315 citations · 1.5k across the 58 of their papers we have counts for
58 papers
NoisyTune: A Little Noise Can Help You Finetune Pretrained Language Models Better
Chuhan Wu, Fangzhao Wu, Tao Qi +2
Effectively finetuning pretrained language models (PLMs) is critical for their success in downstream tasks. However, PLMs may have risks in overfitting the pretraining tasks and da…
FedAttack: Effective and Covert Poisoning Attack on Federated Recommendation via Hard Sampling
Chuhan Wu, Fangzhao Wu, Tao Qi +2
Federated learning (FL) is a feasible technique to learn personalized recommendation models from decentralized user data. Unfortunately, federated recommender systems are vulnerabl…
Game of Privacy: Towards Better Federated Platform Collaboration under Privacy Restriction
Chuhan Wu, Fangzhao Wu, Tao Qi +4
Vertical federated learning (VFL) aims to train models from cross-silo data with different feature spaces stored on different platforms. Existing VFL methods usually assume all dat…
Pixel-Stega: Generative Image Steganography Based on Autoregressive Models
Siyu Zhang, Zhongliang Yang, Haoqin Tu +2
In this letter, we explored generative image steganography based on autoregressive models. We proposed Pixel-Stega, which implements pixel-level information hiding with autoregress…
A New Sentence Extraction Strategy for Unsupervised Extractive Summarization Methods
Dehao Tao, Yingzhu Xiong, Zhongliang Yang +1
In recent years, text summarization methods have attracted much attention again thanks to the researches on neural network models. Most of the current text summarization methods ba…
Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving
Tao Qi, Fangzhao Wu, Chuhan Wu +2
News recommendation is important for personalized online news services. Most existing news recommendation methods rely on centrally stored user behavior data to both train models o…
Fastformer: Additive Attention Can Be All You Need
Chuhan Wu, Fangzhao Wu, Tao Qi +2
Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Tran…
UserBERT: Contrastive User Model Pre-training
Chuhan Wu, Fangzhao Wu, Yang Yu +3
User modeling is critical for personalized web applications. Existing user modeling methods usually train user models from user behaviors with task-specific labeled data. However,…
Smart Bird: Learnable Sparse Attention for Efficient and Effective Transformer
Chuhan Wu, Fangzhao Wu, Tao Qi +4
Transformer has achieved great success in NLP. However, the quadratic complexity of the self-attention mechanism in Transformer makes it inefficient in handling long sequences. Man…
Is News Recommendation a Sequential Recommendation Task?
Chuhan Wu, Fangzhao Wu, Tao Qi +1
News recommendation is often modeled as a sequential recommendation task, which assumes that there are rich short-term dependencies over historical clicked news. However, in news r…
DebiasGAN: Eliminating Position Bias in News Recommendation with Adversarial Learning
Chuhan Wu, Fangzhao Wu, Yongfeng Huang
News recommendation is important for improving news reading experience of users. Users' news click behaviors are widely used for inferring user interests and predicting future clic…
PP-Rec: News Recommendation with Personalized User Interest and Time-aware News Popularity
Tao Qi, Fangzhao Wu, Chuhan Wu +1
Personalized news recommendation methods are widely used in online news services. These methods usually recommend news based on the matching between news content and user interest…
HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation
Tao Qi, Fangzhao Wu, Chuhan Wu +4
User interest modeling is critical for personalized news recommendation. Existing news recommendation methods usually learn a single user embedding for each user from their previou…
Provably Secure Generative Linguistic Steganography
Siyu Zhang, Zhongliang Yang, Jinshuai Yang +1
Generative linguistic steganography mainly utilized language models and applied steganographic sampling (stegosampling) to generate high-security steganographic text (stegotext). H…
One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers
Chuhan Wu, Fangzhao Wu, Yongfeng Huang
Pre-trained language models (PLMs) achieve great success in NLP. However, their huge model sizes hinder their applications in many practical systems. Knowledge distillation is a po…
Personalized News Recommendation with Knowledge-aware Interactive Matching
Tao Qi, Fangzhao Wu, Chuhan Wu +1
The most important task in personalized news recommendation is accurate matching between candidate news and user interest. Most of existing news recommendation methods model candid…
Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling
Chuhan Wu, Fangzhao Wu, Tao Qi +1
Transformer is important for text modeling. However, it has difficulty in handling long documents due to the quadratic complexity with input text length. In order to handle this pr…
Distribution Matching for Rationalization
Yongfeng Huang, Yujun Chen, Yulun Du +1
The task of rationalization aims to extract pieces of input text as rationales to justify neural network predictions on text classification tasks. By definition, rationales represe…
Rethinking InfoNCE: How Many Negative Samples Do You Need?
Chuhan Wu, Fangzhao Wu, Yongfeng Huang
InfoNCE loss is a widely used loss function for contrastive model training. It aims to estimate the mutual information between a pair of variables by discriminating between each po…
Empowering News Recommendation with Pre-trained Language Models
Chuhan Wu, Fangzhao Wu, Tao Qi +1
Personalized news recommendation is an essential technique for online news services. News articles usually contain rich textual content, and accurate news modeling is important for…
MM-Rec: Multimodal News Recommendation
Chuhan Wu, Fangzhao Wu, Tao Qi +1
Accurate news representation is critical for news recommendation. Most of existing news representation methods learn news representations only from news texts while ignore the visu…
Two Birds with One Stone: Unified Model Learning for Both Recall and Ranking in News Recommendation
Chuhan Wu, Fangzhao Wu, Tao Qi +1
Recall and ranking are two critical steps in personalized news recommendation. Most existing news recommender systems conduct personalized news recall and ranking separately with d…
FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
Chuhan Wu, Fangzhao Wu, Yang Cao +2
Graph neural network (GNN) is widely used for recommendation to model high-order interactions between users and items. Existing GNN-based recommendation methods rely on centralized…
FeedRec: News Feed Recommendation with Various User Feedbacks
Chuhan Wu, Fangzhao Wu, Tao Qi +1
Accurate user interest modeling is important for news recommendation. Most existing methods for news recommendation rely on implicit feedbacks like click for inferring user interes…