IPOF: An Extremely and Excitingly Simple Outlier Detection Booster via Infinite Propagation

• URL: http://arxiv.org/abs/2108.00360v1
• Date: Sun, 1 Aug 2021 03:48:09 GMT
• Title: IPOF: An Extremely and Excitingly Simple Outlier Detection Booster via Infinite Propagation
• Authors: Sibo Zhu, Handong Zhao, Hongfu Liu
• Abstract summary: Outlier detection is one of the most popular and continuously rising topics in the data mining field. In this paper, we consider the score-based outlier detection category and point out that the performance of current outlier detection algorithms might be further boosted by score propagation. Specifically, we propose Infinite propagation of Outlier Factor (iPOF) algorithm, an extremely and excitingly simple outlier detection booster via infinite propagation.
• Score: 30.91911545889579
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Outlier detection is one of the most popular and continuously rising topics in the data mining field due to its crucial academic value and extensive industrial applications. Among different settings, unsupervised outlier detection is the most challenging and practical one, which attracts tremendous efforts from diverse perspectives. In this paper, we consider the score-based outlier detection category and point out that the performance of current outlier detection algorithms might be further boosted by score propagation. Specifically, we propose Infinite Propagation of Outlier Factor (iPOF) algorithm, an extremely and excitingly simple outlier detection booster via infinite propagation. By employing score-based outlier detectors for initialization, iPOF updates each data point's outlier score by averaging the outlier factors of its nearest common neighbors. Extensive experimental results on numerous datasets in various domains demonstrate the effectiveness and efficiency of iPOF significantly over several classical and recent state-of-the-art methods. We also provide the parameter analysis on the number of neighbors, the unique parameter in iPOF, and different initial outlier detectors for general validation. It is worthy to note that iPOF brings in positive improvements ranging from 2% to 46% on the average level, and in some cases, iPOF boosts the performance over 3000% over the original outlier detection algorithm.

Related papers

• Margin-bounded Confidence Scores for Out-of-Distribution Detection [2.373572816573706]
  We propose a novel method called Margin bounded Confidence Scores (MaCS) to address the nontrivial OOD detection problem. MaCS enlarges the disparity between ID and OOD scores, which in turn makes the decision boundary more compact. Experiments on various benchmark datasets for image classification tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-09-22T05:40:25Z)
• Rethinking Unsupervised Outlier Detection via Multiple Thresholding [15.686139522490189]
  We propose a multiple thresholding (Multi-T) module to advance existing scoring methods. It generates two thresholds that isolate inliers and outliers from the unlabelled target dataset. Experiments verify that Multi-T can significantly improve proposed outlier scoring methods.
  arXiv  Detail & Related papers  (2024-07-07T14:09:50Z)
• Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation [110.34982764201689]
  Out-of-distribution (OOD) detection is important for deploying reliable machine learning models on real-world applications. Recent advances in outlier exposure have shown promising results on OOD detection via fine-tuning model with informatively sampled auxiliary outliers. We propose a novel framework, namely, Diversified Outlier Exposure (DivOE), for effective OOD detection via informative extrapolation based on the given auxiliary outliers.
  arXiv  Detail & Related papers  (2023-10-21T07:16:09Z)
• Adaptive Thresholding Heuristic for KPI Anomaly Detection [1.57731592348751]
  A plethora of outlier detectors have been explored in the time series domain, however, in a business sense, not all outliers are anomalies of interest. This article proposes an Adaptive Thresholding Heuristic (ATH) to dynamically adjust the detection threshold based on the local properties of the data distribution and adapt to changes in time series patterns. Experimental results show that ATH is efficient making it scalable for near real time anomaly detection and flexible with forecasters and outlier detectors.
  arXiv  Detail & Related papers  (2023-08-21T06:45:28Z)
• Little Help Makes a Big Difference: Leveraging Active Learning to Improve Unsupervised Time Series Anomaly Detection [2.1684857243537334]
  A large set of anomaly detection algorithms have been deployed for detecting unexpected network incidents. Unsupervised anomaly detection algorithms often suffer from excessive false alarms. We propose to use active learning to introduce and benefit from the feedback of operators.
  arXiv  Detail & Related papers  (2022-01-25T13:54:19Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• EAD: an ensemble approach to detect adversarial examples from the hidden features of deep neural networks [1.3212032015497979]
  We propose an Ensemble Adversarial Detector (EAD) for the identification of adversarial examples. EAD combines multiple detectors that exploit distinct properties of the input instances in the internal representation of a pre-trained Deep Neural Network (DNN) We show that EAD achieves the best AUROC and AUPR in the large majority of the settings and comparable performance in the others.
  arXiv  Detail & Related papers  (2021-11-24T17:05:26Z)
• Robust and Accurate Object Detection via Adversarial Learning [111.36192453882195]
  This work augments the fine-tuning stage for object detectors by exploring adversarial examples. Our approach boosts the performance of state-of-the-art EfficientDets by +1.1 mAP on the object detection benchmark.
  arXiv  Detail & Related papers  (2021-03-23T19:45:26Z)
• Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference [150.07326223077405]
  Few-shot learning is attracting much attention to mitigate data scarcity. We present a discriminative nearest neighbor classification with deep self-attention. We propose to boost the discriminative ability by transferring a natural language inference (NLI) model.
  arXiv  Detail & Related papers  (2020-10-25T00:39:32Z)
• AP-Loss for Accurate One-Stage Object Detection [49.13608882885456]
  One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously. The former suffers much from extreme foreground-background imbalance due to the large number of anchors. This paper proposes a novel framework to replace the classification task in one-stage detectors with a ranking task.
  arXiv  Detail & Related papers  (2020-08-17T13:22:01Z)
• Multi-Scale Positive Sample Refinement for Few-Shot Object Detection [61.60255654558682]
  Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances. We propose a Multi-scale Positive Sample Refinement (MPSR) approach to enrich object scales in FSOD. MPSR generates multi-scale positive samples as object pyramids and refines the prediction at various scales.
  arXiv  Detail & Related papers  (2020-07-18T09:48:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.