Partial Multi-View Outlier Detection Based on Collective Learning

Authors: Jun Guo, Wenwu Zhu

AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on benchmark datasets show that our proposed approach consistently and significantly outperforms state-of-the-art baselines.
Researcher Affiliation Academia Jun Guo,1 Wenwu Zhu1,2 1 Tsinghua-Berkeley Shenzhen Institue, Tsinghua University, Shenzhen 518055, China 2 Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
Pseudocode Yes Algorithm 1 Partial Multi-view Outlier Detection Based on Collective Learning
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository.
Open Datasets Yes Oxford Flowers Dataset (Flowers) (Nilsback and Zisserman 2006) is comprised of 17 flower classes, with 80 images per class. ... USPS-MNIST Dataset combines two popular handwritten datasets, USPS (Hull 1994) and MNIST (Le Cun et al. 1998).
Dataset Splits No The paper describes how samples are selected and how partiality and outliers are generated ('randomly select 50 images per digit', 'delete the same number of samples', 'Partial Object Ratio (POR) from 0% to 75%', 'randomly perturb 10% of all data'), but it does not specify explicit train, validation, or test dataset splits in terms of percentages or counts for model training and evaluation.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments.
Software Dependencies No The paper does not specify any software dependencies or their version numbers (e.g., programming languages, libraries, frameworks, or solvers).
Experiment Setup Yes Since AUC is adopted as the evaluation metric, we do not need to specify the threshold τ in Algorithm 1. Then, there are two major parameters, i.e., the number of self-guided iterations T and the number of nearest neighbors k. ... we set a maximum iteration number T for the self-guided iteration. ... we judge the alternating optimization to be converged as long as the value of Eq.(7) changes not obviously ( 10 7). ... Regarding parameter k, we limit it to a certain percentage of the total number of objects. It is observed that our proposed method achieves a relatively good performance when the proportion is in the range of [3%, 5%].