Paper Group ANR 1548
WhiteNet: Phishing Website Detection by Visual Whitelists. Graph Neural Networks with Generated Parameters for Relation Extraction. Image-Guided Depth Sampling and Reconstruction. Proper-Composite Loss Functions in Arbitrary Dimensions. Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning. An Exact Refo …
WhiteNet: Phishing Website Detection by Visual Whitelists
| Title | WhiteNet: Phishing Website Detection by Visual Whitelists |
| Authors | Sahar Abdelnabi, Katharina Krombholz, Mario Fritz |
| Abstract | Phishing websites are still a major threat in today’s Internet ecosystem. Despite numerous previous efforts, black and white listing methods do not offer sufficient protection - in particular against zero-day phishing attacks. This paper contributes WhiteNet, a new similarity-based phishing detection framework, based on a triplet network with three shared Convolutional Neural Networks (CNNs). WhiteNet learns profiles for websites in order to detect zero-day phishing websites by a “visual whitelist”. We furthermore present WhitePhish, the largest dataset to date that facilitates visual phishing detection in an ecologically valid manner. We show that our method outperforms the state-of-the-art by a large margin while being robust against a range of evasion attacks. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://arxiv.org/abs/1909.00300v2 |
| https://arxiv.org/pdf/1909.00300v2.pdf | |
| PWC | https://paperswithcode.com/paper/whitenet-phishing-website-detection-by-visual |
| Repo | |
| Framework | |
Graph Neural Networks with Generated Parameters for Relation Extraction
| Title | Graph Neural Networks with Generated Parameters for Relation Extraction |
| Authors | Hao Zhu, Yankai Lin, Zhiyuan Liu, Jie Fu, Tat-seng Chua, Maosong Sun |
| Abstract | Recently, progress has been made towards improving relational reasoning in machine learning field. Among existing models, graph neural networks (GNNs) is one of the most effective approaches for multi-hop relational reasoning. In fact, multi-hop relational reasoning is indispensable in many natural language processing tasks such as relation extraction. In this paper, we propose to generate the parameters of graph neural networks (GP-GNNs) according to natural language sentences, which enables GNNs to process relational reasoning on unstructured text inputs. We verify GP-GNNs in relation extraction from text. Experimental results on a human-annotated dataset and two distantly supervised datasets show that our model achieves significant improvements compared to baselines. We also perform a qualitative analysis to demonstrate that our model could discover more accurate relations by multi-hop relational reasoning. |
| Tasks | Relational Reasoning, Relation Extraction |
| Published | 2019-02-02 |
| URL | http://arxiv.org/abs/1902.00756v1 |
| http://arxiv.org/pdf/1902.00756v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-neural-networks-with-generated |
| Repo | |
| Framework | |
Image-Guided Depth Sampling and Reconstruction
| Title | Image-Guided Depth Sampling and Reconstruction |
| Authors | Adam Wolff, Shachar Praisler, Ilya Tcenov, Guy Gilboa |
| Abstract | Depth acquisition, based on active illumination, is essential for autonomous and robotic navigation. LiDARs (Light Detection And Ranging) with mechanical, fixed, sampling templates are commonly used in today’s autonomous vehicles. An emerging technology, based on solid-state depth sensors, with no mechanical parts, allows fast, adaptive, programmable scans. In this paper, we investigate the topic of adaptive, image-driven, sampling and reconstruction strategies. First, we formulate a piece-wise linear depth model with several tolerance parameters and estimate its validity for indoor and outdoor scenes. Our model and experiments predict that, in the optimal case, about 20-60 piece-wise linear structures can approximate well a depth map. This translates to a depth-to-image sampling ratio of about 1/1200. We propose a simple, generic, sampling and reconstruction algorithm, based on super-pixels. We reach a sampling rate which is still far from the optimal case. However, our sampling improves grid and random sampling, consistently, for a wide variety of reconstruction methods. Moreover, our proposed reconstruction achieves state-of-the-art results, compared to image-guided depth completion algorithms, reducing the required sampling rate by a factor of 3-4. A single-pixel depth camera built in our lab illustrates the concept. |
| Tasks | Autonomous Vehicles, Depth Completion |
| Published | 2019-08-04 |
| URL | https://arxiv.org/abs/1908.01379v1 |
| https://arxiv.org/pdf/1908.01379v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-guided-depth-sampling-and |
| Repo | |
| Framework | |
Proper-Composite Loss Functions in Arbitrary Dimensions
| Title | Proper-Composite Loss Functions in Arbitrary Dimensions |
| Authors | Zac Cranko, Robert C. Williamson, Richard Nock |
| Abstract | The study of a machine learning problem is in many ways is difficult to separate from the study of the loss function being used. One avenue of inquiry has been to look at these loss functions in terms of their properties as scoring rules via the proper-composite representation, in which predictions are mapped to probability distributions which are then scored via a scoring rule. However, recent research so far has primarily been concerned with analysing the (typically) finite-dimensional conditional risk problem on the output space, leaving aside the larger total risk minimisation. We generalise a number of these results to an infinite dimensional setting and in doing so we are able to exploit the familial resemblance of density and conditional density estimation to provide a simple characterisation of the canonical link. |
| Tasks | Density Estimation |
| Published | 2019-02-19 |
| URL | https://arxiv.org/abs/1902.06881v2 |
| https://arxiv.org/pdf/1902.06881v2.pdf | |
| PWC | https://paperswithcode.com/paper/proper-composite-loss-functions-in-arbitrary |
| Repo | |
| Framework | |
Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning
| Title | Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning |
| Authors | Tianyu Li, Bogdan Mazoure, Doina Precup, Guillaume Rabusseau |
| Abstract | Learning and planning in partially-observable domains is one of the most difficult problems in reinforcement learning. Traditional methods consider these two problems as independent, resulting in a classical two-stage paradigm: first learn the environment dynamics and then plan accordingly. This approach, however, disconnects the two problems and can consequently lead to algorithms that are sample inefficient and time consuming. In this paper, we propose a novel algorithm that combines learning and planning together. Our algorithm is closely related to the spectral learning algorithm for predicitive state representations and offers appealing theoretical guarantees and time complexity. We empirically show on two domains that our approach is more sample and time efficient compared to classical methods. |
| Tasks | |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.05010v2 |
| https://arxiv.org/pdf/1911.05010v2.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-planning-under-partial |
| Repo | |
| Framework | |
An Exact Reformulation of Feature-Vector-based Radial-Basis-Function Networks for Graph-based Observations
| Title | An Exact Reformulation of Feature-Vector-based Radial-Basis-Function Networks for Graph-based Observations |
| Authors | Isaac J. Sledge, Jose C. Principe |
| Abstract | Radial-basis-function networks are traditionally defined for sets of vector-based observations. In this short paper, we reformulate such networks so that they can be applied to adjacency-matrix representations of weighted, directed graphs that represent the relationships between object pairs. We re-state the sum-of-squares objective function so that it is purely dependent on entries from the adjacency matrix. From this objective function, we derive a gradient descent update for the network weights. We also derive a gradient update that simulates the repositioning of the radial basis prototypes and changes in the radial basis prototype parameters. An important property of our radial basis function networks is that they are guaranteed to yield the same responses as conventional radial-basis networks trained on a corresponding vector realization of the relationships encoded by the adjacency-matrix. Such a vector realization only needs to provably exist for this property to hold, which occurs whenever the relationships correspond to distances from some arbitrary metric applied to a latent set of vectors. We therefore completely avoid needing to actually construct vectorial realizations via multi-dimensional scaling, which ensures that the underlying relationships are totally preserved. |
| Tasks | |
| Published | 2019-01-22 |
| URL | https://arxiv.org/abs/1901.07484v2 |
| https://arxiv.org/pdf/1901.07484v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-exact-reformulation-of-feature-vector |
| Repo | |
| Framework | |
Functional Transparency for Structured Data: a Game-Theoretic Approach
| Title | Functional Transparency for Structured Data: a Game-Theoretic Approach |
| Authors | Guang-He Lee, Wengong Jin, David Alvarez-Melis, Tommi S. Jaakkola |
| Abstract | We provide a new approach to training neural models to exhibit transparency in a well-defined, functional manner. Our approach naturally operates over structured data and tailors the predictor, functionally, towards a chosen family of (local) witnesses. The estimation problem is setup as a co-operative game between an unrestricted predictor such as a neural network, and a set of witnesses chosen from the desired transparent family. The goal of the witnesses is to highlight, locally, how well the predictor conforms to the chosen family of functions, while the predictor is trained to minimize the highlighted discrepancy. We emphasize that the predictor remains globally powerful as it is only encouraged to agree locally with locally adapted witnesses. We analyze the effect of the proposed approach, provide example formulations in the context of deep graph and sequence models, and empirically illustrate the idea in chemical property prediction, temporal modeling, and molecule representation learning. |
| Tasks | Representation Learning |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1902.09737v1 |
| http://arxiv.org/pdf/1902.09737v1.pdf | |
| PWC | https://paperswithcode.com/paper/functional-transparency-for-structured-data-a |
| Repo | |
| Framework | |
Applying Transfer Learning To Deep Learned Models For EEG Analysis
| Title | Applying Transfer Learning To Deep Learned Models For EEG Analysis |
| Authors | Axel Uran, Coert van Gemeren, Rosanne van Diepen, Ricardo Chavarriaga, José del R. Millán |
| Abstract | The introduction of deep learning and transfer learning techniques in fields such as computer vision allowed a leap forward in the accuracy of image classification tasks. Currently there is only limited use of such techniques in neuroscience. The challenge of using deep learning methods to successfully train models in neuroscience, lies in the complexity of the information that is processed, the availability of data and the cost of producing sufficient high quality annotations. Inspired by its application in computer vision, we introduce transfer learning on electrophysiological data to enable training a model with limited amounts of data. Our method was tested on the dataset of the BCI competition IV 2a and compared to the top results that were obtained using traditional machine learning techniques. Using our DL model we outperform the top result of the competition by 33%. We also explore transferability of knowledge between trained models over different experiments, called inter-experimental transfer learning. This reduces the amount of required data even further and is especially useful when few subjects are available. This method is able to outperform the standard deep learning methods used in the BCI competition IV 2b approaches by 18%. In this project we propose a method that can produce reliable electroencephalography (EEG) signal classification, based on modest amounts of training data through the use of transfer learning. |
| Tasks | EEG, Image Classification, Transfer Learning |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01332v1 |
| https://arxiv.org/pdf/1907.01332v1.pdf | |
| PWC | https://paperswithcode.com/paper/applying-transfer-learning-to-deep-learned |
| Repo | |
| Framework | |
Hybrid NER System for Multi-Source Offer Feeds
| Title | Hybrid NER System for Multi-Source Offer Feeds |
| Authors | Anusha Holla, Bharat Gaind, Vikas Reddy Katta, Abhishek Kundu, S Kamalesh |
| Abstract | Data available across the web is largely unstructured. Offers published by multiple sources like banks, digital wallets, merchants, etc., are one of the most accessed advertising data in today’s world. This data gets accessed by millions of people on a daily basis and is easily interpreted by humans, but since it is largely unstructured and diverse, using an algorithmic way to extract meaningful information out of these offers is hard. Identifying the essential offer entities (for instance, its amount, the product on which the offer is applicable, the merchant providing the offer, etc.) from these offers plays a vital role in targeting the right customers to improve sales. This work presents and evaluates various existing Named Entity Recognizer (NER) models which can identify the required entities from offer feeds. We also propose a novel Hybrid NER model constructed by two-level stacking of Conditional Random Field, Bidirectional LSTM and Spacy models at the first level and an SVM classifier at the second. The proposed hybrid model has been tested on offer feeds collected from multiple sources and has shown better performance in the offer domain when compared to the existing models. |
| Tasks | |
| Published | 2019-01-24 |
| URL | https://arxiv.org/abs/1901.08406v2 |
| https://arxiv.org/pdf/1901.08406v2.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-ner-system-for-multi-source-offer |
| Repo | |
| Framework | |
A Neural Architecture for Designing Truthful and Efficient Auctions
| Title | A Neural Architecture for Designing Truthful and Efficient Auctions |
| Authors | Andrea Tacchetti, DJ Strouse, Marta Garnelo, Thore Graepel, Yoram Bachrach |
| Abstract | Auctions are protocols to allocate goods to buyers who have preferences over them, and collect payments in return. Economists have invested significant effort in designing auction rules that result in allocations of the goods that are desirable for the group as a whole. However, for settings where participants’ valuations of the items on sale are their private information, the rules of the auction must deter buyers from misreporting their preferences, so as to maximize their own utility, since misreported preferences hinder the ability for the auctioneer to allocate goods to those who want them most. Manual auction design has yielded excellent mechanisms for specific settings, but requires significant effort when tackling new domains. We propose a deep learning based approach to automatically design auctions in a wide variety of domains, shifting the design work from human to machine. We assume that participants’ valuations for the items for sale are independently sampled from an unknown but fixed distribution. Our system receives a data-set consisting of such valuation samples, and outputs an auction rule encoding the desired incentive structure. We focus on producing truthful and efficient auctions that minimize the economic burden on participants. We evaluate the auctions designed by our framework on well-studied domains, such as multi-unit and combinatorial auctions, showing that they outperform known auction designs in terms of the economic burden placed on participants. |
| Tasks | |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05181v1 |
| https://arxiv.org/pdf/1907.05181v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-neural-architecture-for-designing-truthful |
| Repo | |
| Framework | |
Bayesian Nonparametric Adaptive Spectral Density Estimation for Financial Time Series
| Title | Bayesian Nonparametric Adaptive Spectral Density Estimation for Financial Time Series |
| Authors | Nick James, Roman Marchant, Richard Gerlach, Sally Cripps |
| Abstract | Discrimination between non-stationarity and long-range dependency is a difficult and long-standing issue in modelling financial time series. This paper uses an adaptive spectral technique which jointly models the non-stationarity and dependency of financial time series in a non-parametric fashion assuming that the time series consists of a finite, but unknown number, of locally stationary processes, the locations of which are also unknown. The model allows a non-parametric estimate of the dependency structure by modelling the auto-covariance function in the spectral domain. All our estimates are made within a Bayesian framework where we use aReversible Jump Markov Chain Monte Carlo algorithm for inference. We study the frequentist properties of our estimates via a simulation study, and present a novel way of generating time series data from a nonparametric spectrum. Results indicate that our techniques perform well across a range of data generating processes. We apply our method to a number of real examples and our results indicate that several financial time series exhibit both long-range dependency and non-stationarity. |
| Tasks | Density Estimation, Time Series |
| Published | 2019-02-09 |
| URL | http://arxiv.org/abs/1902.03350v1 |
| http://arxiv.org/pdf/1902.03350v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-nonparametric-adaptive-spectral |
| Repo | |
| Framework | |
Analogy-Based Preference Learning with Kernels
| Title | Analogy-Based Preference Learning with Kernels |
| Authors | Mohsen Ahmadi Fahandar, Eyke Hüllermeier |
| Abstract | Building on a specific formalization of analogical relationships of the form “A relates to B as C relates to D”, we establish a connection between two important subfields of artificial intelligence, namely analogical reasoning and kernel-based machine learning. More specifically, we show that so-called analogical proportions are closely connected to kernel functions on pairs of objects. Based on this result, we introduce the analogy kernel, which can be seen as a measure of how strongly four objects are in analogical relationship. As an application, we consider the problem of object ranking in the realm of preference learning, for which we develop a new method based on support vector machines trained with the analogy kernel. Our first experimental results for data sets from different domains (sports, education, tourism, etc.) are promising and suggest that our approach is competitive to state-of-the-art algorithms in terms of predictive accuracy. |
| Tasks | |
| Published | 2019-01-07 |
| URL | http://arxiv.org/abs/1901.02001v1 |
| http://arxiv.org/pdf/1901.02001v1.pdf | |
| PWC | https://paperswithcode.com/paper/analogy-based-preference-learning-with |
| Repo | |
| Framework | |
VoronoiNet: General Functional Approximators with Local Support
| Title | VoronoiNet: General Functional Approximators with Local Support |
| Authors | Francis Williams, Daniele Panozzo, Kwang Moo Yi, Andrea Tagliasacchi |
| Abstract | Voronoi diagrams are highly compact representations that are used in various Graphics applications. In this work, we show how to embed a differentiable version of it – via a novel deep architecture – into a generative deep network. By doing so, we achieve a highly compact latent embedding that is able to provide much more detailed reconstructions, both in 2D and 3D, for various shapes. In this tech report, we introduce our representation and present a set of preliminary results comparing it with recently proposed implicit occupancy networks. |
| Tasks | |
| Published | 2019-12-08 |
| URL | https://arxiv.org/abs/1912.03629v1 |
| https://arxiv.org/pdf/1912.03629v1.pdf | |
| PWC | https://paperswithcode.com/paper/voronoinet-general-functional-approximators |
| Repo | |
| Framework | |
The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentation
| Title | The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentation |
| Authors | Robin Chan, Matthias Rottmann, Radin Dardashti, Fabian Hüger, Peter Schlicht, Hanno Gottschalk |
| Abstract | Neural networks for semantic segmentation can be seen as statistical models that provide for each pixel of one image a probability distribution on predefined classes. The predicted class is then usually obtained by the maximum a-posteriori probability (MAP) which is known as Bayes rule in decision theory. From decision theory we also know that the Bayes rule is optimal regarding the simple symmetric cost function. Therefore, it weights each type of confusion between two different classes equally, e.g., given images of urban street scenes there is no distinction in the cost function if the network confuses a person with a street or a building with a tree. Intuitively, there might be confusions of classes that are more important to avoid than others. In this work, we want to raise awareness of the possibility of explicitly defining confusion costs and the associated ethical difficulties if it comes down to providing numbers. We define two cost functions from different extreme perspectives, an egoistic and an altruistic one, and show how safety relevant quantities like precision / recall and (segment-wise) false positive / negative rate change when interpolating between MAP, egoistic and altruistic decision rules. |
| Tasks | Semantic Segmentation |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01342v1 |
| https://arxiv.org/pdf/1907.01342v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-ethical-dilemma-when-not-setting-up-cost |
| Repo | |
| Framework | |
Exploiting SIFT Descriptor for Rotation Invariant Convolutional Neural Network
| Title | Exploiting SIFT Descriptor for Rotation Invariant Convolutional Neural Network |
| Authors | Abhay Kumar, Nishant Jain, Chirag Singh, Suraj Tripathi |
| Abstract | This paper presents a novel approach to exploit the distinctive invariant features in convolutional neural network. The proposed CNN model uses Scale Invariant Feature Transform (SIFT) descriptor instead of the max-pooling layer. Max-pooling layer discards the pose, i.e., translational and rotational relationship between the low-level features, and hence unable to capture the spatial hierarchies between low and high level features. The SIFT descriptor layer captures the orientation and the spatial relationship of the features extracted by convolutional layer. The proposed SIFT Descriptor CNN therefore combines the feature extraction capabilities of CNN model and rotation invariance of SIFT descriptor. Experimental results on the MNIST and fashionMNIST datasets indicates reasonable improvements over conventional methods available in literature. |
| Tasks | |
| Published | 2019-03-30 |
| URL | http://arxiv.org/abs/1904.00197v1 |
| http://arxiv.org/pdf/1904.00197v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-sift-descriptor-for-rotation |
| Repo | |
| Framework | |
