DIN and DIEN: target-conditioned interest activation and evolution

What changed

Used candidate-conditioned attention to select historical user interests; DIEN added auxiliary-supervised sequential interest extraction and attention-modulated recurrent evolution.

Scientific scope

Used candidate-conditioned attention to select historical user interests; DIEN added auxiliary-supervised sequential interest extraction and attention-modulated recurrent evolution. 2017DIN and2018DIEN bundled with different original bylines. Inherits attention/GRUs and behavior embeddings; inferred latent interest is not measured psychological state or causal preference. v1DIN does not acquire later Dice/minibatch-regularization details without the corresponding revised source. Claimed online CTR changes are source-specific experiments, not universal welfare improvements.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. 2017DIN and2018DIEN bundled with different original bylines. Inherits attention/GRUs and behavior embeddings; inferred latent interest is not measured psychological state or causal preference. v1DIN does not acquire later Dice/minibatch-regularization details without the corresponding revised source. Claimed online CTR changes are source-specific experiments, not universal welfare improvements.

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.

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