January 30, 2020

3017 words 15 mins read

Paper Group ANR 370

Lifelog Patterns Analyzation using Graph Embedding based on Deep Neural Network. Probabilistic Forecasting using Deep Generative Models. Detection and Mitigation of Rare Subclasses in Neural Network Classifiers. Sharp Guarantees for Solving Random Equations with One-Bit Information. Go From the General to the Particular: Multi-Domain Translation wi …

Lifelog Patterns Analyzation using Graph Embedding based on Deep Neural Network


Title	Lifelog Patterns Analyzation using Graph Embedding based on Deep Neural Network
Authors	Wonsup Shin, Tae-Young Kim, Sung-Bae Cho
Abstract	Recently, as the spread of smart devices increases, the amount of data collected through sensors is increasing. A lifelog is a kind of big data to analyze behavior patterns in the daily life of individuals collected from various smart de-vices. However, sensor data is a low-level signal that makes it difficult for hu-mans to recognize the situation directly and cannot express relations clearly. It is also difficult to identify the daily behavior pattern because it records heterogene-ous data by various sensors. In this paper, we propose a method to define a graph structure with node and edge and to extract the daily behavior pattern from the generated lifelog graph. We use the graph convolution method to embeds the lifelog graph and maps it to low dimension. The graph convolution layer im-proves the expressive power of the daily behavior pattern by implanting the life-log graph in the non-Euclidean space and learns the patterns of graphs. Experi-mental results show that the proposed method automatically extracts meaningful user patterns from UbiqLog dataset. In addition, we confirm the usefulness by comparing our method with existing methods to evaluate performance.
Tasks	Graph Embedding
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04252v1
PDF	https://arxiv.org/pdf/1909.04252v1.pdf
PWC	https://paperswithcode.com/paper/lifelog-patterns-analyzation-using-graph
Repo
Framework

Probabilistic Forecasting using Deep Generative Models


Title	Probabilistic Forecasting using Deep Generative Models
Authors	Alessandro Fanfarillo, Behrooz Roozitalab, Weiming Hu, Guido Cervone
Abstract	The Analog Ensemble (AnEn) method tries to estimate the probability distribution of the future state of the atmosphere with a set of past observations that correspond to the best analogs of a deterministic Numerical Weather Prediction (NWP). This model post-processing method has been successfully used to improve the forecast accuracy for several weather-related applications including air quality, and short-term wind and solar power forecasting, to name a few. In order to provide a meaningful probabilistic forecast, the AnEn method requires storing a historical set of past predictions and observations in memory for a period of at least several months and spanning the seasons relevant for the prediction of interest. Although the memory and computing costs of the AnEn method are less expensive than using a brute-force dynamical ensemble approach, for a large number of stations and large datasets, the amount of memory required for AnEn can easily become prohibitive. Furthermore, in order to find the best analogs associated with a certain prediction produced by a NWP model, the current approach requires searching over the entire dataset by applying a certain metric. This approach requires applying the metric over the entire historical dataset, which may take a substantial amount of time. In this work, we investigate an alternative way to implement the AnEn method using deep generative models. By doing so, a generative model can entirely or partially replace the dataset of pairs of predictions and observations, reducing the amount of memory required to produce the probabilistic forecast by several orders of magnitude. Furthermore, the generative model can generate a meaningful set of analogs associated with a certain forecast in constant time without performing any search, saving a considerable amount of time even in the presence of huge historical datasets.
Tasks
Published	2019-09-26
URL	https://arxiv.org/abs/1909.11865v1
PDF	https://arxiv.org/pdf/1909.11865v1.pdf
PWC	https://paperswithcode.com/paper/probabilistic-forecasting-using-deep
Repo
Framework

Detection and Mitigation of Rare Subclasses in Neural Network Classifiers


Title	Detection and Mitigation of Rare Subclasses in Neural Network Classifiers
Authors	Colin Paterson, Radu Calinescu
Abstract	Regions of high-dimensional input spaces that are underrepresented in training datasets reduce machine-learnt classifier performance, and may lead to corner cases and unwanted bias for classifiers used in decision making systems. When these regions belong to otherwise well-represented classes, their presence and negative impact are very hard to identify. We propose an approach for the detection and mitigation of such rare subclasses in neural network classifiers. The new approach is underpinned by an easy-to-compute commonality metric that supports the detection of rare subclasses, and comprises methods for reducing their impact during both model training and model exploitation.
Tasks	Decision Making
Published	2019-11-28
URL	https://arxiv.org/abs/1911.12780v1
PDF	https://arxiv.org/pdf/1911.12780v1.pdf
PWC	https://paperswithcode.com/paper/detection-and-mitigation-of-rare-subclasses
Repo
Framework

Sharp Guarantees for Solving Random Equations with One-Bit Information


Title	Sharp Guarantees for Solving Random Equations with One-Bit Information
Authors	Hossein Taheri, Ramtin Pedarsani, Christos Thrampoulidis
Abstract	We study the performance of a wide class of convex optimization-based estimators for recovering a signal from corrupted one-bit measurements in high-dimensions. Our general result predicts sharply the performance of such estimators in the linear asymptotic regime when the measurement vectors have entries IID Gaussian. This includes, as a special case, the previously studied least-squares estimator and various novel results for other popular estimators such as least-absolute deviations, hinge-loss and logistic-loss. Importantly, we exploit the fact that our analysis holds for generic convex loss functions to prove a bound on the best achievable performance across the entire class of estimators. Numerical simulations corroborate our theoretical findings and suggest they are accurate even for relatively small problem dimensions.
Tasks
Published	2019-08-12
URL	https://arxiv.org/abs/1908.04433v2
PDF	https://arxiv.org/pdf/1908.04433v2.pdf
PWC	https://paperswithcode.com/paper/sharp-guarantees-for-solving-random-equations
Repo
Framework

Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks


Title	Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks
Authors	Yong Wang, Longyue Wang, Shuming Shi, Victor O. K. Li, Zhaopeng Tu
Abstract	The key challenge of multi-domain translation lies in simultaneously encoding both the general knowledge shared across domains and the particular knowledge distinctive to each domain in a unified model. Previous work shows that the standard neural machine translation (NMT) model, trained on mixed-domain data, generally captures the general knowledge, but misses the domain-specific knowledge. In response to this problem, we augment NMT model with additional domain transformation networks to transform the general representations to domain-specific representations, which are subsequently fed to the NMT decoder. To guarantee the knowledge transformation, we also propose two complementary supervision signals by leveraging the power of knowledge distillation and adversarial learning. Experimental results on several language pairs, covering both balanced and unbalanced multi-domain translation, demonstrate the effectiveness and universality of the proposed approach. Encouragingly, the proposed unified model achieves comparable results with the fine-tuning approach that requires multiple models to preserve the particular knowledge. Further analyses reveal that the domain transformation networks successfully capture the domain-specific knowledge as expected.
Tasks	Machine Translation
Published	2019-11-22
URL	https://arxiv.org/abs/1911.09912v1
PDF	https://arxiv.org/pdf/1911.09912v1.pdf
PWC	https://paperswithcode.com/paper/go-from-the-general-to-the-particular-multi
Repo
Framework

Extensions to Justification Theory


Title	Extensions to Justification Theory
Authors	Simon Marynissen
Abstract	Justification theory is a unifying framework for semantics of non-monotonic logics. It is built on the notion of a justification, which intuitively is a graph that explains the truth value of certain facts in a structure. Knowledge representation languages covered by justification theory include logic programs, argumentation frameworks, inductive definitions, and nested inductive and coinductive definitions. In addition, justifications are also used for implementation purposes. They are used to compute unfounded sets in modern ASP solvers, can be used to check for relevance of atoms in complete search algorithms, and recent lazy grounding algorithms are built on top of them. In this extended abstract, we lay out possible extensions to justification theory.
Tasks
Published	2019-05-09
URL	https://arxiv.org/abs/1905.06184v1
PDF	https://arxiv.org/pdf/1905.06184v1.pdf
PWC	https://paperswithcode.com/paper/190506184
Repo
Framework

Image recovery from rotational and translational invariants


Title	Image recovery from rotational and translational invariants
Authors	Nicholas F. Marshall, Ti-Yen Lan, Tamir Bendory, Amit Singer
Abstract	We introduce a framework for recovering an image from its rotationally and translationally invariant features based on autocorrelation analysis. This work is an instance of the multi-target detection statistical model, which is mainly used to study the mathematical and computational properties of single-particle reconstruction using cryo-electron microscopy (cryo-EM) at low signal-to-noise ratios. We demonstrate with synthetic numerical experiments that an image can be reconstructed from rotationally and translationally invariant features and show that the reconstruction is robust to noise. These results constitute an important step towards the goal of structure determination of small biomolecules using cryo-EM.
Tasks
Published	2019-10-22
URL	https://arxiv.org/abs/1910.10006v1
PDF	https://arxiv.org/pdf/1910.10006v1.pdf
PWC	https://paperswithcode.com/paper/image-recovery-from-rotational-and
Repo
Framework


Title	Parameter Sharing Decoder Pair for Auto Composing
Authors	Xu Zhao
Abstract	Auto Composing is an active and appealing research area in the past few years, and lots of efforts have been put into inventing more robust models to solve this problem. With the fast evolution of deep learning techniques, some deep neural network-based language models are becoming dominant. Notably, the transformer structure has been proven to be very efficient and promising in modeling texts. However, the transformer-based language models usually contain huge number of parameters and the size of the model is usually too large to put in production for some storage limited applications. In this paper, we propose a parameter sharing decoder pair (PSDP), which reduces the number of parameters dramatically and at the same time maintains the capability of generating understandable and reasonable compositions. Works created by the proposed model are presented to demonstrate the effectiveness of the model.
Tasks
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14270v2
PDF	https://arxiv.org/pdf/1910.14270v2.pdf
PWC	https://paperswithcode.com/paper/parameter-sharing-decoder-pair-for-auto
Repo
Framework

Learning Parametric Constraints in High Dimensions from Demonstrations


Title	Learning Parametric Constraints in High Dimensions from Demonstrations
Authors	Glen Chou, Necmiye Ozay, Dmitry Berenson
Abstract	We present a scalable algorithm for learning parametric constraints in high dimensions from safe expert demonstrations. To reduce the ill-posedness of the constraint recovery problem, our method uses hit-and-run sampling to generate lower cost, and thus unsafe, trajectories. Both safe and unsafe trajectories are used to obtain a representation of the unsafe set that is compatible with the data by solving an integer program in that representation’s parameter space. Our method can either leverage a known parameterization or incrementally grow a parameterization while remaining consistent with the data, and we provide theoretical guarantees on the conservativeness of the recovered unsafe set. We evaluate our method on high-dimensional constraints for high-dimensional systems by learning constraints for 7-DOF arm, quadrotor, and planar pushing examples, and show that our method outperforms baseline approaches.
Tasks
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03477v1
PDF	https://arxiv.org/pdf/1910.03477v1.pdf
PWC	https://paperswithcode.com/paper/learning-parametric-constraints-in-high
Repo
Framework

Trading-off Accuracy and Energy of Deep Inference on Embedded Systems: A Co-Design Approach


Title	Trading-off Accuracy and Energy of Deep Inference on Embedded Systems: A Co-Design Approach
Authors	Nitthilan Kannappan Jayakodi, Anwesha Chatterjee, Wonje Choi, Janardhan Rao Doppa, Partha Pratim Pande
Abstract	Deep neural networks have seen tremendous success for different modalities of data including images, videos, and speech. This success has led to their deployment in mobile and embedded systems for real-time applications. However, making repeated inferences using deep networks on embedded systems poses significant challenges due to constrained resources (e.g., energy and computing power). To address these challenges, we develop a principled co-design approach. Building on prior work, we develop a formalism referred to as Coarse-to-Fine Networks (C2F Nets) that allow us to employ classifiers of varying complexity to make predictions. We propose a principled optimization algorithm to automatically configure C2F Nets for a specified trade-off between accuracy and energy consumption for inference. The key idea is to select a classifier on-the-fly whose complexity is proportional to the hardness of the input example: simple classifiers for easy inputs and complex classifiers for hard inputs. We perform comprehensive experimental evaluation using four different C2F Net architectures on multiple real-world image classification tasks. Our results show that optimized C2F Net can reduce the Energy Delay Product (EDP) by 27 to 60 percent with no loss in accuracy when compared to the baseline solution, where all predictions are made using the most complex classifier in C2F Net.
Tasks	Image Classification
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10584v1
PDF	http://arxiv.org/pdf/1901.10584v1.pdf
PWC	https://paperswithcode.com/paper/trading-off-accuracy-and-energy-of-deep
Repo
Framework

Spectral Clustering of Signed Graphs via Matrix Power Means


Title	Spectral Clustering of Signed Graphs via Matrix Power Means
Authors	Pedro Mercado, Francesco Tudisco, Matthias Hein
Abstract	Signed graphs encode positive (attractive) and negative (repulsive) relations between nodes. We extend spectral clustering to signed graphs via the one-parameter family of Signed Power Mean Laplacians, defined as the matrix power mean of normalized standard and signless Laplacians of positive and negative edges. We provide a thorough analysis of the proposed approach in the setting of a general Stochastic Block Model that includes models such as the Labeled Stochastic Block Model and the Censored Block Model. We show that in expectation the signed power mean Laplacian captures the ground truth clusters under reasonable settings where state-of-the-art approaches fail. Moreover, we prove that the eigenvalues and eigenvector of the signed power mean Laplacian concentrate around their expectation under reasonable conditions in the general Stochastic Block Model. Extensive experiments on random graphs and real world datasets confirm the theoretically predicted behaviour of the signed power mean Laplacian and show that it compares favourably with state-of-the-art methods.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.06230v1
PDF	https://arxiv.org/pdf/1905.06230v1.pdf
PWC	https://paperswithcode.com/paper/spectral-clustering-of-signed-graphs-via
Repo
Framework

Mimicking the In-Camera Color Pipeline for Camera-Aware Object Compositing


Title	Mimicking the In-Camera Color Pipeline for Camera-Aware Object Compositing
Authors	Jun Gao, Xiao Li, Liwei Wang, Sanja Fidler, Stephen Lin
Abstract	We present a method for compositing virtual objects into a photograph such that the object colors appear to have been processed by the photo’s camera imaging pipeline. Compositing in such a camera-aware manner is essential for high realism, and it requires the color transformation in the photo’s pipeline to be inferred, which is challenging due to the inherent one-to-many mapping that exists from a scene to a photo. To address this problem for the case of a single photo taken from an unknown camera, we propose a dual-learning approach in which the reverse color transformation (from the photo to the scene) is jointly estimated. Learning of the reverse transformation is used to facilitate learning of the forward mapping, by enforcing cycle consistency of the two processes. We additionally employ a feature sharing schema to extract evidence from the target photo in the reverse mapping to guide the forward color transformation. Our dual-learning approach achieves object compositing results that surpass those of alternative techniques.
Tasks
Published	2019-03-27
URL	http://arxiv.org/abs/1903.11248v1
PDF	http://arxiv.org/pdf/1903.11248v1.pdf
PWC	https://paperswithcode.com/paper/mimicking-the-in-camera-color-pipeline-for
Repo
Framework

Mimic The Raw Domain: Accelerating Action Recognition in the Compressed Domain


Title	Mimic The Raw Domain: Accelerating Action Recognition in the Compressed Domain
Authors	Barak Battash, Haim Barad, Hanlin Tang, Amit Bleiweiss
Abstract	Video understanding usually requires expensive computation that prohibits its deployment, yet videos contain significant spatiotemporal redundancy that can be exploited. In particular, operating directly on the motion vectors and residuals in the compressed video domain can significantly accelerate the compute, by not using the raw videos which demand colossal storage capacity. Existing methods approach this task as a multiple modalities problem. In this paper we are approaching the task in a completely different way; we are looking at the data from the compressed stream as a one unit clip and propose that the residual frames can replace the original RGB frames from the raw domain. Furthermore, we are using teacher-student method to aid the network in the compressed domain to mimic the teacher network in the raw domain. We show experiments on three leading datasets (HMDB51, UCF1, and Kinetics) that approach state-of-the-art accuracy on raw video data by using compressed data. Our model MFCD-Net outperforms prior methods in the compressed domain and more importantly, our model has 11X fewer parameters and 3X fewer Flops, dramatically improving the efficiency of video recognition inference. This approach enables applying neural networks exclusively in the compressed domain without compromising accuracy while accelerating performance.
Tasks	Video Recognition, Video Understanding
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08206v2
PDF	https://arxiv.org/pdf/1911.08206v2.pdf
PWC	https://paperswithcode.com/paper/mimic-the-raw-domain-accelerating-action
Repo
Framework

Asymptotically Optimal One- and Two-Sample Testing with Kernels


Title	Asymptotically Optimal One- and Two-Sample Testing with Kernels
Authors	Shengyu Zhu, Biao Chen, Zhitang Chen, Pengfei Yang
Abstract	We characterize the asymptotic performance of nonparametric one- and two-sample testing. The exponential decay rate or error exponent of the type-II error probability is used as the asymptotic performance metric, and an optimal test achieves the maximum rate subject to a constant level constraint on the type-I error probability. With Sanov’s theorem, we derive a sufficient condition for one-sample tests to achieve the optimal error exponent in the universal setting, i.e., for any distribution defining the alternative hypothesis. We then show that two classes of Maximum Mean Discrepancy (MMD) based tests attain the optimal type-II error exponent on $\mathbb R^d$, while the quadratic-time Kernel Stein Discrepancy (KSD) based tests achieve this optimality with an asymptotic level constraint. For general two-sample testing, however, Sanov’s theorem is insufficient to obtain a similar sufficient condition. We proceed to establish an extended version of Sanov’s theorem and derive an exact error exponent for the quadratic-time MMD based two-sample tests. The obtained error exponent is further shown to be optimal among all two-sample tests satisfying a given level constraint. Our results not only solve a long-standing open problem in information theory and statistics, but also provide an achievability result for optimal nonparametric one- and two-sample testing. Application to off-line change detection and related issues are also discussed.
Tasks
Published	2019-08-27
URL	https://arxiv.org/abs/1908.10037v1
PDF	https://arxiv.org/pdf/1908.10037v1.pdf
PWC	https://paperswithcode.com/paper/asymptotically-optimal-one-and-two-sample
Repo
Framework

A Framework for Parallelizing OWL Classification in Description Logic Reasoners


Title	A Framework for Parallelizing OWL Classification in Description Logic Reasoners
Authors	Zixi Quan, Volker Haarslev
Abstract	In this paper we report on a black-box approach to parallelize existing description logic (DL) reasoners for the Web Ontology Language (OWL). We focus on OWL ontology classification, which is an important inference service and supported by every major OWL/DL reasoner. We propose a flexible parallel framework which can be applied to existing OWL reasoners in order to speed up their classification process. In order to test its performance, we evaluated our framework by parallelizing major OWL reasoners for concept classification. In comparison to the selected black-box reasoner our results demonstrate that the wall clock time of ontology classification can be improved by one order of magnitude for most real-world ontologies.
Tasks
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07749v1
PDF	https://arxiv.org/pdf/1906.07749v1.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-parallelizing-owl
Repo
Framework