Federated learning (FL) is an important technique for learning models fr...
Large language models (LLMs) have demonstrated powerful capabilities in ...
Algorithmic fairness has become an important machine learning problem,
e...
With the swift advancement of deep learning, state-of-the-art algorithms...
Existing research efforts for multi-interest candidate matching in
recom...
The increasing data privacy concerns in recommendation systems have made...
Query-aware webpage snippet extraction is widely used in search engines ...
Previous works have validated that text generation APIs can be stolen th...
This paper presents FedX, an unsupervised federated learning framework. ...
We consider the problem of personalised news recommendation where each u...
Vertical federated learning (VFL) is a privacy-preserving machine learni...
Federated learning (FL) enables multiple clients to collaboratively trai...
Contrastive learning is widely used for recommendation model learning, w...
Privacy protection is an essential issue in personalized news recommenda...
User modeling is important for news recommendation. Existing methods usu...
News recommendation aims to match news with personalized user interest.
...
News recommendation aims to help online news platform users find their
p...
Ensemble knowledge distillation can extract knowledge from multiple teac...
Single-tower models are widely used in the ranking stage of news
recomme...
Diversity is an important factor in providing high-quality personalized ...
Adversarial learning is a widely used technique in fair representation
l...
Big models are widely used by online recommender systems to boost
recomm...
News recommendation is a core technique used by many online news platfor...
Effectively finetuning pretrained language models (PLMs) is critical for...
Federated learning (FL) is an important paradigm for training global mod...
News recommendation is critical for personalized news distribution. Fede...
Vertical federated learning (VFL) aims to train models from cross-silo d...
Federated learning (FL) is a feasible technique to learn personalized
re...
Nowadays, due to the breakthrough in natural language generation (NLG),
...
Personalized news recommendation has been widely adopted to improve user...
News recommendation is critical for personalized news access. Most exist...
News recommendation is important for personalized online news services. ...
User modeling is critical for personalized web applications. Existing us...
Federated learning is widely used to learn intelligent models from
decen...
Transformer has achieved great success in NLP. However, the quadratic
co...
Transformer is a powerful model for text understanding. However, it is
i...
News recommendation is often modeled as a sequential recommendation task...
Personalized news recommendation is an important technique to help users...
News recommendation is important for improving news reading experience o...
User interest modeling is critical for personalized news recommendation....
Personalized news recommendation methods are widely used in online news
...
Transformer is important for text modeling. However, it has difficulty i...
Pre-trained language models (PLMs) achieve great success in NLP. However...
InfoNCE loss is a widely used loss function for contrastive model traini...
The advances in pre-trained models (e.g., BERT, XLNET and etc) have larg...
The most important task in personalized news recommendation is accurate
...
Personalized news recommendation is an essential technique for online ne...
Accurate news representation is critical for news recommendation. Most o...
Recall and ranking are two critical steps in personalized news
recommend...
News recommendation is critical for personalized news access. Existing n...