DCMT framework improves CVR AUC by 1.07%, addressing selection bias and data sparsity.

Feng Zhu, Mingjie Zhong, Xinxing Yang et al.

This survey reviews over 300 methods for automatic knowledge graph construction, focusing on knowledge acquisition, refinement, and evolution, emphasizing deep learning and multi-scenario applications.

Lingfeng Zhong, Jia Wu, Qian Li et al.

HyDE combines instruction-guided generation and contrastive encoding for zero-shot dense retrieval without relevance labels.

Luyu Gao, Xueguang Ma, Jimmy Lin et al.

Pre-trained BERT-based neural rankers outperform traditional methods in medical systematic review screening prioritization, with significant improvements in key metrics.

Shuai Wang, Harrisen Scells, Bevan Koopman et al.

FRU employs local stored logs and importance filtering to enable fast user forgetting in federated recommenders, reducing retraining time by 7x.

Wei Yuan, Hongzhi Yin, Fangzhao Wu et al.

RankT5 fine-tunes T5 with ranking losses, improving ranking performance by 1.8% on MS MARCO dataset.

Honglei Zhuang, Zhen Qin, Rolf Jagerman et al.

KuaiRand uses randomly exposed videos with 12 user signals, enabling unbiased recommendation evaluation.

Chongming Gao, Shijun Li, Yuan Zhang et al.

This study models recommendation system scaling laws, revealing performance follows a power law plus constant, with data size being the dominant factor.

Newsha Ardalani, Carole-Jean Wu, Zeliang Chen et al.

BM3 introduces a self-supervised multi-modal recommendation framework using dropout-based contrastive views, achieving 2-9x faster training and outperforming state-of-the-art on large datasets.

Xin Zhou, Hongyu Zhou, Yong Liu et al.

Proposes CAGCN, a recommendation-oriented GNN leveraging CIR to enhance collaboration signals, surpassing 1-WL discriminative power.

Yu Wang, Yuying Zhao, Yi Zhang et al.

Introduced a Generalized Delayed Feedback Model (GDFM) to enhance conversion rate prediction timeliness in recommender systems.

Jia-Qi Yang, De-Chuan Zhan

Unified recommendation model M6-Rec using prompt tuning and multi-task fusion, supports open-domain tasks with 5-10% accuracy gain and 30% faster inference.

Zeyu Cui, Jianxin Ma, Chang Zhou et al.

Proposes Hypergraph Contrastive Collaborative Filtering (HCCF), integrating hypergraph structure learning and self-supervised contrast to improve recommendation robustness.

Lianghao Xia, Chao Huang, Yong Xu et al.

This study analyzes how variations in ground truth affect query performance prediction (QPP) evaluation, recommending stable metric-model combinations.

Debasis Ganguly, Suchana Datta, Mandar Mitra et al.

Scaling T5-based dual encoders with fixed embedding size significantly improves out-of-domain retrieval, outperforming SOTA on BEIR dataset.

Jianmo Ni, Chen Qu, Jing Lu et al.

Proposed CLUE uses contrastive learning to scale user representations, outperforming task-specific models with significant transferability.

Kyuyong Shin, Hanock Kwak, Su Young Kim et al.

GRCN employs adaptive graph refinement with prototype networks to improve multimedia recommendation with implicit feedback, achieving over 9% improvement in Recall@10.

Wei Yinwei, Wang Xiang, Nie Liqiang et al.

DuoRec employs contrastive regularization to address representation degeneration in sequential recommendation, improving embedding uniformity.

Ruihong Qiu, Zi Huang, Hongzhi Yin et al.

Proposes a unified framework integrating dense and sparse retrieval via logical scoring and physical retrieval models.

Jimmy Lin

SPLADE v2 enhances sparse lexical representations with max pooling and distillation, achieving over 9% NDCG@10 improvement on TREC DL 2019 for efficient first-stage retrieval.

Thibault Formal, Carlos Lassance, Benjamin Piwowarski et al.