scholarly journals Learn the Highest Label and Rest Label Description Degrees

2021 ◽  
Author(s):  
Jing Wang ◽  
Xin Geng
Keyword(s):  
Theoretical Analysis ◽  
Real World ◽  
Classification Performance ◽  
Experimental Results ◽  
Classification Problems ◽  
Large Margin ◽  
Performance Deterioration ◽  
Real World Datasets ◽  
New Perspective ◽  
Label Distribution

Although Label Distribution Learning (LDL) has found wide applications in varieties of classification problems, it may face the challenge of objective mismatch -- LDL neglects the optimal label for the sake of learning the whole label distribution, which leads to performance deterioration. To improve classification performance and solve the objective mismatch, we propose a new LDL algorithm called LDL-HR. LDL-HR provides a new perspective of label distribution, \textit{i.e.}, a combination of the \textbf{highest label} and the \textbf{rest label description degrees}. It works as follows. First, we learn the highest label by fitting the degenerated label distribution and large margin. Second, we learn the rest label description degrees to exploit generalization. Theoretical analysis shows the generalization of LDL-HR. Besides, the experimental results on 18 real-world datasets validate the statistical superiority of our method.

scholarly journals Differentially Private Pairwise Learning Revisited

2021 ◽  
Author(s):  
Zhiyu Xue ◽  
Shaoyang Yang ◽  
Mengdi Huai ◽  
Di Wang
Keyword(s):  
Theoretical Analysis ◽  
Real World ◽  
Differential Privacy ◽  
Experimental Results ◽  
Loss Functions ◽  
Privacy Issue ◽  
Strongly Convex ◽  
Pairwise Learning ◽  
General Convex ◽  
Real World Datasets

Instead of learning with pointwise loss functions, learning with pairwise loss functions (pairwise learning) has received much attention recently as it is more capable of modeling the relative relationship between pairs of samples. However, most of the existing algorithms for pairwise learning fail to take into consideration the privacy issue in their design. To address this issue, previous work studied pairwise learning in the Differential Privacy (DP) model. However, their utilities (population errors) are far from optimal. To address the sub-optimal utility issue, in this paper, we proposed new pure or approximate DP algorithms for pairwise learning. Specifically, under the assumption that the loss functions are Lipschitz, our algorithms could achieve the optimal expected population risk for both strongly convex and general convex cases. We also conduct extensive experiments on real-world datasets to evaluate the proposed algorithms, experimental results support our theoretical analysis and show the priority of our algorithms.

scholarly journals OFCOD: On the Fly Clustering Based Outlier Detection Framework

Data ◽  
2020 ◽  
Vol 6 (1) ◽  
pp. 1
Author(s):  
Ahmed Elmogy ◽  
Hamada Rizk ◽  
Amany M. Sarhan
Keyword(s):  
Data Mining ◽  
Image Processing ◽  
Intrusion Detection ◽  
Real Time ◽  
Outlier Detection ◽  
Real World ◽  
Medical Data ◽  
Experimental Results ◽  
Real Time Applications ◽  
Real World Datasets

In data mining, outlier detection is a major challenge as it has an important role in many applications such as medical data, image processing, fraud detection, intrusion detection, and so forth. An extensive variety of clustering based approaches have been developed to detect outliers. However they are by nature time consuming which restrict their utilization with real-time applications. Furthermore, outlier detection requests are handled one at a time, which means that each request is initiated individually with a particular set of parameters. In this paper, the first clustering based outlier detection framework, (On the Fly Clustering Based Outlier Detection (OFCOD)) is presented. OFCOD enables analysts to effectively find out outliers on time with request even within huge datasets. The proposed framework has been tested and evaluated using two real world datasets with different features and applications; one with 699 records, and another with five millions records. The experimental results show that the performance of the proposed framework outperforms other existing approaches while considering several evaluation metrics.

Review Summary Generation in Online Systems: Frameworks for Supervised and Unsupervised Scenarios

2021 ◽  
Vol 15 (3) ◽  
pp. 1-33
Author(s):  
Wenjun Jiang ◽  
Jing Chen ◽  
Xiaofei Ding ◽  
Jie Wu ◽  
Jiawei He ◽  
...  
Keyword(s):  
Decision Making ◽  
Real World ◽  
Text Summarization ◽  
Experimental Results ◽  
Product Review ◽  
Comprehensive Review ◽  
Online Systems ◽  
Real World Datasets ◽  
Different Characteristics

In online systems, including e-commerce platforms, many users resort to the reviews or comments generated by previous consumers for decision making, while their time is limited to deal with many reviews. Therefore, a review summary, which contains all important features in user-generated reviews, is expected. In this article, we study “how to generate a comprehensive review summary from a large number of user-generated reviews.” This can be implemented by text summarization, which mainly has two types of extractive and abstractive approaches. Both of these approaches can deal with both supervised and unsupervised scenarios, but the former may generate redundant and incoherent summaries, while the latter can avoid redundancy but usually can only deal with short sequences. Moreover, both approaches may neglect the sentiment information. To address the above issues, we propose comprehensive Review Summary Generation frameworks to deal with the supervised and unsupervised scenarios. We design two different preprocess models of re-ranking and selecting to identify the important sentences while keeping users’ sentiment in the original reviews. These sentences can be further used to generate review summaries with text summarization methods. Experimental results in seven real-world datasets (Idebate, Rotten Tomatoes Amazon, Yelp, and three unlabelled product review datasets in Amazon) demonstrate that our work performs well in review summary generation. Moreover, the re-ranking and selecting models show different characteristics.

scholarly journals Multiple Noisy Label Distribution Propagation for Crowdsourcing

2019 ◽  
Author(s):  
Hao Zhang ◽  
Liangxiao Jiang ◽  
Wenqiang Xu
Keyword(s):  
Supervised Learning ◽  
Real World ◽  
Effective Means ◽  
Ground Truth ◽  
Cost Effective ◽  
Nearest Neighbors ◽  
True Label ◽  
Real World Datasets ◽  
The Individual ◽  
Label Distribution

Crowdsourcing services provide a fast, efficient, and cost-effective means of obtaining large labeled data for supervised learning. Ground truth inference, also called label integration, designs proper aggregation strategies to infer the unknown true label of each instance from the multiple noisy label set provided by ordinary crowd workers. However, to the best of our knowledge, nearly all existing label integration methods focus solely on the multiple noisy label set itself of the individual instance while totally ignoring the intercorrelation among multiple noisy label sets of different instances. To solve this problem, a multiple noisy label distribution propagation (MNLDP) method is proposed in this study. MNLDP first transforms the multiple noisy label set of each instance into its multiple noisy label distribution and then propagates its multiple noisy label distribution to its nearest neighbors. Consequently, each instance absorbs a fraction of the multiple noisy label distributions from its nearest neighbors and yet simultaneously maintains a fraction of its own original multiple noisy label distribution. Promising experimental results on simulated and real-world datasets validate the effectiveness of our proposed method.

scholarly journals Adaptive Double-Exploration Tradeoff for Outlier Detection

2020 ◽  
Vol 34 (04) ◽  
pp. 6837-6844
Author(s):  
Xiaojin Zhang ◽  
Honglei Zhuang ◽  
Shengyu Zhang ◽  
Yuan Zhou
Keyword(s):  
Confidence Interval ◽  
Outlier Detection ◽  
Real World ◽  
Efficient Algorithm ◽  
Experimental Results ◽  
Sample Complexity ◽  
Bandit Problem ◽  
Real World Datasets ◽  
Synthetic Datasets ◽  
The Individual

We study a variant of the thresholding bandit problem (TBP) in the context of outlier detection, where the objective is to identify the outliers whose rewards are above a threshold. Distinct from the traditional TBP, the threshold is defined as a function of the rewards of all the arms, which is motivated by the criterion for identifying outliers. The learner needs to explore the rewards of the arms as well as the threshold. We refer to this problem as "double exploration for outlier detection". We construct an adaptively updated confidence interval for the threshold, based on the estimated value of the threshold in the previous rounds. Furthermore, by automatically trading off exploring the individual arms and exploring the outlier threshold, we provide an efficient algorithm in terms of the sample complexity. Experimental results on both synthetic datasets and real-world datasets demonstrate the efficiency of our algorithm.

Combining Expert Strategies in Multimodal Classification

2014 ◽  
Vol 590 ◽  
pp. 693-697
Author(s):  
Jing Peng
Keyword(s):  
Real World ◽  
Classification Performance ◽  
Experimental Results ◽  
Robust Classification ◽  
Multimodal Classification ◽  
Novel Algorithm

In multimodal classification, we look for a set of strategies for mining and exploiting the most informative modalities for a given situation. These strategies are computations performed by the algorithms. In this paper, we propose to consider strategies as advice given to an algorithm by “expert.” There can be several classification strategies. Each strategy makes different assumptions regarding the fidelity of a sensor modality and uses different data to arrive at its estimates. Each strategy may place different trust in a sensor at different times, and each may be better in different situations. In this paper, we introduce a novel algorithm for combining expert strategies to achieve robust classification performance in a multimodal setting. We provide experimental results using real world examples to demonstrate the efficacy of the proposed algorithm.

SOCIAL INTEREST FOR USER SELECTING ITEMS IN RECOMMENDER SYSTEMS

2013 ◽  
Vol 24 (04) ◽  
pp. 1350022 ◽  
Author(s):  
DA-CHENG NIE ◽  
MING-JING DING ◽  
YAN FU ◽  
JUN-LIN ZHOU ◽  
ZI-KE ZHANG
Keyword(s):  
Recommender Systems ◽  
Real World ◽  
Social Interest ◽  
Experimental Results ◽  
Simple Method ◽  
The Social ◽  
Social Interests ◽  
Similarity Computation ◽  
Real World Datasets

Recommender systems have developed rapidly and successfully. The system aims to help users find relevant items from a potentially overwhelming set of choices. However, most of the existing recommender algorithms focused on the traditional user-item similarity computation, other than incorporating the social interests into the recommender systems. As we know, each user has their own preference field, they may influence their friends' preference in their expert field when considering the social interest on their friends' item collecting. In order to model this social interest, in this paper, we proposed a simple method to compute users' social interest on the specific items in the recommender systems, and then integrate this social interest with similarity preference. The experimental results on two real-world datasets Epinions and Friendfeed show that this method can significantly improve not only the algorithmic precision-accuracy but also the diversity-accuracy.

scholarly journals Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6661
Author(s):  
Lars Schmarje ◽  
Johannes Brünger ◽  
Monty Santarossa ◽  
Simon-Martin Schröder ◽  
Rainer Kiko ◽  
...  
Keyword(s):  
Deep Learning ◽  
Real World ◽  
Supervised Classification ◽  
Limited Information ◽  
Classification Problems ◽  
Previous State ◽  
Supervised Methods ◽  
Real World Datasets ◽  
Fuzzy Labels

Deep learning has been successfully applied to many classification problems including underwater challenges. However, a long-standing issue with deep learning is the need for large and consistently labeled datasets. Although current approaches in semi-supervised learning can decrease the required amount of annotated data by a factor of 10 or even more, this line of research still uses distinct classes. For underwater classification, and uncurated real-world datasets in general, clean class boundaries can often not be given due to a limited information content in the images and transitional stages of the depicted objects. This leads to different experts having different opinions and thus producing fuzzy labels which could also be considered ambiguous or divergent. We propose a novel framework for handling semi-supervised classifications of such fuzzy labels. It is based on the idea of overclustering to detect substructures in these fuzzy labels. We propose a novel loss to improve the overclustering capability of our framework and show the benefit of overclustering for fuzzy labels. We show that our framework is superior to previous state-of-the-art semi-supervised methods when applied to real-world plankton data with fuzzy labels. Moreover, we acquire 5 to 10% more consistent predictions of substructures.

scholarly journals A New Method for Solving Supervised Data Classification Problems

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Parvaneh Shabanzadeh ◽  
Rubiyah Yusof
Keyword(s):  
Mining Industry ◽  
Data Classification ◽  
Classification Performance ◽  
Classification Model ◽  
Selection Algorithm ◽  
Classification Problems ◽  
Nonsmooth Nonconvex Optimization ◽  
Derivative Free ◽  
Real World Datasets ◽  
New Feature

Supervised data classification is one of the techniques used to extract nontrivial information from data. Classification is a widely used technique in various fields, including data mining, industry, medicine, science, and law. This paper considers a new algorithm for supervised data classification problems associated with the cluster analysis. The mathematical formulations for this algorithm are based on nonsmooth, nonconvex optimization. A new algorithm for solving this optimization problem is utilized. The new algorithm uses a derivative-free technique, with robustness and efficiency. To improve classification performance and efficiency in generating classification model, a new feature selection algorithm based on techniques of convex programming is suggested. Proposed methods are tested on real-world datasets. Results of numerical experiments have been presented which demonstrate the effectiveness of the proposed algorithms.

scholarly journals Label Enhancement for Label Distribution Learning

2018 ◽  
Author(s):  
Ning Xu ◽  
An Tao ◽  
Xin Geng
Keyword(s):  
Learning Process ◽  
Real World ◽  
Feature Space ◽  
Graph Laplacian ◽  
Training Set ◽  
Topological Information ◽  
Label Distribution Learning ◽  
Real World Datasets ◽  
Label Distribution ◽  
Training Sets

Label distribution is more general than both single-label annotation and multi-label annotation. It covers a certain number of labels, representing the degree to which each label describes the instance. The learning process on the instances labeled by label distributions is called label distribution learning (LDL). Unfortunately, many training sets only contain simple logical labels rather than label distributions due to the difficulty of obtaining the label distributions directly.  To solve the problem, one way is to recover the label distributions from the logical labels in the training set via leveraging the topological information of the feature space and the correlation among the labels. Such process of recovering label distributions from logical labels is defined as label enhancement (LE), which reinforces the supervision information in the training sets. This paper proposes a novel LE algorithm called Graph Laplacian Label Enhancement (GLLE). Experimental results on one artificial dataset and fourteen real-world datasets show clear advantages of GLLE over several existing LE algorithms.

Sign in / Sign up

Export Citation Format

Share Document