Deconstructing and reconstructing word embedding algorithms
Edward Daniel Newell
Kian Kenyon-Dean
Jackie Cheung
Uncontextualized word embeddings are reliable feature representations of words used to obtain high quality results for various NLP applicati… (see more)ons. Given the historical success of word embeddings in NLP, we propose a retrospective on some of the most well-known word embedding algorithms. In this work, we deconstruct Word2vec, GloVe, and others, into a common form, unveiling some of the necessary and sufficient conditions required for making performant word embeddings. We find that each algorithm: (1) fits vector-covector dot products to approximate pointwise mutual information (PMI); and, (2) modulates the loss gradient to balance weak and strong signals. We demonstrate that these two algorithmic features are sufficient conditions to construct a novel word embedding algorithm, Hilbert-MLE. We find that its embeddings obtain equivalent or better performance against other algorithms across 17 intrinsic and extrinsic datasets.
2019-11-29
ArXiv (preprint)
arxiv.org
arxiv.org
Driver perceptions of advanced driver assistance systems and safety
Sophie Le Page
Jason Millar
Kelly Selina Bronson
Shalaleh Rismani
AJung Moon
Advanced driver assistance systems (ADAS) are often used in the automotive industry to highlight innovative improvements in vehicle safety. … (see more)However, today it is unclear whether certain automation (e.g., adaptive cruise control, lane keeping, parking assist) increases safety of our roads. In this paper, we investigate driver awareness, use, perceived safety, knowledge, training, and attitudes toward ADAS with different automation systems/features. Results of our online survey (n=1018) reveal that there is a significant difference in frequency of use and perceived safety for different ADAS features. Furthermore, we find that at least 70% of drivers activate an ADAS feature"most or all of the time"when driving, yet we find that at least 40% of drivers report feeling that ADAS often compromises their safety when activated. We also find that most respondents learn how to use ADAS in their vehicles by trying it out on the road by themselves, rather than through any formal driver education and training. These results may mirror how certain ADAS features are often activated by default resulting in high usage rates. These results also suggest a lack of driver training and education for safely interacting with, and operating, ADAS, such as turning off systems/features. These findings contribute to a critical discussion about the overall safety implications of current ADAS, especially as they enable higher-level automation features to creep into personal vehicles without a lockstep response in training, regulation, and policy.
2019-11-25
ArXiv (preprint)
arxiv.org
arxiv.org
Drivers' Awareness, Knowledge, and Use of Autonomous Driving Assistance Systems (ADAS) and Vehicle Automation
Kelly Selina Bronson
Sophie Le Page
Katherine M. Robinson
AJung Moon
Shalaleh Rismani
Jason Millar
Advanced driver assistance systems (ADAS) technologies in vehicles (e.g. park assist, lane change assist, emergency braking, etc.), which ta… (see more)ke over parts of the driving task of human drivers, are advancing at a disruptive pace and hold the potential to deliver many benefits to society. However, public understanding of ADAS systems, and driver training and licensing for using them, are lagging behind the fast-paced technological development, which could raise safety issues or slow the deployment of ADAS, thus offsetting their potential benefits. There is, therefore, a need to investigate issues related to public perception of ADAS in order to develop appropriate policies and governance structures which support innovation, and result in the smooth deployment and acceptance of appropriate ADAS for society. In this work we perform a quantitative public survey to better understand how the public's awareness and knowledge of ADAS technologies in their vehicles correlate to their use or engagement of those technologies. We find that up to 67% of participants never or rarely use optional ADAS in their vehicles (e.g. adaptive cruise control), where women were less likely than men to use ADAS even though women reported more awareness of ADAS in their vehicles, better training, and more willingness to pay for ADAS. By performing this analysis we hope to raise awareness around the public perception of current state-of-the-art in ADAS technologies. We also hope to flag concerns that answers to these questions might raise for the regulatory agencies, and manufacturers, responsible for bringing these technologies to market.
2019-11-25
arXiv.org (preprint)
dblp.uni-trier.de
JANOS: An Integrated Predictive and Prescriptive Modeling Framework
David Bergman
Teng Huang
Philip A. Brooks
Andrea Lodi
A. Raghunathan
Business research practice is witnessing a surge in the integration of predictive modeling and prescriptive analysis. We describe a modeling… (see more) framework JANOS that seamlessly integrates the two streams of analytics, allowing researchers and practitioners to embed machine learning models in an end-to-end optimization framework. JANOS allows for specifying a prescriptive model using standard optimization modeling elements such as constraints and variables. The key novelty lies in providing modeling constructs that enable the specification of commonly used predictive models within an optimization model, have the features of the predictive model as variables in the optimization model, and incorporate the output of the predictive models as part of the objective. The framework considers two sets of decision variables: regular and predicted. The relationship between the regular and the predicted variables is specified by the user as pretrained predictive models. JANOS currently supports linear regression, logistic regression, and neural network with rectified linear activation functions. In this paper, we demonstrate the flexibility of the framework through an example on scholarship allocation in a student enrollment problem and provide a numeric performance evaluation. Summary of Contribution. This paper describes a new software tool, JANOS, that integrates predictive modeling and discrete optimization to assist decision making. Specifically, the proposed solver takes as input user-specified pretrained predictive models and formulates optimization models directly over those predictive models by embedding them within an optimization model through linear transformations.
2019-11-21
ArXiv (preprint)
doi.org
arxiv.org
Deep Active Learning: Unified and Principled Method for Query and Training
Changjian Shui
Fan Zhou
Christian Gagné
Boyu Wang
In this paper, we are proposing a unified and principled method for both the querying and training processes in deep batch active learning. … (see more)We are providing theoretical insights from the intuition of modeling the interactive procedure in active learning as distribution matching, by adopting the Wasserstein distance. As a consequence, we derived a new training loss from the theoretical analysis, which is decomposed into optimizing deep neural network parameters and batch query selection through alternative optimization. In addition, the loss for training a deep neural network is naturally formulated as a min-max optimization problem through leveraging the unlabeled data information. Moreover, the proposed principles also indicate an explicit uncertainty-diversity trade-off in the query batch selection. Finally, we evaluate our proposed method on different benchmarks, consistently showing better empirical performances and a better time-efficient query strategy compared to the baselines.
2019-11-20
ArXiv (preprint)
arxiv.org
arxiv.org
Nonlinear chance-constrained problems with applications to hydro scheduling
Andrea Lodi
Enrico Malaguti
Giacomo Nannicini
Dimitri Thomopulos
2019-11-14
Mathematical Programming (published)
doi.org
SST'19 - Software and Systems Traceability
Jan-Philipp Steghöfer
Nan Niu
Jin Guo
Anas Mahmoud
Traceability is the ability to relate di erent artifacts during the development and operation of a system to each other. It enables program … (see more)comprehension, change impact analysis, and facilitates the cooperation of engineers from di erent disciplines. The 10th International Workshop on Software and Systems Traceability (former International Workshop on Traceability in Emerging Forms of Software Engineering, TEFSE), explored the role and impact of traceability in modern software and systems development. The event brought together researchers and practitioners to examine the challenges of recovering, maintaining, and utilizing traceability for the myriad forms of software and systems engineering artifacts. SST'19 was a highly interactive working event focused on discussing the main problems related to software traceability in particular in the context of opportunities and challenges posed by the recent progress in Arti cial Intelligence techniques and proposing possible solutions for such problems.
2019-11-14
ACM SIGSOFT Softw. Eng. Notes (published)
doi.org
What Do Compressed Deep Neural Networks Forget
Sara Hooker
Aaron Courville
Gregory Clark
Yann Dauphin
Andrea Frome
Deep neural network pruning and quantization techniques have demonstrated it is possible to achieve high levels of compression with surprisi… (see more)ngly little degradation to test set accuracy. However, this measure of performance conceals significant differences in how different classes and images are impacted by model compression techniques. We find that models with radically different numbers of weights have comparable top-line performance metrics but diverge considerably in behavior on a narrow subset of the dataset. This small subset of data points, which we term Pruning Identified Exemplars (PIEs) are systematically more impacted by the introduction of sparsity. Compression disproportionately impacts model performance on the underrepresented long-tail of the data distribution. PIEs over-index on atypical or noisy images that are far more challenging for both humans and algorithms to classify. Our work provides intuition into the role of capacity in deep neural networks and the trade-offs incurred by compression. An understanding of this disparate impact is critical given the widespread deployment of compressed models in the wild.
2019-11-13
ArXiv (preprint)
arxiv.org
arxiv.org
Fractal impedance for passive controllers: a framework for interaction robotics
Keyhan Kouhkiloui Babarahmati
Carlo Tiseo
Joshua Smith
Hsiu‐chin Lin
M. S. Erden
Michael Nalin Mistry
2019-11-12
ArXiv (preprint)
doi.org
arxiv.org
Defining ‘actionable’ high- costhealth care use: results using the Canadian Institute for Health Information population grouping methodology
Maureen Anderson
Crawford W. Revie
Henrik Stryhn
Cordell Neudorf
Yvonne Rosehart
Wenbin Li
Meriç Osman
David Buckeridge
Laura C. Rosella
Walter P. Wodchis
2019-11-10
International Journal for Equity in Health (published)
doi.org
Preventing Posterior Collapse in Sequence VAEs with Pooling
Teng Long
Yanshuai Cao
Jackie Cheung
Variational Autoencoders (VAEs) hold great potential for modelling text, as they could in theory separate high-level semantic and syntactic … (see more)properties from local regularities of natural language. Practically, however, VAEs with autoregressive decoders often suffer from posterior collapse, a phenomenon where the model learns to ignore the latent variables, causing the sequence VAE to degenerate into a language model. Previous works attempt to solve this problem with complex architectural changes or costly optimization schemes. In this paper, we argue that posterior collapse is caused in part by the encoder network failing to capture the input variabilities. We verify this hypothesis empirically and propose a straightforward fix using pooling. This simple technique effectively prevents posterior collapse, allowing the model to achieve significantly better data log-likelihood than standard sequence VAEs. Compared to the previous SOTA on preventing posterior collapse, we are able to achieve comparable performances while being significantly faster.
2019-11-10
ArXiv (preprint)
arxiv.org
arxiv.org
Adversarial target-invariant representation learning for domain generalization
Isabela Albuquerque
Joao Monteiro
Tiago Falk
Ioannis Mitliagkas
In many applications of machine learning, the training and test set data come from different distributions, or domains. A number of domain g… (see more)eneralization strategies have been introduced with the goal of achieving good performance on out-of-distribution data. In this paper, we propose an adversarial approach to the problem. We propose a process that enforces pair-wise domain invariance while training a feature extractor over a diverse set of domains. We show that this process ensures invariance to any distribution that can be expressed as a mixture of the training domains. Following this insight, we then introduce an adversarial approach in which pair-wise divergences are estimated and minimized. Experiments on two domain generalization benchmarks for object recognition (i.e., PACS and VLCS) show that the proposed method yields higher average accuracy on the target domains in comparison to previously introduced adversarial strategies, as well as recently proposed methods based on learning invariant representations.
2019-11-03
arXiv.org (preprint)
dblp.uni-trier.de