Userbert: Pre-training user model with contrastive self-supervision
User modeling is critical for personalization. Existing methods usually train user models from
task-specific labeled data, which may be insufficient. In fact, there are usually abundant …
task-specific labeled data, which may be insufficient. In fact, there are usually abundant …
Scaling law for recommendation models: Towards general-purpose user representations
Recent advancement of large-scale pretrained models such as BERT, GPT-3, CLIP, and
Gopher, has shown astonishing achievements across various task domains. Unlike vision …
Gopher, has shown astonishing achievements across various task domains. Unlike vision …
One4all user representation for recommender systems in e-commerce
General-purpose representation learning through large-scale pre-training has shown
promising results in the various machine learning fields. For an e-commerce domain, the …
promising results in the various machine learning fields. For an e-commerce domain, the …
AdaptSSR: pre-training user model with augmentation-adaptive self-supervised ranking
User modeling, which aims to capture users' characteristics or interests, heavily relies on
task-specific labeled data and suffers from the data sparsity issue. Several recent studies …
task-specific labeled data and suffers from the data sparsity issue. Several recent studies …
Deep user match network for click-through rate prediction
Z Huang, M Tao, B Zhang - Proceedings of the 44th International ACM …, 2021 - dl.acm.org
Click-through rate (CTR) prediction is a crucial task in many applications (eg recommender
systems). Recently deep learning based models have been proposed and successfully …
systems). Recently deep learning based models have been proposed and successfully …
Task Relation-aware Continual User Representation Learning
User modeling, which learns to represent users into a low-dimensional representation space
based on their past behaviors, got a surge of interest from the industry for providing …
based on their past behaviors, got a surge of interest from the industry for providing …
Pivotal role of language modeling in recommender systems: Enriching task-specific and task-agnostic representation learning
Recent studies have proposed unified user modeling frameworks that leverage user
behavior data from various applications. Many of them benefit from utilizing users' behavior …
behavior data from various applications. Many of them benefit from utilizing users' behavior …
DDHCN: Dual decoder Hyperformer convolutional network for Downstream-Adaptable user representation learning on app usage
F Zeng, Y Li, J Xiao, D Yang - Expert Systems with Applications, 2024 - Elsevier
In mobile scenarios, there is a need for general user representations to solve multiple target
tasks. However, there are some challenges in the related research (eg, difficulty in learning …
tasks. However, there are some challenges in the related research (eg, difficulty in learning …
Robust user behavioral sequence representation via multi-scale stochastic distribution prediction
C Fu, W Wu, X Zhang, J Hu, J Wang… - Proceedings of the 32nd …, 2023 - dl.acm.org
User behavior representation learned by self-supervised pre-training tasks is widely used in
various domains and applications. Conventional methods usually follow the methodology in …
various domains and applications. Conventional methods usually follow the methodology in …
User Modeling and User Profiling: A Comprehensive Survey
The integration of artificial intelligence (AI) into daily life, particularly through information
retrieval and recommender systems, has necessitated advanced user modeling and …
retrieval and recommender systems, has necessitated advanced user modeling and …