A Comprehensive Survey on Retrieval Methods in Recommender Systems

J Huang, J Chen, J Lin, J Qin, Z Feng, W Zhang… - arxiv preprint arxiv …, 2024 - arxiv.org
In an era dominated by information overload, effective recommender systems are essential
for managing the deluge of data across digital platforms. Multi-stage cascade ranking …

Contrastive cross-domain recommendation in matching

R **e, Q Liu, L Wang, S Liu, B Zhang, L Lin - Proceedings of the 28th …, 2022 - dl.acm.org
Cross-domain recommendation (CDR) aims to provide better recommendation results in the
target domain with the help of the source domain, which is widely used and explored in real …

Constructing tree-based index for efficient and effective dense retrieval

H Li, Q Ai, J Zhan, J Mao, Y Liu, Z Liu… - Proceedings of the 46th …, 2023 - dl.acm.org
Recent studies have shown that Dense Retrieval (DR) techniques can significantly improve
the performance of first-stage retrieval in IR systems. Despite its empirical effectiveness, the …

On missing labels, long-tails and propensities in extreme multi-label classification

E Schultheis, M Wydmuch, R Babbar… - Proceedings of the 28th …, 2022 - dl.acm.org
The propensity model introduced by Jain et al has become a standard approach for dealing
with missing and long-tail labels in extreme multi-label classification (XMLC). In this paper …

A survey on incremental update for neural recommender systems

P Zhang, S Kim - arxiv preprint arxiv:2303.02851, 2023 - arxiv.org
Recommender Systems (RS) aim to provide personalized suggestions of items for users
against consumer over-choice. Although extensive research has been conducted to address …

Equi-vocal: Synthesizing queries for compositional video events from limited user interactions

E Zhang, M Daum, D He, B Haynes, R Krishna… - Proceedings of the …, 2023 - dl.acm.org
We introduce EQUI-VOCAL: a new system that automatically synthesizes queries over
videos from limited user interactions. The user only provides a handful of positive and …

Improving accuracy and diversity in matching of recommendation with diversified preference network

R **e, Q Liu, S Liu, Z Zhang, P Cui… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Real-world recommendation systems need to deal with millions of item candidates.
Therefore, most practical large-scale recommendation systems usually contain two modules …

Adaptive domain interest network for multi-domain recommendation

Y Jiang, Q Li, H Zhu, J Yu, J Li, Z Xu, H Dong… - Proceedings of the 31st …, 2022 - dl.acm.org
Industrial recommender systems usually hold data from multiple business scenarios and are
expected to provide recommendation services for these scenarios simultaneously. In the …

Joint learning of deep retrieval model and product quantization based embedding index

H Zhang, H Shen, Y Qiu, Y Jiang, S Wang… - Proceedings of the 44th …, 2021 - dl.acm.org
Embedding index that enables fast approximate nearest neighbor (ANN) search, serves as
an indispensable component for state-of-the-art deep retrieval systems. Traditional …

Generalized test utilities for long-tail performance in extreme multi-label classification

E Schultheis, M Wydmuch… - Advances in …, 2024 - proceedings.neurips.cc
Extreme multi-label classification (XMLC) is a task of selecting a small subset of relevant
labels from a very large set of possible labels. As such, it is characterized by long-tail labels …