๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

cv usk
@cv_usk
AI / Software Research Notes AI Agent, LLMOps, MLOps, Software Architecture ๆŠ•็จฟใฏๅ€‹ไบบใฎๆ„่ฆ‹ใงใ™ใ€‚
๊ฐ€์ž… May 2026
286 ํŒ”๋กœ์ž‰ ์ค‘    471 ํŒฌ
TL;DR: HiRank is a recommender ranking model that fuses sequential and non-sequential features two ways in a single backbone, and uses effective-rank-aware attention to keep representations diverse. In an online test on the Taobao homepage, orders per user rose 2.27%. Title: Unified Heterogeneous Feature Interaction via Effective-Rank Scaling for Recommender Systems URL: Key points ใƒป๐Ÿงฉ Drops the encode-then-interact pipeline; event-level sequence states stay accessible across layers ใƒป๐Ÿšช Models the main behavior sequence with HSTU-style gated attention ใƒป๐Ÿ”Ž Retrieves from long-term history memories with both interest queries and candidate queries for diverse retrieval ใƒป๐Ÿ”€ Fuses sequence, retrieval outputs, features, and the candidate via token mixing ใƒป๐ŸŽฏ Applies High-Rank Attention over scenario-aware compressed composite tokens ใƒป๐Ÿ“Š Offline: homepage GAUC 0.7801 (+0.0186 over the strongest baseline) ใƒป๐Ÿ›’ Online: orders/user +2.27%, GMV/user +2.86% ๐Ÿ’ก I like the takeaway that sequence length and representation diversity matter, not just model size. #RecSys# #MachineLearning#
๋” ๋ณด๊ธฐ