Improving query representations in dense retrieval using pseudo relevance feedback, significantly enhancing accuracy.

HongChien Yu, Chenyan Xiong, Jamie Callan

SURGE integrates interest graphs with GNNs to model long sequences, boosting recommendation accuracy by 12-15%.

Jianxin Chang, Chen Gao, Yu Zheng et al.

GCE-GNN combines session and global graphs with attention mechanisms to improve session-based recommendation accuracy.

Ziyang Wang, Wei Wei, Gao Cong et al.

Proposes FedNCF, extending Neural Collaborative Filtering to federated learning with secure aggregation, achieving comparable accuracy and faster convergence.

Vasileios Perifanis, Pavlos S. Efraimidis

Proposes UNICORN, a graph-based RL framework, significantly improving CRS success rate by 12% and reducing dialogue turns by 20%.

Yang Deng, Yaliang Li, Fei Sun et al.

Proposes PDA framework using causal intervention to remove bad bias effects and introduce desired bias, improving recommendation accuracy.

Yang Zhang, Fuli Feng, Xiangnan He et al.

DeepImpact leverages semantic impact scores with BERT and DocT5Query to improve first-stage retrieval by 17%, enabling faster and more accurate search.

Antonio Mallia, Omar Khattab, Nicola Tonellotto et al.

LATTICE leverages multimodal content to mine latent item relationships via graph learning, boosting recommendation accuracy by 12% on key metrics.

Jinghao Zhang, Yanqiao Zhu, Qiang Liu et al.

NaturalProofs benchmarks BERT-based proof-reference retrieval; Joint BERT reaches 42.45 R@10 and 50.22 Full@100 on ProofWiki.

Sean Welleck, Jiacheng Liu, Ronan Le Bras et al.

Proposes Sparse Interest Network (SINE) for sequential recommendation, enabling adaptive extraction of multiple interest embeddings, significantly improving accuracy.

Qiaoyu Tan, Jianwei Zhang, Jiangchao Yao et al.

BERT-based models achieve NDCG@10 of 0.6934, surpassing traditional methods by 23%, demonstrating deep learning's superiority in large-scale retrieval.

Nick Craswell, Bhaskar Mitra, Emine Yilmaz et al.

Proposes multi-turn dialogue strategies and Bayesian preference elicitation, improving CRS accuracy by 15%, validated on ReDial dataset.

Chongming Gao, Wenqiang Lei, Xiangnan He et al.

Proposes MIRec, a dual transfer learning framework combining model-level meta-mapping and item-level feature connection to improve long-tail item recommendation.

Yin Zhang, Derek Zhiyuan Cheng, Tiansheng Yao et al.

Proposed Swing and Surprise algorithms efficiently construct large-scale product graphs, significantly improving Taobao recommendation performance.

Xiaoyong Yang, Yadong Zhu, Yi Zhang et al.

GiantMIDI-Piano dataset uses convolutional neural networks and high-resolution transcription, containing 38,700,838 notes.

Qiuqiang Kong, Bochen Li, Jitong Chen et al.

Systematic review of bias types in recommender systems and their debiasing techniques, highlighting impact and future challenges.

Jiawei Chen, Hande Dong, Xiang Wang et al.

Cross-architecture knowledge distillation with Margin-MSE boosts neural ranking models' effectiveness by 3-5% on MSMARCO, improving efficiency-effectiveness balance.

Sebastian Hofstätter, Sophia Althammer, Michael Schröder et al.

SparTerm directly learns sparse text representations in full vocabulary space using importance prediction and gating, achieving state-of-the-art results on MSMARCO.

Yang Bai, Xiaoguang Li, Gang Wang et al.

S^3-Rec enhances sequential recommendation via mutual information maximization, addressing data sparsity.

Kun Zhou, Hui Wang, Wayne Xin Zhao et al.

Proposes graph-based Path Reasoning (CPR) for conversational recommendation, explicitly leveraging user attributes, outperforming SOTA EAR and CRM by 15-20% on success rate.

Wenqiang Lei, Gangyi Zhang, Xiangnan He et al.