95 citations · 102 across the 15 of their papers we have counts for
15 papers
Aggregation Weighting of Federated Learning via Generalization Bound Estimation
Mingwei Xu, Xiaofeng Cao, Ivor W. Tsang +1
Federated Learning (FL) typically aggregates client model parameters using a weighting approach determined by sample proportions. However, this naive weighting method may lead to u…
Nonparametric Iterative Machine Teaching
Chen Zhang, Xiaofeng Cao, Weiyang Liu +2
In this paper, we consider the problem of Iterative Machine Teaching (IMT), where the teacher provides examples to the learner iteratively such that the learner can achieve fast co…
Policy Dispersion in Non-Markovian Environment
Bohao Qu, Xiaofeng Cao, Jielong Yang +4
Markov Decision Process (MDP) presents a mathematical framework to formulate the learning processes of agents in reinforcement learning. MDP is limited by the Markovian assumption…
One-shot Machine Teaching: Cost Very Few Examples to Converge Faster
Chen Zhang, Xiaofeng Cao, Yi Chang +1
Artificial intelligence is to teach machines to take actions like humans. To achieve intelligent teaching, the machine learning community becomes to think about a promising topic n…
Data-Efficient Learning via Minimizing Hyperspherical Energy
Xiaofeng Cao, Weiyang Liu, Ivor W. Tsang
Deep learning on large-scale data is dominant nowadays. The unprecedented scale of data has been arguably one of the most important driving forces for the success of deep learning.…
A Survey of Learning on Small Data: Generalization, Optimization, and Challenge
Xiaofeng Cao, Weixin Bu, Shengjun Huang +4
Learning on big data brings success for artificial intelligence (AI), but the annotation and training costs are expensive. In future, learning on small data that approximates the g…
Black-box Generalization of Machine Teaching
Xiaofeng Cao, Yaming Guo, Ivor W. Tsang +1
Hypothesis-pruning maximizes the hypothesis updates for active learning to find those desired unlabeled data. An inherent assumption is that this learning manner can derive those u…
Hyperbolic Uncertainty Aware Semantic Segmentation
Bike Chen, Wei Peng, Xiaofeng Cao +1
Semantic segmentation (SS) aims to classify each pixel into one of the pre-defined classes. This task plays an important role in self-driving cars and autonomous drones. In SS, man…
Distribution Matching for Machine Teaching
Xiaofeng Cao, Ivor W. Tsang
Machine teaching is an inverse problem of machine learning that aims at steering the student learner towards its target hypothesis, in which the teacher has already known the stude…
Bayesian Active Learning by Disagreements: A Geometric Perspective
Xiaofeng Cao, Ivor W. Tsang
We present geometric Bayesian active learning by disagreements (GBALD), a framework that performs BALD on its core-set construction interacting with model uncertainty estimation. T…
Learning Image-Specific Attributes by Hyperbolic Neighborhood Graph Propagation
Xiaofeng Xu, Ivor W. Tsang, Xiaofeng Cao +2
As a kind of semantic representation of visual object descriptions, attributes are widely used in various computer vision tasks. In most of existing attribute-based research, class…
Edge Federation: Towards an Integrated Service Provisioning Model
Xiaofeng Cao, Guoming Tang, Deke Guo +2
Edge computing is a promising computing paradigm for pushing the cloud service to the network edge. To this end, edge infrastructure providers (EIPs) need to bring computation and…
Target-Independent Active Learning via Distribution-Splitting
Xiaofeng Cao, Ivor W. Tsang, Xiaofeng Xu +1
To reduce the label complexity in Agnostic Active Learning (A^2 algorithm), volume-splitting splits the hypothesis edges to reduce the Vapnik-Chervonenkis (VC) dimension in version…
A Structured Perspective of Volumes on Active Learning
Xiaofeng Cao, Ivor W. Tsang, Guandong Xu
Active Learning (AL) is a learning task that requires learners interactively query the labels of the sampled unlabeled instances to minimize the training outputs with human supervi…
A Divide-and-Conquer Approach to Geometric Sampling for Active Learning
Xiaofeng Cao
Active learning (AL) repeatedly trains the classifier with the minimum labeling budget to improve the current classification model. The training process is usually supervised by an…