Representation Learning by Reconstructing Neighborhoods

Since its introduction, unsupervised representation learning has attracted a lot of attention from the research community, as it is demonstrated to be highly effective and easy-to-apply in tasks such as dimension reduction, clustering, visualization, information retrieval, and semi-supervised learning. In this work, we propose a novel unsupervised representation learning framework called neighbor-encoder, in which domain knowledge can be easily incorporated into the learning process without modifying the general encoder-decoder architecture of the classic autoencoder.In contrast to autoencoder, which reconstructs the input data itself, neighbor-encoder reconstructs the input data's neighbors. As the proposed representation learning problem is essentially a neighbor reconstruction problem, domain knowledge can be easily incorporated in the form of an appropriate definition of similarity between objects. Based on that observation, our framework can leverage any off-the-shelf similarity search algorithms or side information to find the neighbor of an input object. Applications of other algorithms (e.g., association rule mining) in our framework are also possible, given that the appropriate definition of neighbor can vary in different contexts. We have demonstrated the effectiveness of our framework in many diverse domains, including images, text, and time series, and for various data mining tasks including classification, clustering, and visualization. Experimental results show that neighbor-encoder not only outperforms autoencoder in most of the scenarios we consider, but also achieves the state-of-the-art performance on text document clustering.

[1]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[2]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[3]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

[4]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[5]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[6]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[7]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[8]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[9]  Nitesh V. Chawla,et al.  metapath2vec: Scalable Representation Learning for Heterogeneous Networks , 2017, KDD.

[10]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[11]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[12]  Didier Stricker,et al.  Creating and benchmarking a new dataset for physical activity monitoring , 2012, PETRA '12.

[13]  Marc'Aurelio Ranzato,et al.  Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Yiming Yang,et al.  RCV1: A New Benchmark Collection for Text Categorization Research , 2004, J. Mach. Learn. Res..

[15]  Ole Winther,et al.  Autoencoding beyond pixels using a learned similarity metric , 2015, ICML.

[16]  Brendan J. Frey,et al.  Winner-Take-All Autoencoders , 2014, NIPS.

[17]  Trevor Darrell,et al.  Learning Features by Watching Objects Move , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[19]  Yi-Hsuan Yang,et al.  Generating Music Medleys via Playing Music Puzzle Games , 2017, AAAI.

[20]  Jitendra Malik,et al.  Learning to See by Moving , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[21]  Mingzhe Wang,et al.  LINE: Large-scale Information Network Embedding , 2015, WWW.

[22]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[23]  Yi-Hsuan Yang,et al.  Similarity Embedding Network for Unsupervised Sequential Pattern Learning by Playing Music Puzzle Games , 2017, ArXiv.

[24]  Cyrus Shahabi,et al.  m-TSNE: A Framework for Visualizing High-Dimensional Multivariate Time Series , 2017, ArXiv.

[25]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[26]  Kristen Grauman,et al.  Learning Image Representations Tied to Ego-Motion , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[27]  Nitish Srivastava,et al.  Unsupervised Learning of Video Representations using LSTMs , 2015, ICML.

[28]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[29]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[30]  Didier Stricker,et al.  Introducing a New Benchmarked Dataset for Activity Monitoring , 2012, 2012 16th International Symposium on Wearable Computers.

[31]  Daniel R. Figueiredo,et al.  struc2vec: Learning Node Representations from Structural Identity , 2017, KDD.

[32]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[33]  Lei Zheng,et al.  Joint Deep Modeling of Users and Items Using Reviews for Recommendation , 2017, WSDM.

[34]  Yu Chen,et al.  KATE: K-Competitive Autoencoder for Text , 2017, KDD.

[35]  Bo Yang,et al.  Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering , 2016, ICML.

[36]  Armand Joulin,et al.  Unsupervised Learning by Predicting Noise , 2017, ICML.

[37]  William W. Cohen,et al.  TransNets: Learning to Transform for Recommendation , 2017, RecSys.

[38]  Thomas Hofmann,et al.  Greedy Layer-Wise Training of Deep Networks , 2007 .

[39]  Eamonn J. Keogh,et al.  Matrix Profile VI: Meaningful Multidimensional Motif Discovery , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[40]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[41]  Andrew Y. Ng,et al.  Learning Feature Representations with K-Means , 2012, Neural Networks: Tricks of the Trade.

[42]  Brendan J. Frey,et al.  k-Sparse Autoencoders , 2013, ICLR.

[43]  Ana Margarida de Jesus,et al.  Improving Methods for Single-label Text Categorization , 2007 .

[44]  Abhinav Gupta,et al.  Unsupervised Learning of Visual Representations Using Videos , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).