SCASRec unifies ranking and redundancy elimination for route lists via stepwise corrective rewards and an adaptive end-of-recommendation token, claiming SOTA results on two datasets and real deployment.
Deep session interest network for click-through rate prediction
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Click-Through Rate (CTR) prediction plays an important role in many industrial applications, such as online advertising and recommender systems. How to capture users' dynamic and evolving interests from their behavior sequences remains a continuous research topic in the CTR prediction. However, most existing studies overlook the intrinsic structure of the sequences: the sequences are composed of sessions, where sessions are user behaviors separated by their occurring time. We observe that user behaviors are highly homogeneous in each session, and heterogeneous cross sessions. Based on this observation, we propose a novel CTR model named Deep Session Interest Network (DSIN) that leverages users' multiple historical sessions in their behavior sequences. We first use self-attention mechanism with bias encoding to extract users' interests in each session. Then we apply Bi-LSTM to model how users' interests evolve and interact among sessions. Finally, we employ the local activation unit to adaptively learn the influences of various session interests on the target item. Experiments are conducted on both advertising and production recommender datasets and DSIN outperforms other state-of-the-art models on both datasets.
verdicts
UNVERDICTED 5representative citing papers
Next Interest Flow models user intent as continuous evolutionary trajectories on a high-dimensional latent interest manifold with kinematic constraints, bidirectional alignment, and temporal causality mechanisms, yielding reported gains on industrial CTR data.
CCN applies contrastive learning on collaborative co-click/co-non-click signals to structure item representations for trigger-induced recommendations, showing 12.3% CTR and 12.7% order lift in an unseen Taobao scenario after training on a year of heterogeneous data.
UxSID models ultra-long user sequences with semantic-group shared interest memory using Semantic IDs and dual-level attention, achieving state-of-the-art performance and a 0.337% revenue lift in advertising A/B tests.
AMEN aligns item-scene interactions via homogeneous spaces and a TSP mechanism to let all-domain movelines differentially affect CTR predictions, reporting +11.6% CTCVR lift in A/B tests.
citing papers explorer
-
SCASRec: A Self-Correcting and Auto-Stopping Model for Generative Route List Recommendation
SCASRec unifies ranking and redundancy elimination for route lists via stepwise corrective rewards and an adaptive end-of-recommendation token, claiming SOTA results on two datasets and real deployment.
-
Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines
Next Interest Flow models user intent as continuous evolutionary trajectories on a high-dimensional latent interest manifold with kinematic constraints, bidirectional alignment, and temporal causality mechanisms, yielding reported gains on industrial CTR data.
-
Beyond the Trigger: Learning Collaborative Context for Generalizable Trigger-Induced Recommendation
CCN applies contrastive learning on collaborative co-click/co-non-click signals to structure item representations for trigger-induced recommendations, showing 12.3% CTR and 12.7% order lift in an unseen Taobao scenario after training on a year of heterogeneous data.
-
UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence
UxSID models ultra-long user sequences with semantic-group shared interest memory using Semantic IDs and dual-level attention, achieving state-of-the-art performance and a 0.337% revenue lift in advertising A/B tests.
-
All-domain Moveline Evolution Network for Click-Through Rate Prediction
AMEN aligns item-scene interactions via homogeneous spaces and a TSP mechanism to let all-domain movelines differentially affect CTR predictions, reporting +11.6% CTCVR lift in A/B tests.