FWPRec Experiments
All experiments
MIND-small · seeds 42, 43, 44 · RTX 4080 SUPER

Keep the notepad vs sequence models

Keep-the-pad stores a small notepad of recent news taste instead of re-reading the whole click history. Sequence models read that history with a GRU or with attention. We asked which ranks better when everything else is the same: same MIND-small split, same article vectors, same candidate lists, three training seeds. We trained SASRec, GRU4Rec, and HSTU. We did not retrain keep-the-pad; those scores come from the earlier keep-the-pad runs on this split. Keep-the-pad beat all three models on every seed. The gap is small but consistent. This is validation only. Published test-set tables use a different split. Do not mix the two.

Takeaway

Keep-the-pad wins every seed. Mean val NDCG@10: 0.395 vs SASRec 0.372, GRU 0.369, HSTU 0.365.

Mean NDCG@10 · three seeds

HSTU
0.3651
GRU4Rec
0.3693
SASRec
0.3717
Keep the pad
0.3951

NDCG@10 by seed

Model424344Mean
Keep the pad0.39510.39620.39390.3951
SASRec0.37120.37230.37150.3717
GRU4Rec0.36990.36890.36910.3693
HSTU0.35800.37080.36660.3651

Sequence models · mean AUC and MRR

ModelAUCMRR
SASRec0.60420.3355
GRU4Rec0.60190.3329
HSTU0.59620.3285

Isolated suite on damlr-w04. Same MIND-small split as keep-the-pad (dataset seed 42, val fraction 0.1). Sequence models trained here; keep-the-pad scores reused from the dense lab runs (seed 42 lab4080, seeds 43/44 confirm lab), not retrained. Config is SASRecProfile. Validation only. Test split sealed. Do not mix with published test-set tables.