28 citations · 47 across the 10 of their papers we have counts for
10 papers
Semi-Supervised Learning via Weight-aware Distillation under Class Distribution Mismatch
Pan Du, Suyun Zhao, Zisen Sheng +2
Semi-Supervised Learning (SSL) under class distribution mismatch aims to tackle a challenging problem wherein unlabeled data contain lots of unknown categories unseen in the labele…
Oracle-guided Contrastive Clustering
Mengdie Wang, Liyuan Shang, Suyun Zhao +4
Deep clustering aims to learn a clustering representation through deep architectures. Most of the existing methods usually conduct clustering with the unique goal of maximizing clu…
FLDP: Flexible strategy for local differential privacy
Dan Zhao, Suyun Zhao, Ruixuan Liu +3
Local differential privacy (LDP), a technique applying unbiased statistical estimations instead of real data, is often adopted in data collection. In particular, this technique is…
An Accelerator for Rule Induction in Fuzzy Rough Theory
Suyun Zhao, Zhigang Dai, Xizhao Wang +4
Rule-based classifier, that extract a subset of induced rules to efficiently learn/mine while preserving the discernibility information, plays a crucial role in human-explainable a…
Self-supervised Graph Learning for Occasional Group Recommendation
Bowen Hao, Hongzhi Yin, Cuiping Li +1
As an important branch in Recommender System, occasional group recommendation has received more and more attention. In this scenario, each occasional group (cold-start group) has n…
Recommending Courses in MOOCs for Jobs: An Auto Weak Supervision Approach
Bowen Hao, Jing Zhang, Cuiping Li +2
The proliferation of massive open online courses (MOOCs) demands an effective way of course recommendation for jobs posted in recruitment websites, especially for the people who ta…
Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation
Bowen Hao, Jing Zhang, Hongzhi Yin +2
Cold-start problem is a fundamental challenge for recommendation tasks. Despite the recent advances on Graph Neural Networks (GNNs) incorporate the high-order collaborative signal…
FLAME: Differentially Private Federated Learning in the Shuffle Model
Ruixuan Liu, Yang Cao, Hong Chen +2
Federated Learning (FL) is a promising machine learning paradigm that enables the analyzer to train a model without collecting users' raw data. To ensure users' privacy, differenti…
FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selection
Ruixuan Liu, Yang Cao, Masatoshi Yoshikawa +1
As massive data are produced from small gadgets, federated learning on mobile devices has become an emerging trend. In the federated setting, Stochastic Gradient Descent (SGD) has…
JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignment
Bo Chen, Jing Zhang, Xiaobin Tang +2
Abstract. Cross-lingual knowledge alignment is the cornerstone in building a comprehensive knowledge graph (KG), which can benefit various knowledge-driven applications. As the str…