Paper Group ANR 1155
GANE: A Generative Adversarial Network Embedding. Alternate Estimation of a Classifier and the Class-Prior from Positive and Unlabeled Data. Learning Depth from Single Images with Deep Neural Network Embedding Focal Length. AAANE: Attention-based Adversarial Autoencoder for Multi-scale Network Embedding. Data Augmentation for Detection of Architect …
GANE: A Generative Adversarial Network Embedding
Title | GANE: A Generative Adversarial Network Embedding |
Authors | Huiting Hong, Xin Li, Mingzhong Wang |
Abstract | Network embedding has become a hot research topic recently which can provide low-dimensional feature representations for many machine learning applications. Current work focuses on either (1) whether the embedding is designed as an unsupervised learning task by explicitly preserving the structural connectivity in the network, or (2) whether the embedding is a by-product during the supervised learning of a specific discriminative task in a deep neural network. In this paper, we focus on bridging the gap of the two lines of the research. We propose to adapt the Generative Adversarial model to perform network embedding, in which the generator is trying to generate vertex pairs, while the discriminator tries to distinguish the generated vertex pairs from real connections (edges) in the network. Wasserstein-1 distance is adopted to train the generator to gain better stability. We develop three variations of models, including GANE which applies cosine similarity, GANE-O1 which preserves the first-order proximity, and GANE-O2 which tries to preserves the second-order proximity of the network in the low-dimensional embedded vector space. We later prove that GANE-O2 has the same objective function as GANE-O1 when negative sampling is applied to simplify the training process in GANE-O2. Experiments with real-world network datasets demonstrate that our models constantly outperform state-of-the-art solutions with significant improvements on precision in link prediction, as well as on visualizations and accuracy in clustering tasks. |
Tasks | Link Prediction, Network Embedding |
Published | 2018-05-18 |
URL | http://arxiv.org/abs/1805.07324v2 |
http://arxiv.org/pdf/1805.07324v2.pdf | |
PWC | https://paperswithcode.com/paper/gane-a-generative-adversarial-network |
Repo | |
Framework | |
Alternate Estimation of a Classifier and the Class-Prior from Positive and Unlabeled Data
Title | Alternate Estimation of a Classifier and the Class-Prior from Positive and Unlabeled Data |
Authors | Masahiro Kato, Liyuan Xu, Gang Niu, Masashi Sugiyama |
Abstract | We consider a problem of learning a binary classifier only from positive data and unlabeled data (PU learning) and estimating the class-prior in unlabeled data under the case-control scenario. Most of the recent methods of PU learning require an estimate of the class-prior probability in unlabeled data, and it is estimated in advance with another method. However, such a two-step approach which first estimates the class prior and then trains a classifier may not be the optimal approach since the estimation error of the class-prior is not taken into account when a classifier is trained. In this paper, we propose a novel unified approach to estimating the class-prior and training a classifier alternately. Our proposed method is simple to implement and computationally efficient. Through experiments, we demonstrate the practical usefulness of the proposed method. |
Tasks | |
Published | 2018-09-15 |
URL | http://arxiv.org/abs/1809.05710v1 |
http://arxiv.org/pdf/1809.05710v1.pdf | |
PWC | https://paperswithcode.com/paper/alternate-estimation-of-a-classifier-and-the |
Repo | |
Framework | |
Learning Depth from Single Images with Deep Neural Network Embedding Focal Length
Title | Learning Depth from Single Images with Deep Neural Network Embedding Focal Length |
Authors | Lei He, Guanghui Wang, Zhanyi Hu |
Abstract | Learning depth from a single image, as an important issue in scene understanding, has attracted a lot of attention in the past decade. The accuracy of the depth estimation has been improved from conditional Markov random fields, non-parametric methods, to deep convolutional neural networks most recently. However, there exist inherent ambiguities in recovering 3D from a single 2D image. In this paper, we first prove the ambiguity between the focal length and monocular depth learning, and verify the result using experiments, showing that the focal length has a great influence on accurate depth recovery. In order to learn monocular depth by embedding the focal length, we propose a method to generate synthetic varying-focal-length dataset from fixed-focal-length datasets, and a simple and effective method is implemented to fill the holes in the newly generated images. For the sake of accurate depth recovery, we propose a novel deep neural network to infer depth through effectively fusing the middle-level information on the fixed-focal-length dataset, which outperforms the state-of-the-art methods built on pre-trained VGG. Furthermore, the newly generated varying-focal-length dataset is taken as input to the proposed network in both learning and inference phases. Extensive experiments on the fixed- and varying-focal-length datasets demonstrate that the learned monocular depth with embedded focal length is significantly improved compared to that without embedding the focal length information. |
Tasks | Depth Estimation, Network Embedding, Scene Understanding |
Published | 2018-03-27 |
URL | http://arxiv.org/abs/1803.10039v1 |
http://arxiv.org/pdf/1803.10039v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-depth-from-single-images-with-deep |
Repo | |
Framework | |
AAANE: Attention-based Adversarial Autoencoder for Multi-scale Network Embedding
Title | AAANE: Attention-based Adversarial Autoencoder for Multi-scale Network Embedding |
Authors | Lei Sang, Min Xu, Shengsheng Qian, Xindong Wu |
Abstract | Network embedding represents nodes in a continuous vector space and preserves structure information from the Network. Existing methods usually adopt a “one-size-fits-all” approach when concerning multi-scale structure information, such as first- and second-order proximity of nodes, ignoring the fact that different scales play different roles in the embedding learning. In this paper, we propose an Attention-based Adversarial Autoencoder Network Embedding(AAANE) framework, which promotes the collaboration of different scales and lets them vote for robust representations. The proposed AAANE consists of two components: 1) Attention-based autoencoder effectively capture the highly non-linear network structure, which can de-emphasize irrelevant scales during training. 2) An adversarial regularization guides the autoencoder learn robust representations by matching the posterior distribution of the latent embeddings to given prior distribution. This is the first attempt to introduce attention mechanisms to multi-scale network embedding. Experimental results on real-world networks show that our learned attention parameters are different for every network and the proposed approach outperforms existing state-of-the-art approaches for network embedding. |
Tasks | Network Embedding |
Published | 2018-03-24 |
URL | http://arxiv.org/abs/1803.09080v1 |
http://arxiv.org/pdf/1803.09080v1.pdf | |
PWC | https://paperswithcode.com/paper/aaane-attention-based-adversarial-autoencoder |
Repo | |
Framework | |
Data Augmentation for Detection of Architectural Distortion in Digital Mammography using Deep Learning Approach
Title | Data Augmentation for Detection of Architectural Distortion in Digital Mammography using Deep Learning Approach |
Authors | Arthur C. Costa, Helder C. R. Oliveira, Juliana H. Catani, Nestor de Barros, Carlos F. E. Melo, Marcelo A. C. Vieira |
Abstract | Early detection of breast cancer can increase treatment efficiency. Architectural Distortion (AD) is a very subtle contraction of the breast tissue and may represent the earliest sign of cancer. Since it is very likely to be unnoticed by radiologists, several approaches have been proposed over the years but none using deep learning techniques. To train a Convolutional Neural Network (CNN), which is a deep neural architecture, is necessary a huge amount of data. To overcome this problem, this paper proposes a data augmentation approach applied to clinical image dataset to properly train a CNN. Results using receiver operating characteristic analysis showed that with a very limited dataset we could train a CNN to detect AD in digital mammography with area under the curve (AUC = 0.74). |
Tasks | Data Augmentation |
Published | 2018-07-06 |
URL | http://arxiv.org/abs/1807.03167v1 |
http://arxiv.org/pdf/1807.03167v1.pdf | |
PWC | https://paperswithcode.com/paper/data-augmentation-for-detection-of |
Repo | |
Framework | |
Leapfrogging for parallelism in deep neural networks
Title | Leapfrogging for parallelism in deep neural networks |
Authors | Yatin Saraiya |
Abstract | We present a technique, which we term leapfrogging, to parallelize back- propagation in deep neural networks. We show that this technique yields a savings of $1-1/k$ of a dominant term in backpropagation, where k is the number of threads (or gpus). |
Tasks | |
Published | 2018-01-15 |
URL | http://arxiv.org/abs/1801.04928v1 |
http://arxiv.org/pdf/1801.04928v1.pdf | |
PWC | https://paperswithcode.com/paper/leapfrogging-for-parallelism-in-deep-neural |
Repo | |
Framework | |
Understanding Compressive Adversarial Privacy
Title | Understanding Compressive Adversarial Privacy |
Authors | Xiao Chen, Peter Kairouz, Ram Rajagopal |
Abstract | Designing a data sharing mechanism without sacrificing too much privacy can be considered as a game between data holders and malicious attackers. This paper describes a compressive adversarial privacy framework that captures the trade-off between the data privacy and utility. We characterize the optimal data releasing mechanism through convex optimization when assuming that both the data holder and attacker can only modify the data using linear transformations. We then build a more realistic data releasing mechanism that can rely on a nonlinear compression model while the attacker uses a neural network. We demonstrate in a series of empirical applications that this framework, consisting of compressive adversarial privacy, can preserve sensitive information. |
Tasks | |
Published | 2018-09-21 |
URL | http://arxiv.org/abs/1809.08911v2 |
http://arxiv.org/pdf/1809.08911v2.pdf | |
PWC | https://paperswithcode.com/paper/understanding-compressive-adversarial-privacy |
Repo | |
Framework | |
Logically-Constrained Neural Fitted Q-Iteration
Title | Logically-Constrained Neural Fitted Q-Iteration |
Authors | Mohammadhosein Hasanbeig, Alessandro Abate, Daniel Kroening |
Abstract | We propose a method for efficient training of Q-functions for continuous-state Markov Decision Processes (MDPs) such that the traces of the resulting policies satisfy a given Linear Temporal Logic (LTL) property. LTL, a modal logic, can express a wide range of time-dependent logical properties (including “safety”) that are quite similar to patterns in natural language. We convert the LTL property into a limit deterministic Buchi automaton and construct an on-the-fly synchronised product MDP. The control policy is then synthesised by defining an adaptive reward function and by applying a modified neural fitted Q-iteration algorithm to the synchronised structure, assuming that no prior knowledge is available from the original MDP. The proposed method is evaluated in a numerical study to test the quality of the generated control policy and is compared with conventional methods for policy synthesis such as MDP abstraction (Voronoi quantizer) and approximate dynamic programming (fitted value iteration). |
Tasks | |
Published | 2018-09-20 |
URL | http://arxiv.org/abs/1809.07823v4 |
http://arxiv.org/pdf/1809.07823v4.pdf | |
PWC | https://paperswithcode.com/paper/logically-constrained-neural-fitted-q |
Repo | |
Framework | |
Private Selection from Private Candidates
Title | Private Selection from Private Candidates |
Authors | Jingcheng Liu, Kunal Talwar |
Abstract | Differentially Private algorithms often need to select the best amongst many candidate options. Classical works on this selection problem require that the candidates’ goodness, measured as a real-valued score function, does not change by much when one person’s data changes. In many applications such as hyperparameter optimization, this stability assumption is much too strong. In this work, we consider the selection problem under a much weaker stability assumption on the candidates, namely that the score functions are differentially private. Under this assumption, we present algorithms that are near-optimal along the three relevant dimensions: privacy, utility and computational efficiency. Our result can be seen as a generalization of the exponential mechanism and its existing generalizations. We also develop an online version of our algorithm, that can be seen as a generalization of the sparse vector technique to this weaker stability assumption. We show how our results imply better algorithms for hyperparameter selection in differentially private machine learning, as well as for adaptive data analysis. |
Tasks | Hyperparameter Optimization |
Published | 2018-11-19 |
URL | http://arxiv.org/abs/1811.07971v1 |
http://arxiv.org/pdf/1811.07971v1.pdf | |
PWC | https://paperswithcode.com/paper/private-selection-from-private-candidates |
Repo | |
Framework | |
Shielding Google’s language toxicity model against adversarial attacks
Title | Shielding Google’s language toxicity model against adversarial attacks |
Authors | Nestor Rodriguez, Sergio Rojas-Galeano |
Abstract | Lack of moderation in online communities enables participants to incur in personal aggression, harassment or cyberbullying, issues that have been accentuated by extremist radicalisation in the contemporary post-truth politics scenario. This kind of hostility is usually expressed by means of toxic language, profanity or abusive statements. Recently Google has developed a machine-learning-based toxicity model in an attempt to assess the hostility of a comment; unfortunately, it has been suggested that said model can be deceived by adversarial attacks that manipulate the text sequence of the comment. In this paper we firstly characterise such adversarial attacks as using obfuscation and polarity transformations. The former deceives by corrupting toxic trigger content with typographic edits, whereas the latter deceives by grammatical negation of the toxic content. Then, we propose a two–stage approach to counter–attack these anomalies, bulding upon a recently proposed text deobfuscation method and the toxicity scoring model. Lastly, we conducted an experiment with approximately 24000 distorted comments, showing how in this way it is feasible to restore toxicity of the adversarial variants, while incurring roughly on a twofold increase in processing time. Even though novel adversary challenges would keep coming up derived from the versatile nature of written language, we anticipate that techniques combining machine learning and text pattern recognition methods, each one targeting different layers of linguistic features, would be needed to achieve robust detection of toxic language, thus fostering aggression–free digital interaction. |
Tasks | |
Published | 2018-01-05 |
URL | http://arxiv.org/abs/1801.01828v1 |
http://arxiv.org/pdf/1801.01828v1.pdf | |
PWC | https://paperswithcode.com/paper/shielding-googles-language-toxicity-model |
Repo | |
Framework | |
From Adaptive Kernel Density Estimation to Sparse Mixture Models
Title | From Adaptive Kernel Density Estimation to Sparse Mixture Models |
Authors | Colas Schretter, Jianyong Sun, Peter Schelkens |
Abstract | We introduce a balloon estimator in a generalized expectation-maximization method for estimating all parameters of a Gaussian mixture model given one data sample per mixture component. Instead of limiting explicitly the model size, this regularization strategy yields low-complexity sparse models where the number of effective mixture components reduces with an increase of a smoothing probability parameter $\mathbf{P>0}$. This semi-parametric method bridges from non-parametric adaptive kernel density estimation (KDE) to parametric ordinary least-squares when $\mathbf{P=1}$. Experiments show that simpler sparse mixture models retain the level of details present in the adaptive KDE solution. |
Tasks | Density Estimation |
Published | 2018-12-11 |
URL | http://arxiv.org/abs/1812.04397v1 |
http://arxiv.org/pdf/1812.04397v1.pdf | |
PWC | https://paperswithcode.com/paper/from-adaptive-kernel-density-estimation-to |
Repo | |
Framework | |
Face-Focused Cross-Stream Network for Deception Detection in Videos
Title | Face-Focused Cross-Stream Network for Deception Detection in Videos |
Authors | Mingyu Ding, An Zhao, Zhiwu Lu, Tao Xiang, Ji-Rong Wen |
Abstract | Automated deception detection (ADD) from real-life videos is a challenging task. It specifically needs to address two problems: (1) Both face and body contain useful cues regarding whether a subject is deceptive. How to effectively fuse the two is thus key to the effectiveness of an ADD model. (2) Real-life deceptive samples are hard to collect; learning with limited training data thus challenges most deep learning based ADD models. In this work, both problems are addressed. Specifically, for face-body multimodal learning, a novel face-focused cross-stream network (FFCSN) is proposed. It differs significantly from the popular two-stream networks in that: (a) face detection is added into the spatial stream to capture the facial expressions explicitly, and (b) correlation learning is performed across the spatial and temporal streams for joint deep feature learning across both face and body. To address the training data scarcity problem, our FFCSN model is trained with both meta learning and adversarial learning. Extensive experiments show that our FFCSN model achieves state-of-the-art results. Further, the proposed FFCSN model as well as its robust training strategy are shown to be generally applicable to other human-centric video analysis tasks such as emotion recognition from user-generated videos. |
Tasks | Deception Detection, Deception Detection In Videos, Emotion Recognition, Face Detection, Meta-Learning |
Published | 2018-12-11 |
URL | http://arxiv.org/abs/1812.04429v1 |
http://arxiv.org/pdf/1812.04429v1.pdf | |
PWC | https://paperswithcode.com/paper/face-focused-cross-stream-network-for |
Repo | |
Framework | |
Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control
Title | Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control |
Authors | Rhiannon Michelmore, Marta Kwiatkowska, Yarin Gal |
Abstract | A rise in popularity of Deep Neural Networks (DNNs), attributed to more powerful GPUs and widely available datasets, has seen them being increasingly used within safety-critical domains. One such domain, self-driving, has benefited from significant performance improvements, with millions of miles having been driven with no human intervention. Despite this, crashes and erroneous behaviours still occur, in part due to the complexity of verifying the correctness of DNNs and a lack of safety guarantees. In this paper, we demonstrate how quantitative measures of uncertainty can be extracted in real-time, and their quality evaluated in end-to-end controllers for self-driving cars. To this end we utilise a recent method for gathering approximate uncertainty information from DNNs without changing the network’s architecture. We propose evaluation techniques for the uncertainty on two separate architectures which use the uncertainty to predict crashes up to five seconds in advance. We find that mutual information, a measure of uncertainty in classification networks, is a promising indicator of forthcoming crashes. |
Tasks | Autonomous Driving, Self-Driving Cars |
Published | 2018-11-16 |
URL | http://arxiv.org/abs/1811.06817v1 |
http://arxiv.org/pdf/1811.06817v1.pdf | |
PWC | https://paperswithcode.com/paper/evaluating-uncertainty-quantification-in-end |
Repo | |
Framework | |
Adversarial Perturbation Intensity Achieving Chosen Intra-Technique Transferability Level for Logistic Regression
Title | Adversarial Perturbation Intensity Achieving Chosen Intra-Technique Transferability Level for Logistic Regression |
Authors | Martin Gubri |
Abstract | Machine Learning models have been shown to be vulnerable to adversarial examples, ie. the manipulation of data by a attacker to defeat a defender’s classifier at test time. We present a novel probabilistic definition of adversarial examples in perfect or limited knowledge setting using prior probability distributions on the defender’s classifier. Using the asymptotic properties of the logistic regression, we derive a closed-form expression of the intensity of any adversarial perturbation, in order to achieve a given expected misclassification rate. This technique is relevant in a threat model of known model specifications and unknown training data. To our knowledge, this is the first method that allows an attacker to directly choose the probability of attack success. We evaluate our approach on two real-world datasets. |
Tasks | |
Published | 2018-01-06 |
URL | http://arxiv.org/abs/1801.01953v1 |
http://arxiv.org/pdf/1801.01953v1.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-perturbation-intensity-achieving |
Repo | |
Framework | |
A Comparative Study of Fruit Detection and Counting Methods for Yield Mapping in Apple Orchards
Title | A Comparative Study of Fruit Detection and Counting Methods for Yield Mapping in Apple Orchards |
Authors | Nicolai Häni, Pravakar Roy, Volkan Isler |
Abstract | We present new methods for apple detection and counting based on recent deep learning approaches and compare them with state-of-the-art results based on classical methods. Our goal is to quantify performance improvements by neural network-based methods compared to methods based on classical approaches. Additionally, we introduce a complete system for counting apples in an entire row. This task is challenging as it requires tracking fruits in images from both sides of the row. We evaluate the performances of three fruit detection methods and two fruit counting methods on six datasets. Results indicate that the classical detection approach still outperforms the deep learning based methods in the majority of the datasets. For fruit counting though, the deep learning based approach performs better for all of the datasets. Combining the classical detection method together with the neural network based counting approach, we achieve remarkable yield accuracies ranging from 95.56% to 97.83%. |
Tasks | Yield Mapping In Apple Orchards |
Published | 2018-10-22 |
URL | http://arxiv.org/abs/1810.09499v2 |
http://arxiv.org/pdf/1810.09499v2.pdf | |
PWC | https://paperswithcode.com/paper/a-comparative-study-of-fruit-detection-and |
Repo | |
Framework | |