Publications

@conference{Shukla2019,

title = {Interpolation-Prediction Networks for Irregularly Sampled Time Series},

author = {Satya Narayan Shukla and Benjamin Marlin},

year  = {2019},

date = {2019-05-06},

booktitle = {Seventh International Conference on Learning Representations},

abstract = {In this paper, we present a new deep learning architecture for addressing the problem of supervised learning with sparse and irregularly sampled multivariate time series. The architecture is based on the use of a semi-parametric interpolation network followed by the application of a prediction network. The interpolation network allows for information to be shared across multiple dimensions of a multivariate time series during the interpolation stage, while any standard deep learning model can be used for the prediction network. This work is motivated by the analysis of physiological time series data in electronic health records, which are sparse, irregularly sampled, and multivariate. We investigate the performance of this architecture on two datasets for both classification and regression tasks, showing that our approach outperforms a range of baseline and recently proposed models.},

keywords = {},

pubstate = {forthcoming},

tppubtype = {conference}

}

@conference{Li2019,

title = {Learning from Incomplete Data with Generative Adversarial Networks},

author = {Steven Cheng-Xian Li and Bo Jiang and Benjamin Marlin},

year  = {2019},

date = {2019-05-06},

booktitle = {Seventh International Conference on Learning Representations},

abstract = {Generative adversarial networks (GANs) have been shown to provide an effective way to model complex distributions and have obtained impressive results on various challenging tasks. However, typical GANs require fully-observed data during training. In this paper, we present a modular approach to learning GANs from incomplete observations that can be combined with different generator and discriminator networks and is amenable for use with complex, high-dimensional inputs. The proposed framework learns a complete data generator along with a mask generator that models the missingness. We further demonstrate how to impute missing data by equipping our framework with an adversarially trained imputer. We evaluate the proposed framework using a series of experiments with several types of missing completely at random missing data processes.},

keywords = {},

pubstate = {forthcoming},

tppubtype = {conference}

}

@conference{Adams2018,

title = {Learning Time Series Segmentation Models from Temporally Imprecise Labels},

author = {Roy Adams and Benjamin M. Marlin},

url = {http://auai.org/uai2018/proceedings/papers/50.pdf},

year  = {2018},

date = {2018-08-06},

journal = {Conference on Uncertainty in Artificial Intelligence},

abstract = {This paper considers the problem of learning time series segmentation models when the labeled data is subject to temporal uncertainty or noise. Our approach augments the semi-Markov conditional random field (semi-CRF) model with a probabilistic model of the label observation process. This augmentation allows us to estimate the parameters of the semi-CRF from timestamps corresponding roughly to the occurrence of segment transitions. We show how exact marginal inference can be performed in polynomial time enabling learning based on marginal likelihood maximization. Our experiments on two activity detection problems show that the proposed approach can learn models from temporally imprecise labels, and can successfully refine imprecise segmentations through posterior inference. Finally, we show how inference complexity can be reduced by a factor of 40 using static and model-based pruning of the inference dynamic program.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{288,

title = {Learning Time Series Detection Models from Temporally Imprecise Labels},

author = {Roy J Adams and Benjamin M Marlin},

url = {http://proceedings.mlr.press/v54/adams17a/adams17a.pdf},

year  = {2017},

date = {2017-01-01},

booktitle = {The 20th International Conference on Artificial Intelligence and Statistics},

abstract = {<p>In this paper, we consider a new low-quality label learning problem: learning time series detection models from temporally imprecise labels. In this problem, the data consist of a set of input time series, and supervision is provided by a sequence of noisy time stamps corresponding to the occurrence of positive class events. Such temporally imprecise labels commonly occur in areas like mobile health research where human annotators are tasked with labeling the occurrence of very short duration events. We propose a general learning framework for this problem that can accommodate different base classifiers and noise models. We present results on real mobile health data showing that the proposed framework significantly outperforms a number of alternatives including assuming that the label time stamps are noise-free, transforming the problem into the multiple instance learning framework, and learning on labels that were manually re-aligned. </p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{256,

title = {Assessing the Limits of Program-Specific Garbage Collection Performance},

author = {Nicholas Jacek and Meng-Chieh Chiu and Benjamin Marlin and Eliot J B Moss},

url = {http://dl.acm.org/citation.cfm?id=2908120},

year  = {2016},

date = {2016-01-01},

booktitle = {Programming Language Design and Implementation},

abstract = {<p>We consider the ultimate limits of program-specific garbage collector performance for real programs. We first characterize the GC schedule optimization problem using Markov Decision Processes (MDPs). Based on this characterization, we develop a method of determining, for a given program run and heap size, an optimal schedule of collections for a non-generational collector. We further explore the limits of performance of a generational collector, where it is not feasible to search the space of schedules to prove optimality. Still, we show significant improvements with Least Squares Policy Iteration, a reinforcement learning technique for solving MDPs. We demonstrate that there is considerable promise to reduce garbage collection costs by developing program-specific collection policies.</p>},

note = {<p>Distinguished Paper Award</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{279,

title = {Domain Adaptation Methods for Improving Lab-to-field Generalization of Cocaine Detection using Wearable ECG},

author = {Annamalai Natarajan and Gustavo Angarita and Edward Gaiser and Robert Malison and Deepak Ganesan and Benjamin Marlin},

url = {http://dl.acm.org/citation.cfm?id=2971666},

year  = {2016},

date = {2016-01-01},

booktitle = {2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing},

abstract = {<p>Mobile health research on illicit drug use detection typically involves a two-stage study design where data to learn detectors is first collected in lab-based trials, followed by a deployment to subjects in a free-living environment to assess detector performance. While recent work has demonstrated the feasibility of wearable sensors for illicit drug use detection in the lab setting, several key problems can limit lab-to-field generalization performance. For example, lab-based data collection often has low ecological validity, the ground-truth event labels collected in the lab may not be available at the same level of temporal granularity in the field, and there can be significant variability between subjects. In this paper, we present domain adaptation methods for assessing and mitigating potential sources of performance loss in lab-to-field generalization and apply them to the problem of cocaine use detection from wearable electrocardiogram sensor data.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{255,

title = {Hierarchical Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams},

author = {Roy Adams and Nazir Saleheen and Edison Thomaz and Abhinav Parate and Santosh Kumar and Benjamin Marlin},

url = {http://jmlr.org/proceedings/papers/v48/adams16.pdf},

year  = {2016},

date = {2016-01-01},

booktitle = {International Conference on Machine Learning},

abstract = {<p>The field of mobile health (mHealth) has the potential to yield new insights into health and behavior through the analysis of continuously recorded data from wearable health and activity sensors. In this paper, we present a hierarchical span-based conditional random field model for the key problem of jointly detecting discrete events in such sensor data streams and segmenting these events into high-level activity sessions. Our model includes higher-order cardinality factors and inter-event duration factors to capture domain-specific structure in the label space. We show that our model supports exact MAP inference in quadratic time via dynamic programming, which we leverage to perform learning in the structured support vector machine framework. We apply the model to the problems of smoking and eating detection using four real data sets. Our results show statistically significant improvements in segmentation performance at the p=0.005 level relative to a hierarchical pairwise CRF.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{290,

title = {An Improved Data Representation for Smoking Detection with Wearable Respiration Sensors},

author = {Laura Hiatt and Roy Adams and Benjamin Marlin},

year  = {2016},

date = {2016-01-01},

booktitle = {IEEE Wireless Health},

note = {<p>Late breaking extended abstract.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{257,

title = {Learning Shallow Detection Cascades for Wearable Sensor-Based Mobile Health Applications},

author = {Hamid Dadkhahi and Nazir Saleheen and Santosh Kumar and Benjamin Marlin},

url = {https://sites.google.com/site/ondeviceintelligence/icml2016/accepted-papers},

year  = {2016},

date = {2016-01-01},

booktitle = {ICML On Device Intelligence Workshop},

abstract = {<p>The field of mobile health aims to leverage recent advances in wearable on-body sensing technology and smart phone computing capabilities to develop systems that can monitor health states and deliver just-in-time adaptive interventions. However, existing work has largely focused on analyzing collected data in the off-line setting. In this paper, we propose a novel approach to learning shallow detection cascades developed explicitly for use in a real-time wearable-phone or wearable-phone-cloud systems. We apply our approach to the problem of cigarette smoking detection from a combination of wrist-worn actigraphy data and respiration chest band data using two and three stage cascades.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{278,

title = {Parsing Wireless Electrocardiogram Signals with Context Free Grammar Conditional Random Fields},

author = {Thai Nguyen and Roy J Adams and Annamalai Natarajan and Benjamin M Marlin},

url = {http://ieeexplore.ieee.org/abstract/document/7764570/},

year  = {2016},

date = {2016-01-01},

booktitle = {IEEE Wireless Health},

abstract = {<p>Recent advances in wearable sensor technology have made it possible to simultaneously collect multiple streams of physiological and context data from individuals as they go about their daily activities in natural environments. However, extracting reliable higher-level inferences from these raw data streams remains a key data analysis challenge. In this paper, we focus on the specific case of the analysis of data from wireless electrocardiogram (ECG) sensors. We present a new robust probabilistic approach to ECG morphology extraction using conditional random field context free grammar models, which have traditionally been applied to parsing problems in natural language processing. We introduce a robust context free grammar for parsing noisy ECG data, and show significantly improved performance on the ECG morphological labeling task.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{277,

title = {Real-Time Program-Specific Phase Change Detection for Java Programs},

author = {Meng-Chieh Chiu and Benjamin Marlin and Eliot Moss},

url = {http://dl.acm.org/citation.cfm?id=2972221},

year  = {2016},

date = {2016-01-01},

booktitle = {13th International Conference on Principles and Practices of Programming on the Java Platform: Virtual Machines, Languages, and Tools},

abstract = {<p>It is well-known that programs tend to have multiple phases in their execution. Because phases have impact on micro-architectural features such as caches and branch predictors, they are relevant to program performance and energy consumption. They are also relevant to detecting whether a program is executing as expected or is encountering unusual or exceptional conditions, a software engineering and program monitoring concern. We offer here a method for real-time phase change detection in Java programs. After applying a training protocol to a program of interest, our method can detect phase changes at run time for that program with good precision and recall (compared with a textquotedblleftground truthtextquotedblright definition of phases) and with small performance impact (average less than 2%). We also offer improved methodology for evaluating phase change detection mechanisms. In sum, our approach offers the first known implementation of real-time phase detection for Java programs.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Iyengar:2015:IIS:2821650.2821653,

title = {iProgram: Inferring Smart Schedules for Dumb Thermostats},

author = {Srinivasan Iyengar and Sandeep Kalra and Anushree Ghosh and David Irwin and Prashant Shenoy and Benjamin Marlin},

url = {http://doi.acm.org/10.1145/2821650.2821653},

doi = {10.1145/2821650.2821653},

isbn = {978-1-4503-3981-0},

year  = {2015},

date = {2015-01-01},

booktitle = {Proceedings of the 2Nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments},

pages = {211–220},

publisher = {ACM},

address = {New York, NY, USA},

organization = {ACM},

series = {BuildSys textquoteright15},

abstract = {<p>Heating, ventilation, and air conditioning (HVAC) accounts for over 50% of a typical hometextquoterights energy usage. A thermostat generally controls HVAC usage in a home to ensure user comfort. In this paper, we focus on making existing "dumb" programmable thermostats smart by applying energy analytics on smart meter data to infer home occupancy patterns and compute an optimized thermostat schedule. Utilities with smart meter deployments are capable of immediately applying our approach, called iProgram, to homes across their customer base. iProgram addresses new challenges in inferring home occupancy from smart meter data where i) training data is not available and ii) the thermostat schedule may be misaligned with occupancy, frequently resulting in high power usage during unoccupied periods. iProgram translates occupancy patterns inferred from opaque smart meter data into a custom schedule for existing types of programmable thermostats, e.g., 1-day, 7-day, etc. We implement iProgram as a web service and show that it reduces the mismatch time between the occupancy pattern and the thermostat schedule by a median value of 44.28 minutes (out of 100 homes) when compared to a default 8am-6pm weekday schedule, with a median deviation of 30.76 minutes off the optimal schedule. Further, iProgram yields a daily energy saving of 0.42kWh on average across the 100 homes. Utilities may use iProgram to recommend thermostat schedules to customers and provide them estimates of potential energy savings in their energy bills.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{238,

title = {Collaborative Multi-Output Gaussian Processes for Collections of Sparse Multivariate Time Series,},

author = {Steven Cheng-Xian Li and Benjamin M Marlin},

url = {https://sites.google.com/site/nipsts2015/accepted-papers},

year  = {2015},

date = {2015-00-01},

booktitle = {NIPS Time Series Workshop},

abstract = {<p>Collaborative Multi-Output Gaussian Processes (COGPs) are a flexible tool for modeling multivariate time series. They induce correlation across outputs through the use of shared latent processes. While past work has focused on the computational challenges that result from a single multivariate time series with many observed values, this paper explores the problem of fitting the COGP model to collections of many sparse and irregularly sampled multivariate time series. This work is motivated by applications to modeling physiological data (heart rate, blood pressure, etc.) in Electronic Health Records (EHRs).</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{239,

title = {Hierarchical Nested CRFs for Segmentation and Labeling of Physiological Time Series},

author = {Roy J Adams and Edison Thomaz and Benjamin M Marlin},

url = {https://sites.google.com/site/nipsmlhc15/home/schedule},

year  = {2015},

date = {2015-00-01},

booktitle = {NIPS Workshop on Machine Learning in Healthcare},

abstract = {<p>In this paper, we address the problem of nested hierarchical segmentation<br /> 

and labeling of time series data. We present a hierarchical<br /> 

span-based conditional random field framework for this problem that<br /> 

leverages higher-order factors to enforce the nesting constraints. The framework can<br /> 

incorporate a variety of additional factors including higher order cardinality<br /> 

factors. This research is motivated by hierarchical activity recognition problems<br /> 

in the field of mobile Health (mHealth). We show that the specific model of interest in the mHealth setting supports exact MAP inference in quadratic time. Learning is accomplished in the structured support vector machine framework. We show positive results on real and synthetic data sets.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{237,

title = {iProgram: Inferring Smart Schedules for Dumb Thermostats},

author = {Srinivasan Iyengar and Sandeep Kalra and Anushree Ghosh and David Irwin and Prashant Shenoy and Benjamin Marlin},

year  = {2015},

date = {2015-00-01},

booktitle = {10th Annual Women in Machine Learning Workshop},

abstract = {<p>Heating, ventilation, and air conditioning (HVAC) accounts for over 50% of a typical hometextquoterights energy usage. A thermostat generally controls HVAC usage in a home to ensure user comfort. In this paper, we focus on making existing "dumb" programmable thermostats smart by applying energy analytics on smart meter data to infer home occupancy patterns and compute an optimized thermostat schedule. Utilities with smart meter deployments are capable of immediately applying our approach, called iProgram, to homes across their customer base. iProgram addresses new challenges in inferring home occupancy from smart meter data where i) training data is not available and ii) the thermostat schedule may be misaligned with occupancy, frequently resulting in high power usage during unoccupied periods. iProgram translates occupancy patterns inferred from opaque smart meter data into a custom schedule for existing types of programmable thermostats, e.g., 1-day, 7-day, etc. We implement iProgram as a web service and show that it reduces the mismatch time between the occupancy pattern and the thermostat schedule by a median value of 44.28 minutes (out of 100 homes) when compared to a default 8am-6pm weekday schedule, with a median deviation of 30.76 minutes off the optimal schedule. Further, iProgram yields a daily energy saving of 0.42kWh on average across the 100 homes. Utilities may use iProgram to recommend thermostat schedules to customers and provide them estimates of potential energy savings in their energy bills.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{229,

title = {Analysis and synthesis of 3D shape families via deep-learned generative models of surfaces},

author = {Haibin Huang and Evangelos Kalogerakis and Benjamin Marlin},

url = {https://people.cs.umass.edu/~kalo/papers/bsm/bsm_optimized.pdf},

year  = {2015},

date = {2015-00-01},

booktitle = {Symposium on Geometry Processing},

abstract = {<p>We present a method for joint analysis and synthesis of geometrically diverse 3D shape families. Our method first learns part-based templates such that an optimal set of fuzzy point and part correspondences is computed between the shapes of an input collection based on a probabilistic deformation model. In contrast to previous template-based approaches, the geometry and deformation parameters of our part-based templates are learned from scratch. Based on the estimated shape correspondence, our method also learns a probabilistic generative model that hierarchically captures statistical relationships of corresponding surface point positions and parts as well as their existence in the input shapes. A deep learning procedure is used to capture these hierarchical relationships. The resulting generative model is used to produce control point arrangements that drive shape synthesis by combining and deforming parts from the input collection. The generative model also yields compact shape descriptors that are used to perform fine-grained classification. Finally, it can be also coupled with the probabilistic deformation model to further improve shape correspondence. We provide qualitative and quantitative evaluations of our method for shape correspondence, segmentation, fine-grained classification and synthesis. Our experiments demonstrate superior correspondence and segmentation results than previous state-of-the-art approaches.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Natarajan-BCB2014,

title = {Conditional Random Fields for Morphological Analysis of Wireless ECG Signals},

author = {Annamalai Natarajan and Edward Gaiser and Gustavo Angarita and Robert Malison and Deepak Ganesan and Benjamin Marlin},

url = {http://dl.acm.org/citation.cfm?id=2649414},

year  = {2014},

date = {2014-09-01},

booktitle = {Proceedings of the 5th Annual conference on Bioinformatics, Computational Biology and Health Informatics},

publisher = {ACM},

address = {Newport Beach, CA},

organization = {ACM},

abstract = {<p>Thanks to advances in mobile sensing technologies, it has recently become practical to deploy wireless electrocardiograph sensors for continuous recording of ECG signals. This capability has diverse applications in the study of human health and behavior, but to realize its full potential, new computational tools are required to effectively deal with the uncertainty that results from the noisy and highly non-stationary signals collected using these devices. In this work, we present a novel approach to the problem of extracting the morphological structure of ECG signals based on the use of dynamically structured conditional random field (CRF) models. We apply this framework to the problem of extracting morphological structure from wireless ECG sensor data collected in a lab-based study of habituated cocaine users. Our results show that the proposed CRF-based approach significantly out-performs independent prediction models using the same features, as well as a widely cited open source toolkit.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Adams-RecSys2014,

title = {PERSPeCT: Collaborative Filtering for Tailored Health Communications},

author = {Roy J Adams and Rajani S Sadasivam and Kavitha Balakrishnan and Rebecca L Kinney and Thomas K Houston and Benjamin M Marlin},

url = {http://doi.acm.org/10.1145/2645710.2645768},

doi = {10.1145/2645710.2645768},

isbn = {978-1-4503-2668-1},

year  = {2014},

date = {2014-01-01},

booktitle = {Proceedings of the 8th ACM Conference on Recommender Systems},

pages = {329–332},

publisher = {ACM},

address = {New York, NY, USA},

organization = {ACM},

series = {RecSys textquoteright14},

abstract = {<p>The goal of computer tailored health communications (CTHC) is to elicit healthy behavior changes by sending motivational messages personalized to individual patients. One prominent weakness of many existing CTHC systems is that they are based on expert-written rules and thus have no ability to learn from their users over time. One solution to this problem is to develop CTHC systems based on the principles of collaborative filtering, but this approach has not been widely studied. In this paper, we present a case study evaluating nine rating prediction methods for use in the Patient Experience Recommender System for Persuasive Communication Tailoring, a system developed for use in a clinical trial of CTHC-based smoking cessation support interventions.</p>},

note = {<p>n/a</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{DBLP:conf/huc/NatarajanPGAMMG13,

title = {Detecting cocaine use with wearable electrocardiogram sensors},

author = {Annamalai Natarajan and Abhinav Parate and Edward Gaiser and Gustavo Angarita and Robert Malison and Benjamin M Marlin and Deepak Ganesan},

url = {http://doi.acm.org/10.1145/2493432.2493496},

year  = {2013},

date = {2013-01-01},

booktitle = {UbiComp},

pages = {123-132},

abstract = {<p>Ubiquitous physiological sensing has the potential to profoundly improve our understanding of human behavior, leading to more targeted treatments for a variety of disorders. The long term goal of this work is development of novel computational tools to support the study of addiction in the context of cocaine use. The current paper takes the first step in this important direction by posing a simple, but crucial question: Can cocaine use be reliably detected using wearable electrocardiogram (ECG) sensors? The main contributions in this paper include the presentation of a novel clinical study of cocaine use, the development of a computational pipeline for inferring morphological features from noisy ECG waveforms, and the evaluation of feature sets for cocaine use detection. Our results show that 32mg/70kg doses of cocaine can be detected with the area under the receiver operating characteristic curve levels above 0.9 both within and between-subjects.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{DBLP:conf/mobisys/ParateCGM13,

title = {Leveraging graphical models to improve accuracy and reduce privacy risks of mobile sensing},

author = {Abhinav Parate and Meng-Chieh Chiu and Deepak Ganesan and Benjamin M Marlin},

url = {http://doi.acm.org/10.1145/2462456.2464457},

year  = {2013},

date = {2013-01-01},

booktitle = {MobiSys},

pages = {83-96},

abstract = {<p>The proliferation of sensors on mobile phones and wearables has led to a plethora of context classifiers designed to sense the individualtextquoterights context. We argue that a key missing piece in mobile inference is a layer that fuses the outputs of several classifiers to learn deeper insights into an individualtextquoterights habitual patterns and associated correlations between contexts, thereby enabling new systems optimizations and opportunities. In this paper, we design CQue, a dynamic bayesian network that operates over classifiers for individual contexts, observes relations across these outputs across time, and identifies opportunities for improving energy-efficiency and accuracy by taking advantage of relations. In addition, such a layer provides insights into privacy leakage that might occur when seemingly innocuous user context revealed to different applications on a phone may be combined to reveal more information than originally intended. In terms of system architecture, our key contribution is a clean separation between the detection layer and the fusion layer, enabling classifiers to solely focus on detecting the context, and leverage temporal smoothing and fusion mechanisms to further boost performance by just connecting to our higher-level inference engine. To applications and users, CQue provides a query interface, allowing a) applications to obtain more accurate context results while remaining agnostic of what classifiers/sensors are used and when, and b) users to specify what contexts they wish to keep private, and only allow information that has low leakage with the private context to be revealed. We implemented CQue in Android, and our results show that CQue can i) improve activity classification accuracy up to 42%, ii) reduce energy consumption in classifying social, location and activity contexts with high accuracy(>90%) by reducing the number of required classifiers by at least 33%, and iii) effectively detect and suppress contexts that reveal private information.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{DBLP:conf/huc/ParateBCGM13,

title = {Practical prediction and prefetch for faster access to applications on mobile phones},

author = {Abhinav Parate and Matthias B ö and David Chu and Deepak Ganesan and Benjamin M Marlin},

url = {http://doi.acm.org/10.1145/2493432.2493490},

year  = {2013},

date = {2013-01-01},

booktitle = {UbiComp},

pages = {275-284},

abstract = {<p>Mobile phones have evolved from communication devices to indispensable accessories with access to real-time content. The increasing reliance on dynamic content comes at the cost of increased latency to pull the content from the Internet before the user can start using it. While prior work has explored parts of this problem, they ignore the bandwidth costs of prefetching, incur significant training overhead, need several sensors to be turned on, and do not consider practical systems issues that arise from the limited background processing capability supported by mobile operating systems. In this paper, we make app prefetch practical on mobile phones. Our contributions are two-fold. First, we design an app prediction algorithm, APPM, that requires no prior training, adapts to usage dynamics, predicts not only which app will be used next but also when it will be used, and provides high accuracy without requiring additional sensor context. Second, we perform parallel prefetch on screen unlock, a mechanism that leverages the benefits of prediction while operating within the constraints of mobile operating systems. Our experiments are conducted on long-term traces, live deployments on the Android Play Market, and user studies, and show that we outperform prior approaches to predicting app usage, while also providing practical ways to prefetch application content on mobile phones.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{DBLP:conf/naacl/RiedelYMM13,

title = {Relation Extraction with Matrix Factorization and Universal Schemas},

author = {Sebastian Riedel and Limin Yao and Andrew McCallum and Benjamin M Marlin},

url = {http://aclweb.org/anthology/N/N13/N13-1008.pdf},

year  = {2013},

date = {2013-01-01},

booktitle = {HLT-NAACL},

pages = {74-84},

abstract = {<p>Traditional relation extraction predicts relations within some fixed and finite target schema. Machine learning approaches to this task require either manual annotation or, in the case of distant supervision, existing struc- tured sources of the same schema. The need for existing datasets can be avoided by using a universal schema: the union of all in- volved schemas (surface form predicates as in OpenIE, and relations in the schemas of pre- existing databases). This schema has an al- most unlimited set of relations (due to surface forms), and supports integration with existing structured data (through the relation types of existing databases). To populate a database of such schema we present matrix factorization models that learn latent feature vectors for en- tity tuples and relations. We show that such latent models achieve substantially higher accuracy than a traditional classification approach. More importantly, by operating simultaneously on relations observed in text and in pre-existing structured DBs such as Freebase, we are able to reason about unstructured and structured data in mutually-supporting ways. By doing so our approach outperforms state-of-the-art distant supervision.</p>},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}