Contextual Memory Trees

We design and study a Contextual Memory Tree (CMT), a learning memory controller that inserts new memories into an experience store of unbounded size. It is designed to efficiently query for memories from that store, supporting logarithmic time insertion and retrieval operations. Hence CMT can be integrated into existing statistical learning algorithms as an augmented memory unit without substantially increasing training and inference computation. We demonstrate the efficacy of CMT by augmenting existing multi-class and multi-label classification algorithms with CMT and observe statistical improvement. We also test CMT learning on several image-captioning tasks to demonstrate that it performs computationally better than a simple nearest neighbors memory system while benefitting from reward learning.

[1]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[2]  Andrei Z. Broder,et al.  Efficient query evaluation using a two-level retrieval process , 2003, CIKM '03.

[3]  Jure Leskovec,et al.  Hidden factors and hidden topics: understanding rating dimensions with review text , 2013, RecSys.

[4]  Shachar Lovett,et al.  Unsupervised SVMs: On the Complexity of the Furthest Hyperplane Problem , 2012, COLT.

[5]  L. Brouwer.  Über Abbildung von Mannigfaltigkeiten , 1911 .

[6]  Cyrus Rashtchian,et al.  Collecting Image Annotations Using Amazon’s Mechanical Turk , 2010, Mturk@HLT-NAACL.

[7]  Nicole Immorlica,et al.  Locality-sensitive hashing scheme based on p-stable distributions , 2004, SCG '04.

[8]  Manik Varma,et al.  FastXML: a fast, accurate and stable tree-classifier for extreme multi-label learning , 2014, KDD.

[9]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[10]  Gerasimos Spanakis,et al.  A Retrieval-Based Dialogue System Utilizing Utterance and Context Embeddings , 2017, 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA).

[11]  Prateek Jain,et al.  Sparse Local Embeddings for Extreme Multi-label Classification , 2015, NIPS.

[12]  Sanjoy Dasgupta,et al.  Randomized Partition Trees for Nearest Neighbor Search , 2014, Algorithmica.

[13]  Ali Farhadi,et al.  Attribute Discovery via Predictable Discriminative Binary Codes , 2012, ECCV.

[14]  Dale Schuurmans,et al.  Unsupervised and Semi-Supervised Multi-Class Support Vector Machines , 2005, AAAI.

[15]  John Langford,et al.  Logarithmic Time One-Against-Some , 2016, ICML.

[16]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[17]  Ryan M. Rifkin,et al.  In Defense of One-Vs-All Classification , 2004, J. Mach. Learn. Res..

[18]  John Langford,et al.  Logarithmic Time Online Multiclass prediction , 2015, NIPS.

[19]  Sergio Gomez Colmenarejo,et al.  Hybrid computing using a neural network with dynamic external memory , 2016, Nature.

[20]  A. Zubiaga.  Enhancing Navigation on Wikipedia with Social Tags , 2012, ArXiv.

[21]  Arnold W. M. Smeulders,et al.  The Amsterdam Library of Object Images , 2004, International Journal of Computer Vision.

[22]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[23]  Yong Wang,et al.  Search Engine Guided Non-Parametric Neural Machine Translation , 2017, ArXiv.

[24]  Aurko Roy,et al.  Learning to Remember Rare Events , 2017, ICLR.

[25]  John Langford,et al.  Cover trees for nearest neighbor , 2006, ICML.

[26]  Ping Li,et al.  Improved Asymmetric Locality Sensitive Hashing (ALSH) for Maximum Inner Product Search (MIPS) , 2014, UAI.

[27]  Peter Young,et al.  Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics , 2013, J. Artif. Intell. Res..

[28]  Ivan Laptev,et al.  Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  John Langford,et al.  Conditional Probability Tree Estimation Analysis and Algorithms , 2009, UAI.