July 29, 2019

2608 words 13 mins read

Paper Group ANR 106

Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices. Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising. Deep Feature Learning for Graphs. New Fairness Metrics for Recommendation that Embrace Differences. Improving Document Clustering by Eliminating Unnatural Language. A Generative Model of a Pro …

Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices


Title	Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices
Authors	Wenjia Meng, Zonghua Gu, Ming Zhang, Zhaohui Wu
Abstract	With the rapid proliferation of Internet of Things and intelligent edge devices, there is an increasing need for implementing machine learning algorithms, including deep learning, on resource-constrained mobile embedded devices with limited memory and computation power. Typical large Convolutional Neural Networks (CNNs) need large amounts of memory and computational power, and cannot be deployed on embedded devices efficiently. We present Two-Bit Networks (TBNs) for model compression of CNNs with edge weights constrained to (-2, -1, 1, 2), which can be encoded with two bits. Our approach can reduce the memory usage and improve computational efficiency significantly while achieving good performance in terms of classification accuracy, thus representing a reasonable tradeoff between model size and performance.
Tasks	Model Compression
Published	2017-01-02
URL	http://arxiv.org/abs/1701.00485v2
PDF	http://arxiv.org/pdf/1701.00485v2.pdf
PWC	https://paperswithcode.com/paper/two-bit-networks-for-deep-learning-on
Repo
Framework

Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising


Title	Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising
Authors	Jun Xu, Lei Zhang, David Zhang, Xiangchu Feng
Abstract	Most of the existing denoising algorithms are developed for grayscale images, while it is not a trivial work to extend them for color image denoising because the noise statistics in R, G, B channels can be very different for real noisy images. In this paper, we propose a multi-channel (MC) optimization model for real color image denoising under the weighted nuclear norm minimization (WNNM) framework. We concatenate the RGB patches to make use of the channel redundancy, and introduce a weight matrix to balance the data fidelity of the three channels in consideration of their different noise statistics. The proposed MC-WNNM model does not have an analytical solution. We reformulate it into a linear equality-constrained problem and solve it with the alternating direction method of multipliers. Each alternative updating step has closed-form solution and the convergence can be guaranteed. Extensive experiments on both synthetic and real noisy image datasets demonstrate the superiority of the proposed MC-WNNM over state-of-the-art denoising methods.
Tasks	Denoising, Image Denoising
Published	2017-05-28
URL	http://arxiv.org/abs/1705.09912v2
PDF	http://arxiv.org/pdf/1705.09912v2.pdf
PWC	https://paperswithcode.com/paper/multi-channel-weighted-nuclear-norm
Repo
Framework

Deep Feature Learning for Graphs


Title	Deep Feature Learning for Graphs
Authors	Ryan A. Rossi, Rong Zhou, Nesreen K. Ahmed
Abstract	This paper presents a general graph representation learning framework called DeepGL for learning deep node and edge representations from large (attributed) graphs. In particular, DeepGL begins by deriving a set of base features (e.g., graphlet features) and automatically learns a multi-layered hierarchical graph representation where each successive layer leverages the output from the previous layer to learn features of a higher-order. Contrary to previous work, DeepGL learns relational functions (each representing a feature) that generalize across-networks and therefore useful for graph-based transfer learning tasks. Moreover, DeepGL naturally supports attributed graphs, learns interpretable features, and is space-efficient (by learning sparse feature vectors). In addition, DeepGL is expressive, flexible with many interchangeable components, efficient with a time complexity of $\mathcal{O}(E)$, and scalable for large networks via an efficient parallel implementation. Compared with the state-of-the-art method, DeepGL is (1) effective for across-network transfer learning tasks and attributed graph representation learning, (2) space-efficient requiring up to 6x less memory, (3) fast with up to 182x speedup in runtime performance, and (4) accurate with an average improvement of 20% or more on many learning tasks.
Tasks	Graph Representation Learning, Representation Learning, Transfer Learning
Published	2017-04-28
URL	http://arxiv.org/abs/1704.08829v2
PDF	http://arxiv.org/pdf/1704.08829v2.pdf
PWC	https://paperswithcode.com/paper/deep-feature-learning-for-graphs
Repo
Framework

New Fairness Metrics for Recommendation that Embrace Differences


Title	New Fairness Metrics for Recommendation that Embrace Differences
Authors	Sirui Yao, Bert Huang
Abstract	We study fairness in collaborative-filtering recommender systems, which are sensitive to discrimination that exists in historical data. Biased data can lead collaborative filtering methods to make unfair predictions against minority groups of users. We identify the insufficiency of existing fairness metrics and propose four new metrics that address different forms of unfairness. These fairness metrics can be optimized by adding fairness terms to the learning objective. Experiments on synthetic and real data show that our new metrics can better measure fairness than the baseline, and that the fairness objectives effectively help reduce unfairness.
Tasks	Recommendation Systems
Published	2017-06-29
URL	http://arxiv.org/abs/1706.09838v2
PDF	http://arxiv.org/pdf/1706.09838v2.pdf
PWC	https://paperswithcode.com/paper/new-fairness-metrics-for-recommendation-that
Repo
Framework

Improving Document Clustering by Eliminating Unnatural Language


Title	Improving Document Clustering by Eliminating Unnatural Language
Authors	Myungha Jang, Jinho D. Choi, James Allan
Abstract	Technical documents contain a fair amount of unnatural language, such as tables, formulas, pseudo-codes, etc. Unnatural language can be an important factor of confusing existing NLP tools. This paper presents an effective method of distinguishing unnatural language from natural language, and evaluates the impact of unnatural language detection on NLP tasks such as document clustering. We view this problem as an information extraction task and build a multiclass classification model identifying unnatural language components into four categories. First, we create a new annotated corpus by collecting slides and papers in various formats, PPT, PDF, and HTML, where unnatural language components are annotated into four categories. We then explore features available from plain text to build a statistical model that can handle any format as long as it is converted into plain text. Our experiments show that removing unnatural language components gives an absolute improvement in document clustering up to 15%. Our corpus and tool are publicly available.
Tasks
Published	2017-03-16
URL	http://arxiv.org/abs/1703.05706v2
PDF	http://arxiv.org/pdf/1703.05706v2.pdf
PWC	https://paperswithcode.com/paper/improving-document-clustering-by-eliminating
Repo
Framework

A Generative Model of a Pronunciation Lexicon for Hindi


Title	A Generative Model of a Pronunciation Lexicon for Hindi
Authors	Pramod Pandey, Somnath Roy
Abstract	Voice browser applications in Text-to- Speech (TTS) and Automatic Speech Recognition (ASR) systems crucially depend on a pronunciation lexicon. The present paper describes the model of pronunciation lexicon of Hindi developed to automatically generate the output forms of Hindi at two levels, the and the (PS, in short for Prosodic Structure). The latter level involves both syllable-division and stress placement. The paper describes the tool developed for generating the two-level outputs of lexica in Hindi.
Tasks	Speech Recognition
Published	2017-05-06
URL	http://arxiv.org/abs/1705.02452v1
PDF	http://arxiv.org/pdf/1705.02452v1.pdf
PWC	https://paperswithcode.com/paper/a-generative-model-of-a-pronunciation-lexicon
Repo
Framework

Bayesian Multi Plate High Throughput Screening of Compounds


Title	Bayesian Multi Plate High Throughput Screening of Compounds
Authors	Ivo D. Shterev, David B. Dunson, Cliburn Chan, Gregory D. Sempowski
Abstract	High throughput screening of compounds (chemicals) is an essential part of drug discovery [7], involving thousands to millions of compounds, with the purpose of identifying candidate hits. Most statistical tools, including the industry standard B-score method, work on individual compound plates and do not exploit cross-plate correlation or statistical strength among plates. We present a new statistical framework for high throughput screening of compounds based on Bayesian nonparametric modeling. The proposed approach is able to identify candidate hits from multiple plates simultaneously, sharing statistical strength among plates and providing more robust estimates of compound activity. It can flexibly accommodate arbitrary distributions of compound activities and is applicable to any plate geometry. The algorithm provides a principled statistical approach for hit identification and false discovery rate control. Experiments demonstrate significant improvements in hit identification sensitivity and specificity over the B-score method, which is highly sensitive to threshold choice. The framework is implemented as an efficient R extension package BHTSpack and is suitable for large scale data sets.
Tasks	Drug Discovery
Published	2017-09-28
URL	http://arxiv.org/abs/1709.10041v1
PDF	http://arxiv.org/pdf/1709.10041v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-multi-plate-high-throughput
Repo
Framework

Cost and Actual Causation


Title	Cost and Actual Causation
Authors	Liang Zhou
Abstract	I propose the purpose our concept of actual causation serves is minimizing various cost in intervention practice. Actual causation has three features: nonredundant sufficiency, continuity and abnormality; these features correspond to the minimization of exploitative cost, exploratory cost and risk cost in intervention practice. Incorporating these three features, a definition of actual causation is given. I test the definition in 66 causal cases from actual causation literature and show that this definition’s application fit intuition better than some other causal modelling based definitions.
Tasks
Published	2017-07-31
URL	http://arxiv.org/abs/1707.09704v1
PDF	http://arxiv.org/pdf/1707.09704v1.pdf
PWC	https://paperswithcode.com/paper/cost-and-actual-causation
Repo
Framework

Wide and deep volumetric residual networks for volumetric image classification


Title	Wide and deep volumetric residual networks for volumetric image classification
Authors	Varun Arvind, Anthony Costa, Marcus Badgeley, Samuel Cho, Eric Oermann
Abstract	3D shape models that directly classify objects from 3D information have become more widely implementable. Current state of the art models rely on deep convolutional and inception models that are resource intensive. Residual neural networks have been demonstrated to be easier to optimize and do not suffer from vanishing/exploding gradients observed in deep networks. Here we implement a residual neural network for 3D object classification of the 3D Princeton ModelNet dataset. Further, we show that widening network layers dramatically improves accuracy in shallow residual nets, and residual neural networks perform comparable to state-of-the-art 3D shape net models, and we show that widening network layers improves classification accuracy. We provide extensive training and architecture parameters providing a better understanding of available network architectures for use in 3D object classification.
Tasks	3D Object Classification, Image Classification, Object Classification
Published	2017-09-18
URL	http://arxiv.org/abs/1710.01217v1
PDF	http://arxiv.org/pdf/1710.01217v1.pdf
PWC	https://paperswithcode.com/paper/wide-and-deep-volumetric-residual-networks
Repo
Framework

Fair Pipelines


Title	Fair Pipelines
Authors	Amanda Bower, Sarah N. Kitchen, Laura Niss, Martin J. Strauss, Alexander Vargas, Suresh Venkatasubramanian
Abstract	This work facilitates ensuring fairness of machine learning in the real world by decoupling fairness considerations in compound decisions. In particular, this work studies how fairness propagates through a compound decision-making processes, which we call a pipeline. Prior work in algorithmic fairness only focuses on fairness with respect to one decision. However, many decision-making processes require more than one decision. For instance, hiring is at least a two stage model: deciding who to interview from the applicant pool and then deciding who to hire from the interview pool. Perhaps surprisingly, we show that the composition of fair components may not guarantee a fair pipeline under a $(1+\varepsilon)$-equal opportunity definition of fair. However, we identify circumstances that do provide that guarantee. We also propose numerous directions for future work on more general compound machine learning decisions.
Tasks	Decision Making
Published	2017-07-03
URL	http://arxiv.org/abs/1707.00391v1
PDF	http://arxiv.org/pdf/1707.00391v1.pdf
PWC	https://paperswithcode.com/paper/fair-pipelines
Repo
Framework

Compositional Human Pose Regression


Title	Compositional Human Pose Regression
Authors	Xiao Sun, Jiaxiang Shang, Shuang Liang, Yichen Wei
Abstract	Regression based methods are not performing as well as detection based methods for human pose estimation. A central problem is that the structural information in the pose is not well exploited in the previous regression methods. In this work, we propose a structure-aware regression approach. It adopts a reparameterized pose representation using bones instead of joints. It exploits the joint connection structure to define a compositional loss function that encodes the long range interactions in the pose. It is simple, effective, and general for both 2D and 3D pose estimation in a unified setting. Comprehensive evaluation validates the effectiveness of our approach. It significantly advances the state-of-the-art on Human3.6M and is competitive with state-of-the-art results on MPII.
Tasks	3D Pose Estimation, Pose Estimation
Published	2017-04-01
URL	http://arxiv.org/abs/1704.00159v3
PDF	http://arxiv.org/pdf/1704.00159v3.pdf
PWC	https://paperswithcode.com/paper/compositional-human-pose-regression
Repo
Framework

Decomposable Submodular Function Minimization: Discrete and Continuous


Title	Decomposable Submodular Function Minimization: Discrete and Continuous
Authors	Alina Ene, Huy L. Nguyen, László A. Végh
Abstract	This paper investigates connections between discrete and continuous approaches for decomposable submodular function minimization. We provide improved running time estimates for the state-of-the-art continuous algorithms for the problem using combinatorial arguments. We also provide a systematic experimental comparison of the two types of methods, based on a clear distinction between level-0 and level-1 algorithms.
Tasks
Published	2017-03-06
URL	http://arxiv.org/abs/1703.01830v1
PDF	http://arxiv.org/pdf/1703.01830v1.pdf
PWC	https://paperswithcode.com/paper/decomposable-submodular-function-minimization
Repo
Framework

Physical problem solving: Joint planning with symbolic, geometric, and dynamic constraints


Title	Physical problem solving: Joint planning with symbolic, geometric, and dynamic constraints
Authors	Ilker Yildirim, Tobias Gerstenberg, Basil Saeed, Marc Toussaint, Josh Tenenbaum
Abstract	In this paper, we present a new task that investigates how people interact with and make judgments about towers of blocks. In Experiment~1, participants in the lab solved a series of problems in which they had to re-configure three blocks from an initial to a final configuration. We recorded whether they used one hand or two hands to do so. In Experiment~2, we asked participants online to judge whether they think the person in the lab used one or two hands. The results revealed a close correspondence between participants’ actions in the lab, and the mental simulations of participants online. To explain participants’ actions and mental simulations, we develop a model that plans over a symbolic representation of the situation, executes the plan using a geometric solver, and checks the plan’s feasibility by taking into account the physical constraints of the scene. Our model explains participants’ actions and judgments to a high degree of quantitative accuracy.
Tasks
Published	2017-07-25
URL	http://arxiv.org/abs/1707.08212v1
PDF	http://arxiv.org/pdf/1707.08212v1.pdf
PWC	https://paperswithcode.com/paper/physical-problem-solving-joint-planning-with
Repo
Framework

Image Annotation using Multi-Layer Sparse Coding


Title	Image Annotation using Multi-Layer Sparse Coding
Authors	Amara Tariq, Hassan Foroosh
Abstract	Automatic annotation of images with descriptive words is a challenging problem with vast applications in the areas of image search and retrieval. This problem can be viewed as a label-assignment problem by a classifier dealing with a very large set of labels, i.e., the vocabulary set. We propose a novel annotation method that employs two layers of sparse coding and performs coarse-to-fine labeling. Themes extracted from the training data are treated as coarse labels. Each theme is a set of training images that share a common subject in their visual and textual contents. Our system extracts coarse labels for training and test images without requiring any prior knowledge. Vocabulary words are the fine labels to be associated with images. Most of the annotation methods achieve low recall due to the large number of available fine labels, i.e., vocabulary words. These systems also tend to achieve high precision for highly frequent words only while relatively rare words are more important for search and retrieval purposes. Our system not only outperforms various previously proposed annotation systems, but also achieves symmetric response in terms of precision and recall. Our system scores and maintains high precision for words with a wide range of frequencies. Such behavior is achieved by intelligently reducing the number of available fine labels or words for each image based on coarse labels assigned to it.
Tasks	Image Retrieval
Published	2017-05-06
URL	http://arxiv.org/abs/1705.02460v1
PDF	http://arxiv.org/pdf/1705.02460v1.pdf
PWC	https://paperswithcode.com/paper/image-annotation-using-multi-layer-sparse
Repo
Framework

An Efficient, Expressive and Local Minima-free Method for Learning Controlled Dynamical Systems


Title	An Efficient, Expressive and Local Minima-free Method for Learning Controlled Dynamical Systems
Authors	Ahmed Hefny, Carlton Downey, Geoffrey J. Gordon
Abstract	We propose a framework for modeling and estimating the state of controlled dynamical systems, where an agent can affect the system through actions and receives partial observations. Based on this framework, we propose the Predictive State Representation with Random Fourier Features (RFFPSR). A key property in RFF-PSRs is that the state estimate is represented by a conditional distribution of future observations given future actions. RFF-PSRs combine this representation with moment-matching, kernel embedding and local optimization to achieve a method that enjoys several favorable qualities: It can represent controlled environments which can be affected by actions; it has an efficient and theoretically justified learning algorithm; it uses a non-parametric representation that has expressive power to represent continuous non-linear dynamics. We provide a detailed formulation, a theoretical analysis and an experimental evaluation that demonstrates the effectiveness of our method.
Tasks
Published	2017-02-12
URL	http://arxiv.org/abs/1702.03537v2
PDF	http://arxiv.org/pdf/1702.03537v2.pdf
PWC	https://paperswithcode.com/paper/an-efficient-expressive-and-local-minima-free
Repo
Framework