Cross-domain Semantic IDs from organic feed activity, quantized via RQ-FSQ, improve industrial ads CTR prediction with gains up to +0.351% AUC at 30x smaller storage.
SIDE: Semantic ID embedding for effective learning from sequences.arXiv preprint arXiv:2506.16698, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Quantizing Intent: Cross-Domain Semantic IDs from Organic Activity for Industrial Ranking
Cross-domain Semantic IDs from organic feed activity, quantized via RQ-FSQ, improve industrial ads CTR prediction with gains up to +0.351% AUC at 30x smaller storage.