July 30, 2019

3234 words 16 mins read

Paper Group AWR 17

Learning Disentangled Representations with Semi-Supervised Deep Generative Models. Lagged Exact Bayesian Online Changepoint Detection with Parameter Estimation. Deep Air Learning: Interpolation, Prediction, and Feature Analysis of Fine-grained Air Quality. Grammar Variational Autoencoder. Constrained Policy Optimization. Deep Reinforcement Learning …

Learning Disentangled Representations with Semi-Supervised Deep Generative Models


Title	Learning Disentangled Representations with Semi-Supervised Deep Generative Models
Authors	N. Siddharth, Brooks Paige, Jan-Willem van de Meent, Alban Desmaison, Noah D. Goodman, Pushmeet Kohli, Frank Wood, Philip H. S. Torr
Abstract	Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are interested in learning disentangled representations that encode distinct aspects of the data into separate variables. We propose to learn such representations using model architectures that generalise from standard VAEs, employing a general graphical model structure in the encoder and decoder. This allows us to train partially-specified models that make relatively strong assumptions about a subset of interpretable variables and rely on the flexibility of neural networks to learn representations for the remaining variables. We further define a general objective for semi-supervised learning in this model class, which can be approximated using an importance sampling procedure. We evaluate our framework’s ability to learn disentangled representations, both by qualitative exploration of its generative capacity, and quantitative evaluation of its discriminative ability on a variety of models and datasets.
Tasks	Representation Learning
Published	2017-06-01
URL	http://arxiv.org/abs/1706.00400v2
PDF	http://arxiv.org/pdf/1706.00400v2.pdf
PWC	https://paperswithcode.com/paper/learning-disentangled-representations-with-1
Repo	https://github.com/probtorch/probtorch
Framework	pytorch

Lagged Exact Bayesian Online Changepoint Detection with Parameter Estimation


Title	Lagged Exact Bayesian Online Changepoint Detection with Parameter Estimation
Authors	Michael Byrd, Linh Nghiem, Jing Cao
Abstract	Identifying changes in the generative process of sequential data, known as changepoint detection, has become an increasingly important topic for a wide variety of fields. A recently developed approach, which we call EXact Online Bayesian Changepoint Detection (EXO), has shown reasonable results with efficient computation for real time updates. The method is based on a \textit{forward} recursive message-passing algorithm. However, the detected changepoints from these methods are unstable. We propose a new algorithm called Lagged EXact Online Bayesian Changepoint Detection (LEXO) that improves the accuracy and stability of the detection by incorporating $\ell$-time lags to the inference. The new algorithm adds a recursive \textit{backward} step to the forward EXO and has computational complexity linear in the number of added lags. Estimation of parameters associated with regimes is also developed. Simulation studies with three common changepoint models show that the detected changepoints from LEXO are much more stable and parameter estimates from LEXO have considerably lower MSE than EXO. We illustrate applicability of the methods with two real world data examples comparing the EXO and LEXO.
Tasks
Published	2017-10-09
URL	http://arxiv.org/abs/1710.03276v3
PDF	http://arxiv.org/pdf/1710.03276v3.pdf
PWC	https://paperswithcode.com/paper/lagged-exact-bayesian-online-changepoint
Repo	https://github.com/lnghiemum/LEXO
Framework	none

Deep Air Learning: Interpolation, Prediction, and Feature Analysis of Fine-grained Air Quality


Title	Deep Air Learning: Interpolation, Prediction, and Feature Analysis of Fine-grained Air Quality
Authors	Zhongang Qi, Tianchun Wang, Guojie Song, Weisong Hu, Xi Li, Zhongfei, Zhang
Abstract	The interpolation, prediction, and feature analysis of fine-gained air quality are three important topics in the area of urban air computing. The solutions to these topics can provide extremely useful information to support air pollution control, and consequently generate great societal and technical impacts. Most of the existing work solves the three problems separately by different models. In this paper, we propose a general and effective approach to solve the three problems in one model called the Deep Air Learning (DAL). The main idea of DAL lies in embedding feature selection and semi-supervised learning in different layers of the deep learning network. The proposed approach utilizes the information pertaining to the unlabeled spatio-temporal data to improve the performance of the interpolation and the prediction, and performs feature selection and association analysis to reveal the main relevant features to the variation of the air quality. We evaluate our approach with extensive experiments based on real data sources obtained in Beijing, China. Experiments show that DAL is superior to the peer models from the recent literature when solving the topics of interpolation, prediction, and feature analysis of fine-gained air quality.
Tasks	Feature Selection
Published	2017-11-02
URL	http://arxiv.org/abs/1711.00939v2
PDF	http://arxiv.org/pdf/1711.00939v2.pdf
PWC	https://paperswithcode.com/paper/deep-air-learning-interpolation-prediction
Repo	https://github.com/linyijun/deep-air-learning-paper
Framework	none

Grammar Variational Autoencoder


Title	Grammar Variational Autoencoder
Authors	Matt J. Kusner, Brooks Paige, José Miguel Hernández-Lobato
Abstract	Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular structures still poses significant challenges. Crucially, state-of-the-art methods often produce outputs that are not valid. We make the key observation that frequently, discrete data can be represented as a parse tree from a context-free grammar. We propose a variational autoencoder which encodes and decodes directly to and from these parse trees, ensuring the generated outputs are always valid. Surprisingly, we show that not only does our model more often generate valid outputs, it also learns a more coherent latent space in which nearby points decode to similar discrete outputs. We demonstrate the effectiveness of our learned models by showing their improved performance in Bayesian optimization for symbolic regression and molecular synthesis.
Tasks
Published	2017-03-06
URL	http://arxiv.org/abs/1703.01925v1
PDF	http://arxiv.org/pdf/1703.01925v1.pdf
PWC	https://paperswithcode.com/paper/grammar-variational-autoencoder
Repo	https://github.com/ZmeiGorynych/generative_playground
Framework	pytorch

Constrained Policy Optimization


Title	Constrained Policy Optimization
Authors	Joshua Achiam, David Held, Aviv Tamar, Pieter Abbeel
Abstract	For many applications of reinforcement learning it can be more convenient to specify both a reward function and constraints, rather than trying to design behavior through the reward function. For example, systems that physically interact with or around humans should satisfy safety constraints. Recent advances in policy search algorithms (Mnih et al., 2016, Schulman et al., 2015, Lillicrap et al., 2016, Levine et al., 2016) have enabled new capabilities in high-dimensional control, but do not consider the constrained setting. We propose Constrained Policy Optimization (CPO), the first general-purpose policy search algorithm for constrained reinforcement learning with guarantees for near-constraint satisfaction at each iteration. Our method allows us to train neural network policies for high-dimensional control while making guarantees about policy behavior all throughout training. Our guarantees are based on a new theoretical result, which is of independent interest: we prove a bound relating the expected returns of two policies to an average divergence between them. We demonstrate the effectiveness of our approach on simulated robot locomotion tasks where the agent must satisfy constraints motivated by safety.
Tasks
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10528v1
PDF	http://arxiv.org/pdf/1705.10528v1.pdf
PWC	https://paperswithcode.com/paper/constrained-policy-optimization
Repo	https://github.com/eloiseberthier/Safe_RL
Framework	none

Deep Reinforcement Learning for De-Novo Drug Design


Title	Deep Reinforcement Learning for De-Novo Drug Design
Authors	Mariya Popova, Olexandr Isayev, Alexander Tropsha
Abstract	We propose a novel computational strategy for de novo design of molecules with desired properties termed ReLeaSE (Reinforcement Learning for Structural Evolution). Based on deep and reinforcement learning approaches, ReLeaSE integrates two deep neural networks - generative and predictive - that are trained separately but employed jointly to generate novel targeted chemical libraries. ReLeaSE employs simple representation of molecules by their SMILES strings only. Generative models are trained with stack-augmented memory network to produce chemically feasible SMILES strings, and predictive models are derived to forecast the desired properties of the de novo generated compounds. In the first phase of the method, generative and predictive models are trained separately with a supervised learning algorithm. In the second phase, both models are trained jointly with the reinforcement learning approach to bias the generation of new chemical structures towards those with the desired physical and/or biological properties. In the proof-of-concept study, we have employed the ReLeaSE method to design chemical libraries with a bias toward structural complexity or biased toward compounds with either maximal, minimal, or specific range of physical properties such as melting point or hydrophobicity, as well as to develop novel putative inhibitors of JAK2. The approach proposed herein can find a general use for generating targeted chemical libraries of novel compounds optimized for either a single desired property or multiple properties.
Tasks
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10907v2
PDF	http://arxiv.org/pdf/1711.10907v2.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-for-de-novo-drug
Repo	https://github.com/isayev/ReLeaSE
Framework	pytorch

Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN


Title	Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
Authors	Weiwei Hu, Ying Tan
Abstract	Machine learning has been used to detect new malware in recent years, while malware authors have strong motivation to attack such algorithms. Malware authors usually have no access to the detailed structures and parameters of the machine learning models used by malware detection systems, and therefore they can only perform black-box attacks. This paper proposes a generative adversarial network (GAN) based algorithm named MalGAN to generate adversarial malware examples, which are able to bypass black-box machine learning based detection models. MalGAN uses a substitute detector to fit the black-box malware detection system. A generative network is trained to minimize the generated adversarial examples’ malicious probabilities predicted by the substitute detector. The superiority of MalGAN over traditional gradient based adversarial example generation algorithms is that MalGAN is able to decrease the detection rate to nearly zero and make the retraining based defensive method against adversarial examples hard to work.
Tasks	Malware Detection
Published	2017-02-20
URL	http://arxiv.org/abs/1702.05983v1
PDF	http://arxiv.org/pdf/1702.05983v1.pdf
PWC	https://paperswithcode.com/paper/generating-adversarial-malware-examples-for
Repo	https://github.com/yortyj/Exploiting-GANs-for-Phun-and-Profit
Framework	none

A generalized method toward drug-target interaction prediction via low-rank matrix projection


Title	A generalized method toward drug-target interaction prediction via low-rank matrix projection
Authors	Ratha Pech, Dong Hao, Yan-Li Lee, Maryna Po, Tao Zhou
Abstract	Drug-target interaction (DTI) prediction plays a very important role in drug development and drug discovery. Biochemical experiments or \textit{in vitro} methods are very expensive, laborious and time-consuming. Therefore, \textit{in silico} approaches including docking simulation and machine learning have been proposed to solve this problem. In particular, machine learning approaches have attracted increasing attentions recently. However, in addition to the known drug-target interactions, most of the machine learning methods require extra characteristic information such as chemical structures, genome sequences, binding types and so on. Whenever such information is not available, they may perform poor. Very recently, the similarity-based link prediction methods were extended to bipartite networks, which can be applied to solve the DTI prediction problem by using topological information only. In this work, we propose a method based on low-rank matrix projection to solve the DTI prediction problem. On one hand, when there is no extra characteristic information of drugs or targets, the proposed method utilizes only the known interactions. On the other hand, the proposed method can also utilize the extra characteristic information when it is available and the performances will be remarkably improved. Moreover, the proposed method can predict the interactions associated with new drugs or targets of which we know nothing about their associated interactions, but only some characteristic information. We compare the proposed method with ten baseline methods, e.g., six similarity-based methods that utilize only the known interactions and four methods that utilize the extra characteristic information. The datasets and codes implementing the simulations are available at https://github.com/rathapech/DTI_LMP.
Tasks	Drug Discovery, Link Prediction
Published	2017-06-06
URL	http://arxiv.org/abs/1706.01876v2
PDF	http://arxiv.org/pdf/1706.01876v2.pdf
PWC	https://paperswithcode.com/paper/a-generalized-method-toward-drug-target
Repo	https://github.com/rathapech/DTI_LMP
Framework	none

Meta-SGD: Learning to Learn Quickly for Few-Shot Learning


Title	Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
Authors	Zhenguo Li, Fengwei Zhou, Fei Chen, Hang Li
Abstract	Few-shot learning is challenging for learning algorithms that learn each task in isolation and from scratch. In contrast, meta-learning learns from many related tasks a meta-learner that can learn a new task more accurately and faster with fewer examples, where the choice of meta-learners is crucial. In this paper, we develop Meta-SGD, an SGD-like, easily trainable meta-learner that can initialize and adapt any differentiable learner in just one step, on both supervised learning and reinforcement learning. Compared to the popular meta-learner LSTM, Meta-SGD is conceptually simpler, easier to implement, and can be learned more efficiently. Compared to the latest meta-learner MAML, Meta-SGD has a much higher capacity by learning to learn not just the learner initialization, but also the learner update direction and learning rate, all in a single meta-learning process. Meta-SGD shows highly competitive performance for few-shot learning on regression, classification, and reinforcement learning.
Tasks	Few-Shot Learning, Meta-Learning
Published	2017-07-31
URL	http://arxiv.org/abs/1707.09835v2
PDF	http://arxiv.org/pdf/1707.09835v2.pdf
PWC	https://paperswithcode.com/paper/meta-sgd-learning-to-learn-quickly-for-few
Repo	https://github.com/ash3n/Meta-Gradients
Framework	tf

TransNets: Learning to Transform for Recommendation


Title	TransNets: Learning to Transform for Recommendation
Authors	Rose Catherine, William Cohen
Abstract	Recently, deep learning methods have been shown to improve the performance of recommender systems over traditional methods, especially when review text is available. For example, a recent model, DeepCoNN, uses neural nets to learn one latent representation for the text of all reviews written by a target user, and a second latent representation for the text of all reviews for a target item, and then combines these latent representations to obtain state-of-the-art performance on recommendation tasks. We show that (unsurprisingly) much of the predictive value of review text comes from reviews of the target user for the target item. We then introduce a way in which this information can be used in recommendation, even when the target user’s review for the target item is not available. Our model, called TransNets, extends the DeepCoNN model by introducing an additional latent layer representing the target user-target item pair. We then regularize this layer, at training time, to be similar to another latent representation of the target user’s review of the target item. We show that TransNets and extensions of it improve substantially over the previous state-of-the-art.
Tasks	Recommendation Systems
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02298v2
PDF	http://arxiv.org/pdf/1704.02298v2.pdf
PWC	https://paperswithcode.com/paper/transnets-learning-to-transform-for
Repo	https://github.com/rosecatherinek/TransNets
Framework	tf

DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation


Title	DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation
Authors	Markus Oberweger, Vincent Lepetit
Abstract	DeepPrior is a simple approach based on Deep Learning that predicts the joint 3D locations of a hand given a depth map. Since its publication early 2015, it has been outperformed by several impressive works. Here we show that with simple improvements: adding ResNet layers, data augmentation, and better initial hand localization, we achieve better or similar performance than more sophisticated recent methods on the three main benchmarks (NYU, ICVL, MSRA) while keeping the simplicity of the original method. Our new implementation is available at https://github.com/moberweger/deep-prior-pp .
Tasks	Data Augmentation, Hand Pose Estimation, Pose Estimation
Published	2017-08-28
URL	http://arxiv.org/abs/1708.08325v1
PDF	http://arxiv.org/pdf/1708.08325v1.pdf
PWC	https://paperswithcode.com/paper/deepprior-improving-fast-and-accurate-3d-hand
Repo	https://github.com/RonLek/FastV2C-HandNet
Framework	tf

DeepSign: Deep Learning for Automatic Malware Signature Generation and Classification


Title	DeepSign: Deep Learning for Automatic Malware Signature Generation and Classification
Authors	Eli David, Nathan S. Netanyahu
Abstract	This paper presents a novel deep learning based method for automatic malware signature generation and classification. The method uses a deep belief network (DBN), implemented with a deep stack of denoising autoencoders, generating an invariant compact representation of the malware behavior. While conventional signature and token based methods for malware detection do not detect a majority of new variants for existing malware, the results presented in this paper show that signatures generated by the DBN allow for an accurate classification of new malware variants. Using a dataset containing hundreds of variants for several major malware families, our method achieves 98.6% classification accuracy using the signatures generated by the DBN. The presented method is completely agnostic to the type of malware behavior that is logged (e.g., API calls and their parameters, registry entries, websites and ports accessed, etc.), and can use any raw input from a sandbox to successfully train the deep neural network which is used to generate malware signatures.
Tasks	Denoising, Malware Detection
Published	2017-11-21
URL	http://arxiv.org/abs/1711.08336v2
PDF	http://arxiv.org/pdf/1711.08336v2.pdf
PWC	https://paperswithcode.com/paper/deepsign-deep-learning-for-automatic-malware
Repo	https://github.com/tychen5/sportslottery
Framework	none

Higher-order Relation Schema Induction using Tensor Factorization with Back-off and Aggregation


Title	Higher-order Relation Schema Induction using Tensor Factorization with Back-off and Aggregation
Authors	Madhav Nimishakavi, Partha Talukdar
Abstract	Relation Schema Induction (RSI) is the problem of identifying type signatures of arguments of relations from unlabeled text. Most of the previous work in this area have focused only on binary RSI, i.e., inducing only the subject and object type signatures per relation. However, in practice, many relations are high-order, i.e., they have more than two arguments and inducing type signatures of all arguments is necessary. For example, in the sports domain, inducing a schema win(WinningPlayer, OpponentPlayer, Tournament, Location) is more informative than inducing just win(WinningPlayer, OpponentPlayer). We refer to this problem as Higher-order Relation Schema Induction (HRSI). In this paper, we propose Tensor Factorization with Back-off and Aggregation (TFBA), a novel framework for the HRSI problem. To the best of our knowledge, this is the first attempt at inducing higher-order relation schemata from unlabeled text. Using the experimental analysis on three real world datasets, we show how TFBA helps in dealing with sparsity and induce higher order schemata.
Tasks
Published	2017-07-06
URL	http://arxiv.org/abs/1707.01917v2
PDF	http://arxiv.org/pdf/1707.01917v2.pdf
PWC	https://paperswithcode.com/paper/higher-order-relation-schema-induction-using
Repo	https://github.com/madhavcsa/TFBA
Framework	none

One-shot Face Recognition by Promoting Underrepresented Classes


Title	One-shot Face Recognition by Promoting Underrepresented Classes
Authors	Yandong Guo, Lei Zhang
Abstract	In this paper, we study the problem of training large-scale face identification model with imbalanced training data. This problem naturally exists in many real scenarios including large-scale celebrity recognition, movie actor annotation, etc. Our solution contains two components. First, we build a face feature extraction model, and improve its performance, especially for the persons with very limited training samples, by introducing a regularizer to the cross entropy loss for the multi-nomial logistic regression (MLR) learning. This regularizer encourages the directions of the face features from the same class to be close to the direction of their corresponding classification weight vector in the logistic regression. Second, we build a multi-class classifier using MLR on top of the learned face feature extraction model. Since the standard MLR has poor generalization capability for the one-shot classes even if these classes have been oversampled, we propose a novel supervision signal called underrepresented-classes promotion loss, which aligns the norms of the weight vectors of the one-shot classes (a.k.a. underrepresented-classes) to those of the normal classes. In addition to the original cross entropy loss, this new loss term effectively promotes the underrepresented classes in the learned model and leads to a remarkable improvement in face recognition performance. We test our solution on the MS-Celeb-1M low-shot learning benchmark task. Our solution recognizes 94.89% of the test images at the precision of 99% for the one-shot classes. To the best of our knowledge, this is the best performance among all the published methods using this benchmark task with the same setup, including all the participants in the recent MS-Celeb-1M challenge at ICCV 2017.
Tasks	Face Identification, Face Recognition
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05574v2
PDF	http://arxiv.org/pdf/1707.05574v2.pdf
PWC	https://paperswithcode.com/paper/one-shot-face-recognition-by-promoting
Repo	https://github.com/SimonLliu/CSS_and_up_term
Framework	pytorch

Deep Learning-Based Food Calorie Estimation Method in Dietary Assessment


Title	Deep Learning-Based Food Calorie Estimation Method in Dietary Assessment
Authors	Yanchao Liang, Jianhua Li
Abstract	Obesity treatment requires obese patients to record all food intakes per day. Computer vision has been introduced to estimate calories from food images. In order to increase accuracy of detection and reduce the error of volume estimation in food calorie estimation, we present our calorie estimation method in this paper. To estimate calorie of food, a top view and side view is needed. Faster R-CNN is used to detect the food and calibration object. GrabCut algorithm is used to get each food’s contour. Then the volume is estimated with the food and corresponding object. Finally we estimate each food’s calorie. And the experiment results show our estimation method is effective.
Tasks	Calibration
Published	2017-06-10
URL	http://arxiv.org/abs/1706.04062v4
PDF	http://arxiv.org/pdf/1706.04062v4.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-food-calorie-estimation
Repo	https://github.com/Liang-yc/CalorieEstimation
Framework	none