338 citations · 1.1k across the 73 of their papers we have counts for
15 papers · 1 filter
Untargeted Attack against Federated Recommendation Systems via Poisonous Item Embeddings and the Defense
Yang Yu, Qi Liu, Likang Wu +3
Federated recommendation (FedRec) can train personalized recommenders without collecting user data, but the decentralized nature makes it susceptible to poisoning attacks. Most pre…
Progressive Knowledge Transfer Based on Human Visual Perception Mechanism for Perceptual Quality Assessment of Point Clouds
Qi Liu, Yiyun Liu, Honglei Su +2
With the wide applications of colored point cloud in many fields, point cloud perceptual quality assessment plays a vital role in the visual communication systems owing to the exis…
One Person, One Model--Learning Compound Router for Sequential Recommendation
Zhiding Liu, Mingyue Cheng, Zhi Li +2
Deep learning has brought significant breakthroughs in sequential recommendation (SR) for capturing dynamic user interests. A series of recent research revealed that models with mo…
Nested Named Entity Recognition from Medical Texts: An Adaptive Shared Network Architecture with Attentive CRF
Junzhe Jiang, Mingyue Cheng, Qi Liu +2
Recognizing useful named entities plays a vital role in medical information processing, which helps drive the development of medical area research. Deep learning methods have achie…
Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play
Qi Liu, Zihuiwen Ye, Tao Yu +2
The task of context-dependent text-to-SQL aims to convert multi-turn user utterances to formal SQL queries. This is a challenging task due to both the scarcity of training data fro…
Cross-scale Attention Guided Multi-instance Learning for Crohn's Disease Diagnosis with Pathological Images
Ruining Deng, Can Cui, Lucas W. Remedios +12
Multi-instance learning (MIL) is widely used in the computer-aided interpretation of pathological Whole Slide Images (WSIs) to solve the lack of pixel-wise or patch-wise annotation…
Gain-gain and gain-lossless PT-symmetry broken from PT-phase diagram
Qi Zhang, Yun Ma, Qi Liu +5
Parity-time (PT) symmetry and broken in micro/nano photonic structures have been investigated extensively as they bring new opportunities to control the flow of light based on non-…
Improving Multi-Interest Network with Stable Learning
Zhaocheng Liu, Yingtao Luo, Di Zeng +4
Modeling users' dynamic preferences from historical behaviors lies at the core of modern recommender systems. Due to the diverse nature of user interests, recent advances propose t…
Network Pruning via Feature Shift Minimization
Yuanzhi Duan, Yue Zhou, Peng He +3
Channel pruning is widely used to reduce the complexity of deep network models. Recent pruning methods usually identify which parts of the network to discard by proposing a channel…
Causal Machine Learning: A Survey and Open Problems
Jean Kaddour, Aengus Lynch, Qi Liu +2
Causal Machine Learning (CausalML) is an umbrella term for machine learning methods that formalize the data-generation process as a structural causal model (SCM). This perspective…
Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification
Kai Zhang, Qi Liu, Zhenya Huang +5
Cross-domain sentiment classification (CDSC) aims to use the transferable semantics learned from the source domain to predict the sentiment of reviews in the unlabeled target domai…
On the stability of orthogonally Jensen additive and quadratic functional equation
Linlin Fu, Qi Liu, Yongjin Li
We consider the stability of the orthogonal Jensen additive and quadratic equations in -spaces, through applying and extending the approach to the proof of a 2010 result of W.Fr…
Ulam stability of an additive-quadratic functional equation in F-space and quasi-Banach spaces
Linlin Fu, Qi Liu, Yongjin Li
By adopting the direct method and fixed point method, we prove that the Hyers-Ulam stability of the following additive-quadratic functional equation \begin{equation} f(x+y, z+w)+f(…
On the stability of orthogonal additivity in -homogeneous -spaces and quasi-Banach spaces
Qi Liu, Linlin Fu, Yongjin Li
In this paper, we study the stability of the orthogonal equation,which is closely related to the results by Wlodzimierz Fechner and Justyna Sikorska in 2010. There are some differe…
Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis
Kai Zhang, Kun Zhang, Mengdi Zhang +4
Aspect-based sentiment analysis (ABSA) predicts sentiment polarity towards a specific aspect in the given sentence. While pre-trained language models such as BERT have achieved gre…