Paper Group ANR 660
Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compression. 3D shape retrieval basing on representatives of classes. Approximation Strategies for Incomplete MaxSAT. Future Automation Engineering using Structural Graph Convolutional Neural Networks. New And Surprising Ways to Be Mean. Adversarial NPCs with Coup …
Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compression
| Title | Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compression |
| Authors | Jiahao Su, Jingling Li, Bobby Bhattacharjee, Furong Huang |
| Abstract | We propose tensorial neural networks (TNNs), a generalization of existing neural networks by extending tensor operations on low order operands to those on high order ones. The problem of parameter learning is challenging, as it corresponds to hierarchical nonlinear tensor decomposition. We propose to solve the learning problem using stochastic gradient descent by deriving nontrivial backpropagation rules in generalized tensor algebra we introduce. Our proposed TNNs has three advantages over existing neural networks: (1) TNNs naturally apply to high order input object and thus preserve the multi-dimensional structure in the input, as there is no need to flatten the data. (2) TNNs interpret designs of existing neural network architectures. (3) Mapping a neural network to TNNs with the same expressive power results in a TNN of fewer parameters. TNN based compression of neural network improves existing low-rank approximation based compression methods as TNNs exploit two other types of invariant structures, periodicity and modulation, in addition to the low rankness. Experiments on LeNet-5 (MNIST), ResNet-32 (CIFAR10) and ResNet-50 (ImageNet) demonstrate that our TNN based compression outperforms (5% test accuracy improvement universally on CIFAR10) the state-of-the-art low-rank approximation based compression methods under the same compression rate, besides achieving orders of magnitude faster convergence rates due to the efficiency of TNNs. |
| Tasks | Model Compression |
| Published | 2018-05-25 |
| URL | http://arxiv.org/abs/1805.10352v3 |
| http://arxiv.org/pdf/1805.10352v3.pdf | |
| PWC | https://paperswithcode.com/paper/tensorial-neural-networks-generalization-of |
| Repo | |
| Framework | |
3D shape retrieval basing on representatives of classes
| Title | 3D shape retrieval basing on representatives of classes |
| Authors | M. Benjelloun, E. W. Dadi, E. M. Daoudi |
| Abstract | In this paper, we present an improvement of our proposed technique for 3D shape retrieval in classified databases [2] which is based on representatives of classes. Instead of systematically matching the object-query with all 3D models of the database, our idea presented in [2] consist, for a classified database, to represent each class by one representative that is used to orient the retrieval process to the right class (the class excepted to contain 3D models similar to the query). In order to increase the chance to fall in the right class, our idea in this work is to represent each class by more than one representative. In this case, instead of using only one representative to decide which is the right class we use a set of representatives this will contribute certainly to improving the relevance of retrieval results. The obtained experimental results show that the relevance is significantly improved. |
| Tasks | 3D Shape Retrieval |
| Published | 2018-10-21 |
| URL | http://arxiv.org/abs/1810.09008v3 |
| http://arxiv.org/pdf/1810.09008v3.pdf | |
| PWC | https://paperswithcode.com/paper/3d-shape-retrieval-basing-on-representatives |
| Repo | |
| Framework | |
Approximation Strategies for Incomplete MaxSAT
| Title | Approximation Strategies for Incomplete MaxSAT |
| Authors | Saurabh Joshi, Prateek Kumar, Ruben Martins, Sukrut Rao |
| Abstract | Incomplete MaxSAT solving aims to quickly find a solution that attempts to minimize the sum of the weights of the unsatisfied soft clauses without providing any optimality guarantees. In this paper, we propose two approximation strategies for improving incomplete MaxSAT solving. In one of the strategies, we cluster the weights and approximate them with a representative weight. In another strategy, we break up the problem of minimizing the sum of weights of unsatisfiable clauses into multiple minimization subproblems. Experimental results show that approximation strategies can be used to find better solutions than the best incomplete solvers in the MaxSAT Evaluation 2017. |
| Tasks | |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07164v1 |
| http://arxiv.org/pdf/1806.07164v1.pdf | |
| PWC | https://paperswithcode.com/paper/approximation-strategies-for-incomplete |
| Repo | |
| Framework | |
Future Automation Engineering using Structural Graph Convolutional Neural Networks
| Title | Future Automation Engineering using Structural Graph Convolutional Neural Networks |
| Authors | Jiang Wan, Blake S. Pollard, Sujit Rokka Chhetri, Palash Goyal, Mohammad Abdullah Al Faruque, Arquimedes Canedo |
| Abstract | The digitalization of automation engineering generates large quantities of engineering data that is interlinked in knowledge graphs. Classifying and clustering subgraphs according to their functionality is useful to discover functionally equivalent engineering artifacts that exhibit different graph structures. This paper presents a new graph learning algorithm designed to classify engineering data artifacts – represented in the form of graphs – according to their structure and neighborhood features. Our Structural Graph Convolutional Neural Network (SGCNN) is capable of learning graphs and subgraphs with a novel graph invariant convolution kernel and downsampling/pooling algorithm. On a realistic engineering-related dataset, we show that SGCNN is capable of achieving ~91% classification accuracy. |
| Tasks | Knowledge Graphs |
| Published | 2018-08-24 |
| URL | http://arxiv.org/abs/1808.08213v1 |
| http://arxiv.org/pdf/1808.08213v1.pdf | |
| PWC | https://paperswithcode.com/paper/future-automation-engineering-using |
| Repo | |
| Framework | |
New And Surprising Ways to Be Mean. Adversarial NPCs with Coupled Empowerment Minimisation
| Title | New And Surprising Ways to Be Mean. Adversarial NPCs with Coupled Empowerment Minimisation |
| Authors | Christian Guckelsberger, Christoph Salge, Julian Togelius |
| Abstract | Creating Non-Player Characters (NPCs) that can react robustly to unforeseen player behaviour or novel game content is difficult and time-consuming. This hinders the design of believable characters, and the inclusion of NPCs in games that rely heavily on procedural content generation. We have previously addressed this challenge by means of empowerment, a model of intrinsic motivation, and demonstrated how a coupled empowerment maximisation (CEM) policy can yield generic, companion-like behaviour. In this paper, we extend the CEM framework with a minimisation policy to give rise to adversarial behaviour. We conduct a qualitative, exploratory study in a dungeon-crawler game, demonstrating that CEM can exploit the affordances of different content facets in adaptive adversarial behaviour without modifications to the policy. Changes to the level design, underlying mechanics and our character’s actions do not threaten our NPC’s robustness, but yield new and surprising ways to be mean. |
| Tasks | |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.01387v1 |
| http://arxiv.org/pdf/1806.01387v1.pdf | |
| PWC | https://paperswithcode.com/paper/new-and-surprising-ways-to-be-mean |
| Repo | |
| Framework | |
Local moment matching: A unified methodology for symmetric functional estimation and distribution estimation under Wasserstein distance
| Title | Local moment matching: A unified methodology for symmetric functional estimation and distribution estimation under Wasserstein distance |
| Authors | Yanjun Han, Jiantao Jiao, Tsachy Weissman |
| Abstract | We present \emph{Local Moment Matching (LMM)}, a unified methodology for symmetric functional estimation and distribution estimation under Wasserstein distance. We construct an efficiently computable estimator that achieves the minimax rates in estimating the distribution up to permutation, and show that the plug-in approach of our unlabeled distribution estimator is “universal” in estimating symmetric functionals of discrete distributions. Instead of doing best polynomial approximation explicitly as in existing literature of functional estimation, the plug-in approach conducts polynomial approximation implicitly and attains the optimal sample complexity for the entropy, power sum and support size functionals. |
| Tasks | |
| Published | 2018-02-23 |
| URL | http://arxiv.org/abs/1802.08405v2 |
| http://arxiv.org/pdf/1802.08405v2.pdf | |
| PWC | https://paperswithcode.com/paper/local-moment-matching-a-unified-methodology |
| Repo | |
| Framework | |
The Sea Exploration Problem: Data-driven Orienteering on a Continuous Surface
| Title | The Sea Exploration Problem: Data-driven Orienteering on a Continuous Surface |
| Authors | João Pedro Pedroso, Alpar Vajk Kramer, Ke Zhang |
| Abstract | This paper describes a problem arising in sea exploration, where the aim is to schedule the expedition of a ship for collecting information about the resources on the seafloor. The aim is to collect data by probing on a set of carefully chosen locations, so that the information available is optimally enriched. This problem has similarities with the orienteering problem, where the aim is to plan a time-limited trip for visiting a set of vertices, collecting a prize at each of them, in such a way that the total value collected is maximum. In our problem, the score at each vertex is associated with an estimation of the level of the resource on the given surface, which is done by regression using Gaussian processes. Hence, there is a correlation among scores on the selected vertices; this is a first difference with respect to the standard orienteering problem. The second difference is the location of each vertex, which in our problem is a freely chosen point on a given surface. |
| Tasks | Gaussian Processes |
| Published | 2018-02-05 |
| URL | http://arxiv.org/abs/1802.01482v2 |
| http://arxiv.org/pdf/1802.01482v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-sea-exploration-problem-data-driven |
| Repo | |
| Framework | |
Deep residual networks for automatic sleep stage classification of raw polysomnographic waveforms
| Title | Deep residual networks for automatic sleep stage classification of raw polysomnographic waveforms |
| Authors | Alexander Neergaard Olesen, Poul Jennum, Paul Peppard, Emmanuel Mignot, Helge Bjarup Dissing Sorensen |
| Abstract | We have developed an automatic sleep stage classification algorithm based on deep residual neural networks and raw polysomnogram signals. Briefly, the raw data is passed through 50 convolutional layers before subsequent classification into one of five sleep stages. Three model configurations were trained on 1850 polysomnogram recordings and subsequently tested on 230 independent recordings. Our best performing model yielded an accuracy of 84.1% and a Cohen’s kappa of 0.746, improving on previous reported results by other groups also using only raw polysomnogram data. Most errors were made on non-REM stage 1 and 3 decisions, errors likely resulting from the definition of these stages. Further testing on independent cohorts is needed to verify performance for clinical use. |
| Tasks | Automatic Sleep Stage Classification |
| Published | 2018-10-08 |
| URL | http://arxiv.org/abs/1810.03745v1 |
| http://arxiv.org/pdf/1810.03745v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-residual-networks-for-automatic-sleep |
| Repo | |
| Framework | |
Trip Prediction by Leveraging Trip Histories from Neighboring Users
| Title | Trip Prediction by Leveraging Trip Histories from Neighboring Users |
| Authors | Yuxin Chen, Morteza Haghir Chehreghani |
| Abstract | We propose a novel approach for trip prediction by analyzing user’s trip histories. We augment users’ (self-) trip histories by adding ‘similar’ trips from other users, which could be informative and useful for predicting future trips for a given user. This also helps to cope with noisy or sparse trip histories, where the self-history by itself does not provide a reliable prediction of future trips. We show empirical evidence that by enriching the users’ trip histories with additional trips, one can improve the prediction error by 15%-40%, evaluated on multiple subsets of the Nancy2012 dataset. This real-world dataset is collected from public transportation ticket validations in the city of Nancy, France. Our prediction tool is a central component of a trip simulator system designed to analyze the functionality of public transportation in the city of Nancy. |
| Tasks | |
| Published | 2018-12-25 |
| URL | http://arxiv.org/abs/1812.10097v1 |
| http://arxiv.org/pdf/1812.10097v1.pdf | |
| PWC | https://paperswithcode.com/paper/trip-prediction-by-leveraging-trip-histories |
| Repo | |
| Framework | |
Training Deep Neural Network in Limited Precision
| Title | Training Deep Neural Network in Limited Precision |
| Authors | Hyunsun Park, Jun Haeng Lee, Youngmin Oh, Sangwon Ha, Seungwon Lee |
| Abstract | Energy and resource efficient training of DNNs will greatly extend the applications of deep learning. However, there are three major obstacles which mandate accurate calculation in high precision. In this paper, we tackle two of them related to the loss of gradients during parameter update and backpropagation through a softmax nonlinearity layer in low precision training. We implemented SGD with Kahan summation by employing an additional parameter to virtually extend the bit-width of the parameters for a reliable parameter update. We also proposed a simple guideline to help select the appropriate bit-width for the last FC layer followed by a softmax nonlinearity layer. It determines the lower bound of the required bit-width based on the class size of the dataset. Extensive experiments on various network architectures and benchmarks verifies the effectiveness of the proposed technique for low precision training. |
| Tasks | |
| Published | 2018-10-12 |
| URL | http://arxiv.org/abs/1810.05486v1 |
| http://arxiv.org/pdf/1810.05486v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-deep-neural-network-in-limited |
| Repo | |
| Framework | |
Deformation Aware Image Compression
| Title | Deformation Aware Image Compression |
| Authors | Tamar Rott Shaham, Tomer Michaeli |
| Abstract | Lossy compression algorithms aim to compactly encode images in a way which enables to restore them with minimal error. We show that a key limitation of existing algorithms is that they rely on error measures that are extremely sensitive to geometric deformations (e.g. SSD, SSIM). These force the encoder to invest many bits in describing the exact geometry of every fine detail in the image, which is obviously wasteful, because the human visual system is indifferent to small local translations. Motivated by this observation, we propose a deformation-insensitive error measure that can be easily incorporated into any existing compression scheme. As we show, optimal compression under our criterion involves slightly deforming the input image such that it becomes more “compressible”. Surprisingly, while these small deformations are barely noticeable, they enable the CODEC to preserve details that are otherwise completely lost. Our technique uses the CODEC as a “black box”, thus allowing simple integration with arbitrary compression methods. Extensive experiments, including user studies, confirm that our approach significantly improves the visual quality of many CODECs. These include JPEG, JPEG2000, WebP, BPG, and a recent deep-net method. |
| Tasks | Image Compression |
| Published | 2018-04-12 |
| URL | http://arxiv.org/abs/1804.04593v1 |
| http://arxiv.org/pdf/1804.04593v1.pdf | |
| PWC | https://paperswithcode.com/paper/deformation-aware-image-compression |
| Repo | |
| Framework | |
Discriminator Feature-based Inference by Recycling the Discriminator of GANs
| Title | Discriminator Feature-based Inference by Recycling the Discriminator of GANs |
| Authors | Duhyeon Bang, Seoungyoon Kang, Hyunjung Shim |
| Abstract | Generative adversarial networks (GANs)successfully generate high quality data by learning amapping from a latent vector to the data. Various studies assert that the latent space of a GAN is semanticallymeaningful and can be utilized for advanced data analysis and manipulation. To analyze the real data in thelatent space of a GAN, it is necessary to build an inference mapping from the data to the latent vector. Thispaper proposes an effective algorithm to accurately infer the latent vector by utilizing GAN discriminator features. Our primary goal is to increase inference mappingaccuracy with minimal training overhead. Furthermore,using the proposed algorithm, we suggest a conditionalimage generation algorithm, namely a spatially conditioned GAN. Extensive evaluations confirmed that theproposed inference algorithm achieved more semantically accurate inference mapping than existing methodsand can be successfully applied to advanced conditionalimage generation tasks. |
| Tasks | |
| Published | 2018-05-28 |
| URL | https://arxiv.org/abs/1805.10717v2 |
| https://arxiv.org/pdf/1805.10717v2.pdf | |
| PWC | https://paperswithcode.com/paper/high-quality-bidirectional-generative |
| Repo | |
| Framework | |
Deep Generative Model with Beta Bernoulli Process for Modeling and Learning Confounding Factors
| Title | Deep Generative Model with Beta Bernoulli Process for Modeling and Learning Confounding Factors |
| Authors | Prashnna K Gyawali, Cameron Knight, Sandesh Ghimire, B. Milan Horacek, John L. Sapp, Linwei Wang |
| Abstract | While deep representation learning has become increasingly capable of separating task-relevant representations from other confounding factors in the data, two significant challenges remain. First, there is often an unknown and potentially infinite number of confounding factors coinciding in the data. Second, not all of these factors are readily observable. In this paper, we present a deep conditional generative model that learns to disentangle a task-relevant representation from an unknown number of confounding factors that may grow infinitely. This is achieved by marrying the representational power of deep generative models with Bayesian non-parametric factor models, where a supervised deterministic encoder learns task-related representation and a probabilistic encoder with an Indian Buffet Process (IBP) learns the unknown number of unobservable confounding factors. We tested the presented model in two datasets: a handwritten digit dataset (MNIST) augmented with colored digits and a clinical ECG dataset with significant inter-subject variations and augmented with signal artifacts. These diverse data sets highlighted the ability of the presented model to grow with the complexity of the data and identify the absence or presence of unobserved confounding factors. |
| Tasks | Representation Learning |
| Published | 2018-10-31 |
| URL | https://arxiv.org/abs/1811.00073v3 |
| https://arxiv.org/pdf/1811.00073v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-generative-model-with-beta-bernoulli |
| Repo | |
| Framework | |
PhaseLink: A Deep Learning Approach to Seismic Phase Association
| Title | PhaseLink: A Deep Learning Approach to Seismic Phase Association |
| Authors | Zachary E. Ross, Yisong Yue, Men-Andrin Meier, Egill Hauksson, Thomas H. Heaton |
| Abstract | Seismic phase association is a fundamental task in seismology that pertains to linking together phase detections on different sensors that originate from a common earthquake. It is widely employed to detect earthquakes on permanent and temporary seismic networks, and underlies most seismicity catalogs produced around the world. This task can be challenging because the number of sources is unknown, events frequently overlap in time, or can occur simultaneously in different parts of a network. We present PhaseLink, a framework based on recent advances in deep learning for grid-free earthquake phase association. Our approach learns to link phases together that share a common origin, and is trained entirely on tens of millions of synthetic sequences of P- and S-wave arrival times generated using a simple 1D velocity model. Our approach is simple to implement for any tectonic regime, suitable for real-time processing, and can naturally incorporate errors in arrival time picks. Rather than tuning a set of ad hoc hyperparameters to improve performance, PhaseLink can be improved by simply adding examples of problematic cases to the training dataset. We demonstrate the state-of-the-art performance of PhaseLink on a challenging recent sequence from southern California, and synthesized sequences from Japan designed to test the point at which the method fails. For the examined datasets, PhaseLink can precisely associate P- and S-picks to events that are separated by ~12 seconds in origin time. This approach is expected to improve the resolution of seismicity catalogs, add stability to real-time seismic monitoring, and streamline automated processing of large seismic datasets. |
| Tasks | |
| Published | 2018-09-08 |
| URL | http://arxiv.org/abs/1809.02880v2 |
| http://arxiv.org/pdf/1809.02880v2.pdf | |
| PWC | https://paperswithcode.com/paper/phaselink-a-deep-learning-approach-to-seismic |
| Repo | |
| Framework | |
SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data
| Title | SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data |
| Authors | Qi Chen, Weichao Qiu, Yi Zhang, Lingxi Xie, Alan Yuille |
| Abstract | State-of-the-art techniques of artificial intelligence, in particular deep learning, are mostly data-driven. However, collecting and manually labeling a large scale dataset is both difficult and expensive. A promising alternative is to introduce synthesized training data, so that the dataset size can be significantly enlarged with little human labor. But, this raises an important problem in active vision: given an {\bf infinite} data space, how to effectively sample a {\bf finite} subset to train a visual classifier? This paper presents an approach for learning from synthesized data effectively. The motivation is straightforward – increasing the probability of seeing difficult training data. We introduce a module named {\bf SampleAhead} to formulate the learning process into an online communication between a {\em classifier} and a {\em sampler}, and update them iteratively. In each round, we adjust the sampling distribution according to the classification results, and train the classifier using the data sampled from the updated distribution. Experiments are performed by introducing synthesized images rendered from ShapeNet models to assist PASCAL3D+ classification. Our approach enjoys higher classification accuracy, especially in the scenario of a limited number of training samples. This demonstrates its efficiency in exploring the infinite data space. |
| Tasks | |
| Published | 2018-04-01 |
| URL | http://arxiv.org/abs/1804.00248v2 |
| http://arxiv.org/pdf/1804.00248v2.pdf | |
| PWC | https://paperswithcode.com/paper/sampleahead-online-classifier-sampler |
| Repo | |
| Framework | |
