Tao Qi

activity

20202023

most citedFedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation

305 citations · 741 across the 44 of their papers we have counts for

collaborators

Showing 2021Show all

19 papers · 1 filter

cs.IR2021

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…

cs.CL2021★ 80 cited

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…

cs.IR2021★ 2 cited

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,…

cs.CL2021★ 2 cited

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…

cs.IR2021★ 1 cited

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…

hep-ex2021★ 10 cited

Measurement of $e^{+} e^{-} \to γ χ_{c 0, c 1, c 2}$ cross sections at center-of-mass energies between 3.77 and 4.60 GeV

BESIII Collaboration, M. Ablikim, M. N. Achasov +501

The $e^{+} e^{-} \to γ χ_{c J}$ ( $J = 0, 1, 2$ ) processes are studied at center-of-mass energies ranging from 3.773 to 4.600 GeV, using a total integrated luminosity of 19.3 fb $^{- 1}$ $e^{+} e^{-}$ …

cs.IR2021★ 2 cited

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…

cs.IR2021★ 6 cited

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…

cs.IR2021★ 2 cited

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…

cs.CL2021★ 3 cited

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…

cs.IR2021★ 5 cited

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…

hep-ex2021★ 9 cited

Determination of the absolute branching fractions of $D^{0} \to K^{-} e^{+} ν_{e}$ and $D^{+} \to K ˉ^{0} e^{+} ν_{e}$

BESIII Collaboration, M. Ablikim, M. N. Achasov +502

Using 2.93 fb $^{- 1}$ of $e^{+} e^{-}$ collision data collected with the BESIII detector at a center-of-mass energy of 3.773 GeV, we measure the absolute branching fractions of the decay…

cs.IR2021★ 10 cited

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…

cs.IR2021★ 4 cited

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…

hep-ex2021★ 11 cited

Search for the rare semi-leptonic decay $J / ψ \to D^{-} e^{+} ν_{e} + c . c .$

BESIII Collaboration, M. Ablikim, M. N. Achasov +503

Using $10.1 \times 1 0^{9}$ $J / ψ$ events produced by the Beijing Electron Positron Collider (BEPCII) at a center-of-mass energy $s = 3.097 GeV$ and collected with the BESIII…

hep-ex2021★ 1 cited

Observation of $e^{+} e^{-} \to η ψ (2 S)$ at center-of-mass energies from 4.236 to 4.600 GeV

BESIII Collaboration, M. Ablikim, M. N. Achasov +505

Using a total of $5.25 fb^{- 1}$ of $e^{+} e^{-}$ collision data with center-of-mass energies from 4.236 to 4.600 GeV, we report the first observation of the process $e^{+}e^{-…

cs.IR2021★ 305 cited

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…

cs.IR2021★ 8 cited

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…

cs.CL2021★ 2 cited

NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application

Chuhan Wu, Fangzhao Wu, Yang Yu +3

Pre-trained language models (PLMs) like BERT have made great progress in NLP. News articles usually contain rich textual information, and PLMs have the potentials to enhance news t…

Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving

Fastformer: Additive Attention Can Be All You Need

UserBERT: Contrastive User Model Pre-training

Smart Bird: Learnable Sparse Attention for Efficient and Effective Transformer

Is News Recommendation a Sequential Recommendation Task?

Measurement of e+e−→γχc0,c1,c2​ cross sections at center-of-mass energies between 3.77 and 4.60 GeV

PP-Rec: News Recommendation with Personalized User Interest and Time-aware News Popularity

HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation

Personalized News Recommendation with Knowledge-aware Interactive Matching

Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling

Empowering News Recommendation with Pre-trained Language Models

Determination of the absolute branching fractions of D0→K−e+νe​ and D+→Kˉ0e+νe​

MM-Rec: Multimodal News Recommendation

Two Birds with One Stone: Unified Model Learning for Both Recall and Ranking in News Recommendation

Search for the rare semi-leptonic decay J/ψ→D−e+νe​+c.c.

Observation of e+e−→ηψ(2S) at center-of-mass energies from 4.236 to 4.600 GeV

FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation

FeedRec: News Feed Recommendation with Various User Feedbacks

NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application

Measurement of $e^{+} e^{-} \to γ χ_{c 0, c 1, c 2}$ cross sections at center-of-mass energies between 3.77 and 4.60 GeV

Determination of the absolute branching fractions of $D^{0} \to K^{-} e^{+} ν_{e}$ and $D^{+} \to K ˉ^{0} e^{+} ν_{e}$

Search for the rare semi-leptonic decay $J / ψ \to D^{-} e^{+} ν_{e} + c . c .$

Observation of $e^{+} e^{-} \to η ψ (2 S)$ at center-of-mass energies from 4.236 to 4.600 GeV