Adaptive learning with covariate shift-detection for non-stationary environments

Learning with dataset shift is a major challenge in non-stationary environments wherein the input data distribution may shift over time. Detecting the dataset shift point in the time-series data, where the distribution of time-series shifts its properties, is of utmost interest. Dataset shift exists in a broad range of real-world systems. In such systems, there is a need for continuous monitoring of the process behavior and tracking the state of the shift so as to decide about initiating adaptation in a timely manner. This paper presents an adaptive learning algorithm with dataset shift-detection using an exponential weighted moving average (EWMA) model based test in a non-stationary environment. The proposed method initiates the adaptation by reconfiguring the knowledge-base of the classifier. This algorithm is suitable for real-time learning in non-stationary environments. Its performance is evaluated through experiments using synthetic datasets. Results show that it reacts well to different covariate shifts.

[1]  Niall M. Adams,et al.  The impact of changing populations on classifier performance , 1999, KDD '99.

[2]  Xiaojin Zhu,et al.  --1 CONTENTS , 2006 .

[3]  Robi Polikar,et al.  COMPOSE: A Semisupervised Learning Framework for Initially Labeled Nonstationary Streaming Data , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Robi Polikar,et al.  Incremental Learning of Concept Drift in Nonstationary Environments , 2011, IEEE Transactions on Neural Networks.

[5]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[6]  Xindong Wu,et al.  Conceptual equivalence for contrast mining in classification learning , 2008, Data Knowl. Eng..

[7]  Cesare Alippi,et al.  Just-in-time ensemble of classifiers , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[8]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[9]  David A. Cieslak,et al.  A framework for monitoring classifiers’ performance: when and why failure occurs? , 2009, Knowledge and Information Systems.

[10]  PolikarRobi,et al.  Incremental Learning of Concept Drift in Nonstationary Environments , 2011 .

[11]  João Gama,et al.  Learning with Drift Detection , 2004, SBIA.

[12]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[13]  Girijesh Prasad,et al.  Dataset Shift Detection in Non-stationary Environments Using EWMA Charts , 2013, 2013 IEEE International Conference on Systems, Man, and Cybernetics.

[14]  Girijesh Prasad,et al.  EWMA Based Two-Stage Dataset Shift-Detection in Non-stationary Environments , 2013, AIAI.

[15]  Cesare Alippi,et al.  Just-in-Time Adaptive Classifiers—Part II: Designing the Classifier , 2008, IEEE Transactions on Neural Networks.

[16]  Cesare Alippi,et al.  Just-In-Time Classifiers for Recurrent Concepts , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[17]  Jeffrey Xu Yu,et al.  Mining Changes of Classification by Correspondence Tracing , 2003, SDM.

[18]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[19]  Cesare Alippi,et al.  A just-in-time adaptive classification system based on the intersection of confidence intervals rule , 2011, Neural Networks.

[20]  Neil D. Lawrence,et al.  Dataset Shift in Machine Learning , 2009 .

[21]  Francisco Herrera,et al.  A unifying view on dataset shift in classification , 2012, Pattern Recognit..

[22]  Ricard Gavaldà,et al.  Learning from Time-Changing Data with Adaptive Windowing , 2007, SDM.

[23]  J. C. Schlimmer,et al.  Incremental learning from noisy data , 2004, Machine Learning.

[24]  Nathalie Japkowicz,et al.  Assessing the Impact of Changing Environments on Classifier Performance , 2008, Canadian Conference on AI.

[25]  Amos Storkey,et al.  When Training and Test Sets are Different: Characterising Learning Transfer , 2013 .

[26]  J. L. Hemmen,et al.  Nonlinear neural networks. , 1986, Physical review letters.

[27]  Gerhard Widmer,et al.  Learning in the Presence of Concept Drift and Hidden Contexts , 1996, Machine Learning.