October 20, 2019

3078 words 15 mins read

Paper Group AWR 220

Semi-Recurrent CNN-based VAE-GAN for Sequential Data Generation. BOHB: Robust and Efficient Hyperparameter Optimization at Scale. A New Benchmark and Progress Toward Improved Weakly Supervised Learning. Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search. FRAGE: Frequency-Agnostic Word Repres …

Semi-Recurrent CNN-based VAE-GAN for Sequential Data Generation


Title	Semi-Recurrent CNN-based VAE-GAN for Sequential Data Generation
Authors	Mohammad Akbari, Jie Liang
Abstract	A semi-recurrent hybrid VAE-GAN model for generating sequential data is introduced. In order to consider the spatial correlation of the data in each frame of the generated sequence, CNNs are utilized in the encoder, generator, and discriminator. The subsequent frames are sampled from the latent distributions obtained by encoding the previous frames. As a result, the dependencies between the frames are maintained. Two testing frameworks for synthesizing a sequence with any number of frames are also proposed. The promising experimental results on piano music generation indicates the potential of the proposed framework in modeling other sequential data such as video.
Tasks	Music Generation
Published	2018-06-01
URL	http://arxiv.org/abs/1806.00509v1
PDF	http://arxiv.org/pdf/1806.00509v1.pdf
PWC	https://paperswithcode.com/paper/semi-recurrent-cnn-based-vae-gan-for
Repo	https://github.com/makbari7/SR-CNN-VAE-GAN
Framework	tf

BOHB: Robust and Efficient Hyperparameter Optimization at Scale


Title	BOHB: Robust and Efficient Hyperparameter Optimization at Scale
Authors	Stefan Falkner, Aaron Klein, Frank Hutter
Abstract	Modern deep learning methods are very sensitive to many hyperparameters, and, due to the long training times of state-of-the-art models, vanilla Bayesian hyperparameter optimization is typically computationally infeasible. On the other hand, bandit-based configuration evaluation approaches based on random search lack guidance and do not converge to the best configurations as quickly. Here, we propose to combine the benefits of both Bayesian optimization and bandit-based methods, in order to achieve the best of both worlds: strong anytime performance and fast convergence to optimal configurations. We propose a new practical state-of-the-art hyperparameter optimization method, which consistently outperforms both Bayesian optimization and Hyperband on a wide range of problem types, including high-dimensional toy functions, support vector machines, feed-forward neural networks, Bayesian neural networks, deep reinforcement learning, and convolutional neural networks. Our method is robust and versatile, while at the same time being conceptually simple and easy to implement.
Tasks	Hyperparameter Optimization
Published	2018-07-04
URL	http://arxiv.org/abs/1807.01774v1
PDF	http://arxiv.org/pdf/1807.01774v1.pdf
PWC	https://paperswithcode.com/paper/bohb-robust-and-efficient-hyperparameter
Repo	https://github.com/automl/HpBandSter
Framework	none

A New Benchmark and Progress Toward Improved Weakly Supervised Learning


Title	A New Benchmark and Progress Toward Improved Weakly Supervised Learning
Authors	Jason Ramapuram, Russ Webb
Abstract	Knowledge Matters: Importance of Prior Information for Optimization [7], by Gulcehre et. al., sought to establish the limits of current black-box, deep learning techniques by posing problems which are difficult to learn without engineering knowledge into the model or training procedure. In our work, we completely solve the previous Knowledge Matters problem using a generic model, pose a more difficult and scalable problem, All-Pairs, and advance this new problem by introducing a new learned, spatially-varying histogram model called TypeNet which outperforms conventional models on the problem. We present results on All-Pairs where our model achieves 100% test accuracy while the best ResNet models achieve 79% accuracy. In addition, our model is more than an order of magnitude smaller than Resnet-34. The challenge of solving larger-scale All-Pairs problems with high accuracy is presented to the community for investigation.
Tasks
Published	2018-06-30
URL	http://arxiv.org/abs/1807.00126v2
PDF	http://arxiv.org/pdf/1807.00126v2.pdf
PWC	https://paperswithcode.com/paper/a-new-benchmark-and-progress-toward-improved
Repo	https://github.com/apple/ml-all-pairs
Framework	pytorch

Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search


Title	Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search
Authors	Masanori Suganuma, Mete Ozay, Takayuki Okatani
Abstract	Researchers have applied deep neural networks to image restoration tasks, in which they proposed various network architectures, loss functions, and training methods. In particular, adversarial training, which is employed in recent studies, seems to be a key ingredient to success. In this paper, we show that simple convolutional autoencoders (CAEs) built upon only standard network components, i.e., convolutional layers and skip connections, can outperform the state-of-the-art methods which employ adversarial training and sophisticated loss functions. The secret is to employ an evolutionary algorithm to automatically search for good architectures. Training optimized CAEs by minimizing the $\ell_2$ loss between reconstructed images and their ground truths using the ADAM optimizer is all we need. Our experimental results show that this approach achieves 27.8 dB peak signal to noise ratio (PSNR) on the CelebA dataset and 40.4 dB on the SVHN dataset, compared to 22.8 dB and 33.0 dB provided by the former state-of-the-art methods, respectively.
Tasks	Image Restoration
Published	2018-03-01
URL	http://arxiv.org/abs/1803.00370v1
PDF	http://arxiv.org/pdf/1803.00370v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-the-potential-of-standard
Repo	https://github.com/sg-nm/Evolutionary-Autoencoders
Framework	pytorch

FRAGE: Frequency-Agnostic Word Representation


Title	FRAGE: Frequency-Agnostic Word Representation
Authors	Chengyue Gong, Di He, Xu Tan, Tao Qin, Liwei Wang, Tie-Yan Liu
Abstract	Continuous word representation (aka word embedding) is a basic building block in many neural network-based models used in natural language processing tasks. Although it is widely accepted that words with similar semantics should be close to each other in the embedding space, we find that word embeddings learned in several tasks are biased towards word frequency: the embeddings of high-frequency and low-frequency words lie in different subregions of the embedding space, and the embedding of a rare word and a popular word can be far from each other even if they are semantically similar. This makes learned word embeddings ineffective, especially for rare words, and consequently limits the performance of these neural network models. In this paper, we develop a neat, simple yet effective way to learn \emph{FRequency-AGnostic word Embedding} (FRAGE) using adversarial training. We conducted comprehensive studies on ten datasets across four natural language processing tasks, including word similarity, language modeling, machine translation and text classification. Results show that with FRAGE, we achieve higher performance than the baselines in all tasks.
Tasks	Language Modelling, Machine Translation, Text Classification, Word Embeddings
Published	2018-09-18
URL	https://arxiv.org/abs/1809.06858v2
PDF	https://arxiv.org/pdf/1809.06858v2.pdf
PWC	https://paperswithcode.com/paper/frage-frequency-agnostic-word-representation
Repo	https://github.com/bifeng/deep_coding_notes
Framework	tf

Accurate and efficient video de-fencing using convolutional neural networks and temporal information


Title	Accurate and efficient video de-fencing using convolutional neural networks and temporal information
Authors	Chen Du, Byeongkeun Kang, Zheng Xu, Ji Dai, Truong Nguyen
Abstract	De-fencing is to eliminate the captured fence on an image or a video, providing a clear view of the scene. It has been applied for many purposes including assisting photographers and improving the performance of computer vision algorithms such as object detection and recognition. However, the state-of-the-art de-fencing methods have limited performance caused by the difficulty of fence segmentation and also suffer from the motion of the camera or objects. To overcome these problems, we propose a novel method consisting of segmentation using convolutional neural networks and a fast/robust recovery algorithm. The segmentation algorithm using convolutional neural network achieves significant improvement in the accuracy of fence segmentation. The recovery algorithm using optical flow produces plausible de-fenced images and videos. The proposed method is experimented on both our diverse and complex dataset and publicly available datasets. The experimental results demonstrate that the proposed method achieves the state-of-the-art performance for both segmentation and content recovery.
Tasks	Object Detection, Optical Flow Estimation
Published	2018-06-28
URL	http://arxiv.org/abs/1806.10781v1
PDF	http://arxiv.org/pdf/1806.10781v1.pdf
PWC	https://paperswithcode.com/paper/accurate-and-efficient-video-de-fencing-using
Repo	https://github.com/chen-du/De-fencing
Framework	none

The Ocean Tensor Package


Title	The Ocean Tensor Package
Authors	Ewout van den Berg
Abstract	Matrix and tensor operations form the basis of a wide range of fields and applications, and in many cases constitute a substantial part of the overall computational complexity. The ability of general-purpose GPUs to speed up many of these operations and enable others has resulted in a widespread adaptation of these devices. In order for tensor operations to take full advantage of the computational power, specialized software is required, and currently there exist several packages (predominantly in the area of deep learning) that incorporate tensor operations on both CPU and GPU. Nevertheless, a stand-alone framework that supports general tensor operations is still missing. In this paper we fill this gap and propose the Ocean Tensor Library: a modular tensor-support package that is designed to serve as a foundational layer for applications that require dense tensor operations on a variety of device types. The API is carefully designed to be powerful, extensible, and at the same time easy to use. The package is available as open source.
Tasks
Published	2018-10-20
URL	http://arxiv.org/abs/1810.08723v1
PDF	http://arxiv.org/pdf/1810.08723v1.pdf
PWC	https://paperswithcode.com/paper/the-ocean-tensor-package
Repo	https://github.com/ibm/ocean-tensor-package
Framework	none

Multilingual Clustering of Streaming News


Title	Multilingual Clustering of Streaming News
Authors	Sebastião Miranda, Artūrs Znotiņš, Shay B. Cohen, Guntis Barzdins
Abstract	Clustering news across languages enables efficient media monitoring by aggregating articles from multilingual sources into coherent stories. Doing so in an online setting allows scalable processing of massive news streams. To this end, we describe a novel method for clustering an incoming stream of multilingual documents into monolingual and crosslingual story clusters. Unlike typical clustering approaches that consider a small and known number of labels, we tackle the problem of discovering an ever growing number of cluster labels in an online fashion, using real news datasets in multiple languages. Our method is simple to implement, computationally efficient and produces state-of-the-art results on datasets in German, English and Spanish.
Tasks
Published	2018-09-03
URL	http://arxiv.org/abs/1809.00540v1
PDF	http://arxiv.org/pdf/1809.00540v1.pdf
PWC	https://paperswithcode.com/paper/multilingual-clustering-of-streaming-news
Repo	https://github.com/priberam/news-clustering
Framework	none

MRFusion: A Deep Learning architecture to fuse PAN and MS imagery for land cover mapping


Title	MRFusion: A Deep Learning architecture to fuse PAN and MS imagery for land cover mapping
Authors	Raffaele Gaetano, Dino Ienco, Kenji Ose, Remi Cresson
Abstract	Nowadays, Earth Observation systems provide a multitude of heterogeneous remote sensing data. How to manage such richness leveraging its complementarity is a crucial chal- lenge in modern remote sensing analysis. Data Fusion techniques deal with this point proposing method to combine and exploit complementarity among the different data sensors. Considering optical Very High Spatial Resolution (VHSR) images, satellites obtain both Multi Spectral (MS) and panchro- matic (PAN) images at different spatial resolution. VHSR images are extensively exploited to produce land cover maps to deal with agricultural, ecological, and socioeconomic issues as well as assessing ecosystem status, monitoring biodiversity and provid- ing inputs to conceive food risk monitoring systems. Common techniques to produce land cover maps from such VHSR images typically opt for a prior pansharpening of the multi-resolution source for a full resolution processing. Here, we propose a new deep learning architecture to jointly use PAN and MS imagery for a direct classification without any prior image fusion or resampling process. By managing the spectral information at its native spatial resolution, our method, named MRFusion, aims at avoiding the possible infor- mation loss induced by pansharpening or any other hand-crafted preprocessing. Moreover, the proposed architecture is suitably designed to learn non-linear transformations of the sources with the explicit aim of taking as much as possible advantage of the complementarity of PAN and MS imagery. Experiments are carried out on two-real world scenarios depicting large areas with different land cover characteristics. The characteristics of the proposed scenarios underline the applicability and the generality of our method in operational settings.
Tasks
Published	2018-06-29
URL	http://arxiv.org/abs/1806.11452v1
PDF	http://arxiv.org/pdf/1806.11452v1.pdf
PWC	https://paperswithcode.com/paper/mrfusion-a-deep-learning-architecture-to-fuse
Repo	https://github.com/tanodino/MultiResoLCC
Framework	tf

Finding Average Regret Ratio Minimizing Set in Database


Title	Finding Average Regret Ratio Minimizing Set in Database
Authors	Sepanta Zeighami, Raymong Chi-Wing Wong
Abstract	Selecting a certain number of data points (or records) from a database which “best” satisfy users’ expectations is a very prevalent problem with many applications. One application is a hotel booking website showing a certain number of hotels on a single page. However, this problem is very challenging since the selected points should “collectively” satisfy the expectation of all users. Showing a certain number of data points to a single user could decrease the satisfaction of a user because the user may not be able to see his/her favorite point which could be found in the original database. In this paper, we would like to find a set of k points such that on average, the satisfaction (ratio) of a user is maximized. This problem takes into account the probability distribution of the users and considers the satisfaction (ratio) of all users, which is more reasonable in practice, compared with the existing studies that only consider the worst-case satisfaction (ratio) of the users, which may not reflect the whole population and is not useful in some applications. Motivated by this, in this paper, we propose algorithms for this problem. Finally, we conducted experiments to show the effectiveness and the efficiency of the algorithms.
Tasks
Published	2018-10-18
URL	http://arxiv.org/abs/1810.08047v1
PDF	http://arxiv.org/pdf/1810.08047v1.pdf
PWC	https://paperswithcode.com/paper/finding-average-regret-ratio-minimizing-set
Repo	https://github.com/szeighami/FAM_Greedy-Shrink
Framework	none

A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction


Title	A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction
Authors	Shamil Chollampatt, Hwee Tou Ng
Abstract	We improve automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network. The network is initialized with embeddings that make use of character N-gram information to better suit this task. When evaluated on common benchmark test data sets (CoNLL-2014 and JFLEG), our model substantially outperforms all prior neural approaches on this task as well as strong statistical machine translation-based systems with neural and task-specific features trained on the same data. Our analysis shows the superiority of convolutional neural networks over recurrent neural networks such as long short-term memory (LSTM) networks in capturing the local context via attention, and thereby improving the coverage in correcting grammatical errors. By ensembling multiple models, and incorporating an N-gram language model and edit features via rescoring, our novel method becomes the first neural approach to outperform the current state-of-the-art statistical machine translation-based approach, both in terms of grammaticality and fluency.
Tasks	Grammatical Error Correction, Language Modelling
Published	2018-01-26
URL	http://arxiv.org/abs/1801.08831v1
PDF	http://arxiv.org/pdf/1801.08831v1.pdf
PWC	https://paperswithcode.com/paper/a-multilayer-convolutional-encoder-decoder
Repo	https://github.com/seaweiqing/neuraltalk_plus_charcnn
Framework	tf

Visualizing the Feature Importance for Black Box Models


Title	Visualizing the Feature Importance for Black Box Models
Authors	Giuseppe Casalicchio, Christoph Molnar, Bernd Bischl
Abstract	In recent years, a large amount of model-agnostic methods to improve the transparency, trustability and interpretability of machine learning models have been developed. We introduce local feature importance as a local version of a recent model-agnostic global feature importance method. Based on local feature importance, we propose two visual tools: partial importance (PI) and individual conditional importance (ICI) plots which visualize how changes in a feature affect the model performance on average, as well as for individual observations. Our proposed methods are related to partial dependence (PD) and individual conditional expectation (ICE) plots, but visualize the expected (conditional) feature importance instead of the expected (conditional) prediction. Furthermore, we show that averaging ICI curves across observations yields a PI curve, and integrating the PI curve with respect to the distribution of the considered feature results in the global feature importance. Another contribution of our paper is the Shapley feature importance, which fairly distributes the overall performance of a model among the features according to the marginal contributions and which can be used to compare the feature importance across different models.
Tasks	Feature Importance
Published	2018-04-18
URL	http://arxiv.org/abs/1804.06620v3
PDF	http://arxiv.org/pdf/1804.06620v3.pdf
PWC	https://paperswithcode.com/paper/visualizing-the-feature-importance-for-black
Repo	https://github.com/giuseppec/featureImportance
Framework	none

Granger-causal Attentive Mixtures of Experts: Learning Important Features with Neural Networks


Title	Granger-causal Attentive Mixtures of Experts: Learning Important Features with Neural Networks
Authors	Patrick Schwab, Djordje Miladinovic, Walter Karlen
Abstract	Knowledge of the importance of input features towards decisions made by machine-learning models is essential to increase our understanding of both the models and the underlying data. Here, we present a new approach to estimating feature importance with neural networks based on the idea of distributing the features of interest among experts in an attentive mixture of experts (AME). AMEs use attentive gating networks trained with a Granger-causal objective to learn to jointly produce accurate predictions as well as estimates of feature importance in a single model. Our experiments show (i) that the feature importance estimates provided by AMEs compare favourably to those provided by state-of-the-art methods, (ii) that AMEs are significantly faster at estimating feature importance than existing methods, and (iii) that the associations discovered by AMEs are consistent with those reported by domain experts.
Tasks	Feature Importance
Published	2018-02-06
URL	http://arxiv.org/abs/1802.02195v6
PDF	http://arxiv.org/pdf/1802.02195v6.pdf
PWC	https://paperswithcode.com/paper/granger-causal-attentive-mixtures-of-experts
Repo	https://github.com/d909b/ame
Framework	tf

Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding


Title	Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding
Authors	Dong Liu, Ke Sun, Zhangyang Wang, Runsheng Liu, Zheng-Jun Zha
Abstract	The problem of $L_p$-norm constrained coding is to convert signal into code that lies inside an $L_p$-ball and most faithfully reconstructs the signal. Previous works under the name of sparse coding considered the cases of $L_0$ and $L_1$ norms. The cases with $p>1$ values, i.e. non-sparse coding studied in this paper, remain a difficulty. We propose an interpretable deep structure namely Frank-Wolfe Network (F-W Net), whose architecture is inspired by unrolling and truncating the Frank-Wolfe algorithm for solving an $L_p$-norm constrained problem with $p\geq 1$. We show that the Frank-Wolfe solver for the $L_p$-norm constraint leads to a novel closed-form nonlinear unit, which is parameterized by $p$ and termed $pool_p$. The $pool_p$ unit links the conventional pooling, activation, and normalization operations, making F-W Net distinct from existing deep networks either heuristically designed or converted from projected gradient descent algorithms. We further show that the hyper-parameter $p$ can be made learnable instead of pre-chosen in F-W Net, which gracefully solves the non-sparse coding problem even with unknown $p$. We evaluate the performance of F-W Net on an extensive range of simulations as well as the task of handwritten digit recognition, where F-W Net exhibits strong learning capability. We then propose a convolutional version of F-W Net, and apply the convolutional F-W Net into image denoising and super-resolution tasks, where F-W Net all demonstrates impressive effectiveness, flexibility, and robustness.
Tasks	Denoising, Handwritten Digit Recognition, Image Denoising, Super-Resolution
Published	2018-02-28
URL	https://arxiv.org/abs/1802.10252v4
PDF	https://arxiv.org/pdf/1802.10252v4.pdf
PWC	https://paperswithcode.com/paper/l_p-norm-constrained-coding-with-frank-wolfe
Repo	https://github.com/sunke123/FW-Net
Framework	none

Paper Abstract Writing through Editing Mechanism


Title	Paper Abstract Writing through Editing Mechanism
Authors	Qingyun Wang, Zhihao Zhou, Lifu Huang, Spencer Whitehead, Boliang Zhang, Heng Ji, Kevin Knight
Abstract	We present a paper abstract writing system based on an attentive neural sequence-to-sequence model that can take a title as input and automatically generate an abstract. We design a novel Writing-editing Network that can attend to both the title and the previously generated abstract drafts and then iteratively revise and polish the abstract. With two series of Turing tests, where the human judges are asked to distinguish the system-generated abstracts from human-written ones, our system passes Turing tests by junior domain experts at a rate up to 30% and by non-expert at a rate up to 80%.
Tasks	Paper generation, Text Generation
Published	2018-05-15
URL	http://arxiv.org/abs/1805.06064v1
PDF	http://arxiv.org/pdf/1805.06064v1.pdf
PWC	https://paperswithcode.com/paper/paper-abstract-writing-through-editing
Repo	https://github.com/EagleW/Writing-editing-Network
Framework	pytorch