HiRank Unifies Sequence Modeling and Feature Interaction via Effective-Rank Scaling for Multi-Scenario Recommendation
_reachsumit · x · 2026-10-28
Addressing how industrial ranking models must jointly capture heterogeneous feature interactions, long-term user behaviors, and multi-scenario dependencies under strict serving constraints, the paper proposes HiRank, a unified framework for multi-scenario recommendation.
HiRank integrates gated sequential attention with heterogeneous feature interaction in one backbone, enabling bidirectional fusion between sequential and non-sequential representations, and uses scenario-aware aggregation to compress low-order tokens into compact representations transformed by per-scenario projections into composite tokens for more effective high-order self-attention.
More from Research
- Anthropic shares early results from six Claude drug-discovery partnerships, starts own rare-disease programs — IAmSamFin · 2026-10-28
- TTME beats test-time training on 5 math tasks while cutting FLOPs by 82.8-84.6% — UCSantaBarbara · 2026-10-28
- EnvLunch turns executable environments into free verifiable agent training data — KingsCollegeLondon · 2026-10-28
- Anthropic reveals it is developing its own experimental drugs using Claude — Polymarket · 2026-10-28
- Stanford launches TaskNet: 132 worker interviews build a large-scale occupational task inventory — soumitrashukla9 · 2026-10-28
- KAIST's Principia uses LLMs to construct and refine scientific principles at test time — coallaoh · 2026-10-28