xDeepFM: compressed vector-wise feature interactions

What changed

Combined a compressed interaction network computing explicit vector-wise feature crosses with a deep implicit-interaction branch and a linear component.

Scientific scope

Combined a compressed interaction network computing explicit vector-wise feature crosses with a deep implicit-interaction branch and a linear component. Inherits Wide&Deep, FM and DCN, but CIN is a separately specified method delta. Bounded-degree explicit interactions are constrained by architecture, not unconstrained arbitrary polynomial learning. Original v1has placeholder ACM Woodstock/ISBN/DOI fields: none are treated as real publication identifiers.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits Wide&Deep, FM and DCN, but CIN is a separately specified method delta. Bounded-degree explicit interactions are constrained by architecture, not unconstrained arbitrary polynomial learning. Original v1has placeholder ACM Woodstock/ISBN/DOI fields: none are treated as real publication identifiers.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction