I
Ivor W. Tsang
Researcher at University of Technology, Sydney
Publications - 361
Citations - 22076
Ivor W. Tsang is an academic researcher from University of Technology, Sydney. The author has contributed to research in topics: Computer science & Support vector machine. The author has an hindex of 64, co-authored 322 publications receiving 18649 citations. Previous affiliations of Ivor W. Tsang include Hong Kong University of Science and Technology & Agency for Science, Technology and Research.
Papers
More filters
Posted Content
Learning Image-Specific Attributes by Hyperbolic Neighborhood Graph Propagation
Xiaofeng Xu,Xiaofeng Xu,Ivor W. Tsang,Xiaofeng Cao,Ruiheng Zhang,Ruiheng Zhang,Chuancai Liu,Chuancai Liu +7 more
TL;DR: This paper proposes to learn image-specific attributes by graph-based attribute propagation by considering the intrinsic property of hyperbolic geometry that its distance expands exponentially, andHyperbolic neighborhood graph (HNG) is constructed to characterize the relationship between samples.
Posted Content
Neural Optimization Kernel: Towards Robust Deep Learning.
Yueming Lyu,Ivor W. Tsang +1 more
TL;DR: In this article, a neural optimization kernel (NOK) was proposed, which is defined as the inner product between two $T$-step updated functionals in RKHS w.r.t. a regularized optimization problem.
Journal ArticleDOI
Nonparametric Iterative Machine Teaching
TL;DR: In this paper , the authors consider the problem of nonparametric iterative machine teaching (NIMT), where the teacher provides examples to the learner iteratively such that the learners can achieve fast convergence to a target model.
Posted Content
Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Network.
TL;DR: Wang et al. as mentioned in this paper proposed a novel collaborative prediction unit (CoPU), which aggregates the predictions from multiple collaborative predictors according to a collaborative graph, and the edge weights of the collaborative graph reflect the importance of each predictor.
Journal ArticleDOI
DifFormer: Multi-Resolutional Differencing Transformer With Dynamic Ranging for Time Series Analysis.
TL;DR: Difformer as discussed by the authors proposes a novel multi-resolutional differencing mechanism, which is able to progressively and adaptively make nuanced yet meaningful changes prominent, meanwhile, the periodic or cyclic patterns can be dynamically captured with flexible lagging and dynamic ranging operations.