arXiv subjects

Pengtao Xie

Publications and source records attributed to Pengtao Xie.

114 records · Page 7Linked to original sources

arXiv2015

Petuum: A New Platform for Distributed Machine Learning on Big Data

What is a systematic way to efficiently apply a wide spectrum of advanced ML programs to industrial scale problems, using Big Models (up to 100s of billions of parameters) on Big Data (up to terabytes or petabytes)? Modern parallelization strategies employ fine-grained operations and scheduling beyond the classic bulk-synchronous processing paradigm popularized by MapReduce, or even specialized graph-based execution that relies on graph representations of ML programs. The variety of approaches tends to pull systems and algorithms design in different directions, and it remains difficult to find a universal platform applicable to a wide range of ML programs at scale. We propose a general-purpose framework that systematically addresses data- and model-parallel challenges in large-scale ML, by observing that many ML programs are fundamentally optimization-centric and admit error-tolerant, iterative-convergent algorithmic solutions. This presents unique opportunities for an integrative system design, such as bounded-error network synchronization and dynamic scheduling based on ML program structure. We demonstrate the efficacy of these system designs versus well-known implementations of modern ML algorithms, allowing ML programs to run in much less time and at considerably larger model sizes, even on modestly-sized compute clusters.

stat.ML↗

arXiv2015

CryptGraph: Privacy Preserving Graph Analytics on Encrypted Graph

Many graph mining and analysis services have been deployed on the cloud, which can alleviate users from the burden of implementing and maintaining graph algorithms. However, putting graph analytics on the cloud can invade users' privacy. To solve this problem, we propose CryptGraph, which runs graph analytics on encrypted graph to preserve the privacy of both users' graph data and the analytic results. In CryptGraph, users encrypt their graphs before uploading them to the cloud. The cloud runs graph analysis on the encrypted graphs and obtains results which are also in encrypted form that the cloud cannot decipher. During the process of computing, the encrypted graphs are never decrypted on the cloud side. The encrypted results are sent back to users and users perform the decryption to obtain the plaintext results. In this process, users' graphs and the analytics results are both encrypted and the cloud knows neither of them. Thereby, users' privacy can be strongly protected. Meanwhile, with the help of homomorphic encryption, the results analyzed from the encrypted graphs are guaranteed to be correct. In this paper, we present how to encrypt a graph using homomorphic encryption and how to query the structure of an encrypted graph by computing polynomials. To solve the problem that certain operations are not executable on encrypted graphs, we propose hard computation outsourcing to seek help from users. Using two graph algorithms as examples, we show how to apply our methods to perform analytics on encrypted graphs. Experiments on two datasets demonstrate the correctness and feasibility of our methods.

cs.CR↗

arXiv2014

Crypto-Nets: Neural Networks over Encrypted Data

The problem we address is the following: how can a user employ a predictive model that is held by a third party, without compromising private information. For example, a hospital may wish to use a cloud service to predict the readmission risk of a patient. However, due to regulations, the patient's medical files cannot be revealed. The goal is to make an inference using the model, without jeopardizing the accuracy of the prediction or the privacy of the data. To achieve high accuracy, we use neural networks, which have been shown to outperform other learning models for many tasks. To achieve the privacy requirements, we use homomorphic encryption in the following protocol: the data owner encrypts the data and sends the ciphertexts to the third party to obtain a prediction from a trained model. The model operates on these ciphertexts and sends back the encrypted prediction. In this protocol, not only the data remains private, even the values predicted are available only to the data owner. Using homomorphic encryption and modifications to the activation functions and training algorithms of neural networks, we show that it is protocol is possible and may be feasible. This method paves the way to build a secure cloud-based neural network prediction services without invading users' privacy.

cs.LG↗

arXiv2014

Cauchy Principal Component Analysis

Principal Component Analysis (PCA) has wide applications in machine learning, text mining and computer vision. Classical PCA based on a Gaussian noise model is fragile to noise of large magnitude. Laplace noise assumption based PCA methods cannot deal with dense noise effectively. In this paper, we propose Cauchy Principal Component Analysis (Cauchy PCA), a very simple yet effective PCA method which is robust to various types of noise. We utilize Cauchy distribution to model noise and derive Cauchy PCA under the maximum likelihood estimation (MLE) framework with low rank constraint. Our method can robustly estimate the low rank matrix regardless of whether noise is large or small, dense or sparse. We analyze the robustness of Cauchy PCA from a robust statistics view and present an efficient singular value projection optimization method. Experimental results on both simulated data and real applications demonstrate the robustness of Cauchy PCA to various noise patterns.

cs.LG↗

arXiv2014

Large Scale Distributed Distance Metric Learning

In large scale machine learning and data mining problems with high feature dimensionality, the Euclidean distance between data points can be uninformative, and Distance Metric Learning (DML) is often desired to learn a proper similarity measure (using side information such as example data pairs being similar or dissimilar). However, high dimensionality and large volume of pairwise constraints in modern big data can lead to prohibitive computational cost for both the original DML formulation in Xing et al. (2002) and later extensions. In this paper, we present a distributed algorithm for DML, and a large-scale implementation on a parameter server architecture. Our approach builds on a parallelizable reformulation of Xing et al. (2002), and an asynchronous stochastic gradient descent optimization procedure. To our knowledge, this is the first distributed solution to DML, and we show that, on a system with 256 CPU cores, our program is able to complete a DML task on a dataset with 1 million data points, 22-thousand features, and 200 million labeled data pairs, in 15 hours; and the learned metric shows great effectiveness in properly measuring distances.

cs.LG↗

arXiv2013

Integrating Document Clustering and Topic Modeling

Document clustering and topic modeling are two closely related tasks which can mutually benefit each other. Topic modeling can project documents into a topic space which facilitates effective document clustering. Cluster labels discovered by document clustering can be incorporated into topic models to extract local topics specific to each cluster and global topics shared by all clusters. In this paper, we propose a multi-grain clustering topic model (MGCTM) which integrates document clustering and topic modeling into a unified framework and jointly performs the two tasks to achieve the overall best performance. Our model tightly couples two components: a mixture component used for discovering latent groups in document collection and a topic model component used for mining multi-grain topics including local topics specific to each cluster and global topics shared across clusters.We employ variational inference to approximate the posterior of hidden variables and learn model parameters. Experiments on two datasets demonstrate the effectiveness of our model.

cs.LG↗