bilibili video) with downloadable pre-trained encoders from Hugging Face and PyTorch.

166 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

166

Forks

22

Language

Python

License

Apache-2.0

Last pushed

Feb 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/westlake-repl/IDvs.MoRec"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.