Paper Group AWR 316
Computation of optimal transport and related hedging problems via penalization and neural networks. Robust Neural Malware Detection Models for Emulation Sequence Learning. SqueezeFit: Label-aware dimensionality reduction by semidefinite programming. Cloud Detection From RGB Color Remote Sensing Images With Deep Pyramid Networks. Community Regulariz …
Computation of optimal transport and related hedging problems via penalization and neural networks
Title | Computation of optimal transport and related hedging problems via penalization and neural networks |
Authors | Stephan Eckstein, Michael Kupper |
Abstract | This paper presents a widely applicable approach to solving (multi-marginal, martingale) optimal transport and related problems via neural networks. The core idea is to penalize the optimization problem in its dual formulation and reduce it to a finite dimensional one which corresponds to optimizing a neural network with smooth objective function. We present numerical examples from optimal transport, martingale optimal transport, portfolio optimization under uncertainty and generative adversarial networks that showcase the generality and effectiveness of the approach. |
Tasks | Portfolio Optimization |
Published | 2018-02-23 |
URL | http://arxiv.org/abs/1802.08539v2 |
http://arxiv.org/pdf/1802.08539v2.pdf | |
PWC | https://paperswithcode.com/paper/computation-of-optimal-transport-and-related |
Repo | https://github.com/stephaneckstein/transport-and-related |
Framework | tf |
Robust Neural Malware Detection Models for Emulation Sequence Learning
Title | Robust Neural Malware Detection Models for Emulation Sequence Learning |
Authors | Rakshit Agrawal, Jack W. Stokes, Mady Marinescu, Karthik Selvaraj |
Abstract | Malicious software, or malware, presents a continuously evolving challenge in computer security. These embedded snippets of code in the form of malicious files or hidden within legitimate files cause a major risk to systems with their ability to run malicious command sequences. Malware authors even use polymorphism to reorder these commands and create several malicious variations. However, if executed in a secure environment, one can perform early malware detection on emulated command sequences. The models presented in this paper leverage this sequential data derived via emulation in order to perform Neural Malware Detection. These models target the core of the malicious operation by learning the presence and pattern of co-occurrence of malicious event actions from within these sequences. Our models can capture entire event sequences and be trained directly using the known target labels. These end-to-end learning models are powered by two commonly used structures - Long Short-Term Memory (LSTM) Networks and Convolutional Neural Networks (CNNs). Previously proposed sequential malware classification models process no more than 200 events. Attackers can evade detection by delaying any malicious activity beyond the beginning of the file. We present specialized models that can handle extremely long sequences while successfully performing malware detection in an efficient way. We present an implementation of the Convoluted Partitioning of Long Sequences approach in order to tackle this vulnerability and operate on long sequences. We present our results on a large dataset consisting of 634,249 file sequences, with extremely long file sequences. |
Tasks | Malware Classification, Malware Detection |
Published | 2018-06-28 |
URL | http://arxiv.org/abs/1806.10741v1 |
http://arxiv.org/pdf/1806.10741v1.pdf | |
PWC | https://paperswithcode.com/paper/robust-neural-malware-detection-models-for |
Repo | https://github.com/tychen5/sportslottery |
Framework | none |
SqueezeFit: Label-aware dimensionality reduction by semidefinite programming
Title | SqueezeFit: Label-aware dimensionality reduction by semidefinite programming |
Authors | Culver McWhirter, Dustin G. Mixon, Soledad Villar |
Abstract | Given labeled points in a high-dimensional vector space, we seek a low-dimensional subspace such that projecting onto this subspace maintains some prescribed distance between points of differing labels. Intended applications include compressive classification. Taking inspiration from large margin nearest neighbor classification, this paper introduces a semidefinite relaxation of this problem. Unlike its predecessors, this relaxation is amenable to theoretical analysis, allowing us to provably recover a planted projection operator from the data. |
Tasks | Dimensionality Reduction |
Published | 2018-12-06 |
URL | http://arxiv.org/abs/1812.02768v1 |
http://arxiv.org/pdf/1812.02768v1.pdf | |
PWC | https://paperswithcode.com/paper/squeezefit-label-aware-dimensionality |
Repo | https://github.com/solevillar/SqueezeFit |
Framework | none |
Cloud Detection From RGB Color Remote Sensing Images With Deep Pyramid Networks
Title | Cloud Detection From RGB Color Remote Sensing Images With Deep Pyramid Networks |
Authors | Savas Ozkan, Mehmet Efendioglu, Caner Demirpolat |
Abstract | Cloud detection from remotely observed data is a critical pre-processing step for various remote sensing applications. In particular, this problem becomes even harder for RGB color images, since there is no distinct spectral pattern for clouds, which is directly separable from the Earth surface. In this paper, we adapt a deep pyramid network (DPN) to tackle this problem. For this purpose, the network is enhanced with a pre-trained parameter model at the encoder layer. Moreover, the method is able to obtain accurate pixel-level segmentation and classification results from a set of noisy labeled RGB color images. In order to demonstrate the superiority of the method, we collect and label data with the corresponding cloud/non-cloudy masks acquired from low-orbit Gokturk-2 and RASAT satellites. The experimental results validates that the proposed method outperforms several baselines even for hard cases (e.g. snowy mountains) that are perceptually difficult to distinguish by human eyes. |
Tasks | Cloud Detection |
Published | 2018-01-26 |
URL | http://arxiv.org/abs/1801.08706v1 |
http://arxiv.org/pdf/1801.08706v1.pdf | |
PWC | https://paperswithcode.com/paper/cloud-detection-from-rgb-color-remote-sensing |
Repo | https://github.com/savasozkan/cloud_detection |
Framework | tf |
Community Regularization of Visually-Grounded Dialog
Title | Community Regularization of Visually-Grounded Dialog |
Authors | Akshat Agarwal, Swaminathan Gurumurthy, Vasu Sharma, Mike Lewis, Katia Sycara |
Abstract | The task of conducting visually grounded dialog involves learning goal-oriented cooperative dialog between autonomous agents who exchange information about a scene through several rounds of questions and answers in natural language. We posit that requiring artificial agents to adhere to the rules of human language, while also requiring them to maximize information exchange through dialog is an ill-posed problem. We observe that humans do not stray from a common language because they are social creatures who live in communities, and have to communicate with many people everyday, so it is far easier to stick to a common language even at the cost of some efficiency loss. Using this as inspiration, we propose and evaluate a multi-agent community-based dialog framework where each agent interacts with, and learns from, multiple agents, and show that this community-enforced regularization results in more relevant and coherent dialog (as judged by human evaluators) without sacrificing task performance (as judged by quantitative metrics). |
Tasks | |
Published | 2018-08-10 |
URL | http://arxiv.org/abs/1808.04359v2 |
http://arxiv.org/pdf/1808.04359v2.pdf | |
PWC | https://paperswithcode.com/paper/community-regularization-of-visually-grounded |
Repo | https://github.com/agakshat/visualdialog-pytorch |
Framework | pytorch |
Byte-Level Recursive Convolutional Auto-Encoder for Text
Title | Byte-Level Recursive Convolutional Auto-Encoder for Text |
Authors | Xiang Zhang, Yann LeCun |
Abstract | This article proposes to auto-encode text at byte-level using convolutional networks with a recursive architecture. The motivation is to explore whether it is possible to have scalable and homogeneous text generation at byte-level in a non-sequential fashion through the simple task of auto-encoding. We show that non-sequential text generation from a fixed-length representation is not only possible, but also achieved much better auto-encoding results than recurrent networks. The proposed model is a multi-stage deep convolutional encoder-decoder framework using residual connections, containing up to 160 parameterized layers. Each encoder or decoder contains a shared group of modules that consists of either pooling or upsampling layers, making the network recursive in terms of abstraction levels in representation. Results for 6 large-scale paragraph datasets are reported, in 3 languages including Arabic, Chinese and English. Analyses are conducted to study several properties of the proposed model. |
Tasks | Text Generation |
Published | 2018-02-06 |
URL | http://arxiv.org/abs/1802.01817v1 |
http://arxiv.org/pdf/1802.01817v1.pdf | |
PWC | https://paperswithcode.com/paper/byte-level-recursive-convolutional-auto |
Repo | https://github.com/smalik169/recursive-convolutional-autoencoder |
Framework | pytorch |
Confidence Propagation through CNNs for Guided Sparse Depth Regression
Title | Confidence Propagation through CNNs for Guided Sparse Depth Regression |
Authors | Abdelrahman Eldesokey, Michael Felsberg, Fahad Shahbaz Khan |
Abstract | Generally, convolutional neural networks (CNNs) process data on a regular grid, e.g. data generated by ordinary cameras. Designing CNNs for sparse and irregularly spaced input data is still an open research problem with numerous applications in autonomous driving, robotics, and surveillance. In this paper, we propose an algebraically-constrained normalized convolution layer for CNNs with highly sparse input that has a smaller number of network parameters compared to related work. We propose novel strategies for determining the confidence from the convolution operation and propagating it to consecutive layers. We also propose an objective function that simultaneously minimizes the data error while maximizing the output confidence. To integrate structural information, we also investigate fusion strategies to combine depth and RGB information in our normalized convolution network framework. In addition, we introduce the use of output confidence as an auxiliary information to improve the results. The capabilities of our normalized convolution network framework are demonstrated for the problem of scene depth completion. Comprehensive experiments are performed on the KITTI-Depth and the NYU-Depth-v2 datasets. The results clearly demonstrate that the proposed approach achieves superior performance while requiring only about 1-5% of the number of parameters compared to the state-of-the-art methods. |
Tasks | Autonomous Driving, Depth Completion |
Published | 2018-11-05 |
URL | https://arxiv.org/abs/1811.01791v2 |
https://arxiv.org/pdf/1811.01791v2.pdf | |
PWC | https://paperswithcode.com/paper/confidence-propagation-through-cnns-for |
Repo | https://github.com/abdo-eldesokey/nconv |
Framework | pytorch |
Propagating Confidences through CNNs for Sparse Data Regression
Title | Propagating Confidences through CNNs for Sparse Data Regression |
Authors | Abdelrahman Eldesokey, Michael Felsberg, Fahad Shahbaz Khan |
Abstract | In most computer vision applications, convolutional neural networks (CNNs) operate on dense image data generated by ordinary cameras. Designing CNNs for sparse and irregularly spaced input data is still an open problem with numerous applications in autonomous driving, robotics, and surveillance. To tackle this challenging problem, we introduce an algebraically-constrained convolution layer for CNNs with sparse input and demonstrate its capabilities for the scene depth completion task. We propose novel strategies for determining the confidence from the convolution operation and propagating it to consecutive layers. Furthermore, we propose an objective function that simultaneously minimizes the data error while maximizing the output confidence. Comprehensive experiments are performed on the KITTI depth benchmark and the results clearly demonstrate that the proposed approach achieves superior performance while requiring three times fewer parameters than the state-of-the-art methods. Moreover, our approach produces a continuous pixel-wise confidence map enabling information fusion, state inference, and decision support. |
Tasks | Autonomous Driving, Depth Completion |
Published | 2018-05-30 |
URL | http://arxiv.org/abs/1805.11913v3 |
http://arxiv.org/pdf/1805.11913v3.pdf | |
PWC | https://paperswithcode.com/paper/propagating-confidences-through-cnns-for |
Repo | https://github.com/abdo-eldesokey/nconv |
Framework | pytorch |
Fair Clustering Through Fairlets
Title | Fair Clustering Through Fairlets |
Authors | Flavio Chierichetti, Ravi Kumar, Silvio Lattanzi, Sergei Vassilvitskii |
Abstract | We study the question of fair clustering under the {\em disparate impact} doctrine, where each protected class must have approximately equal representation in every cluster. We formulate the fair clustering problem under both the $k$-center and the $k$-median objectives, and show that even with two protected classes the problem is challenging, as the optimum solution can violate common conventions—for instance a point may no longer be assigned to its nearest cluster center! En route we introduce the concept of fairlets, which are minimal sets that satisfy fair representation while approximately preserving the clustering objective. We show that any fair clustering problem can be decomposed into first finding good fairlets, and then using existing machinery for traditional clustering algorithms. While finding good fairlets can be NP-hard, we proceed to obtain efficient approximation algorithms based on minimum cost flow. We empirically quantify the value of fair clustering on real-world datasets with sensitive attributes. |
Tasks | |
Published | 2018-02-15 |
URL | http://arxiv.org/abs/1802.05733v1 |
http://arxiv.org/pdf/1802.05733v1.pdf | |
PWC | https://paperswithcode.com/paper/fair-clustering-through-fairlets |
Repo | https://github.com/talwagner/fair_clustering |
Framework | none |
Adversarial Time-to-Event Modeling
Title | Adversarial Time-to-Event Modeling |
Authors | Paidamoyo Chapfuwa, Chenyang Tao, Chunyuan Li, Courtney Page, Benjamin Goldstein, Lawrence Carin, Ricardo Henao |
Abstract | Modern health data science applications leverage abundant molecular and electronic health data, providing opportunities for machine learning to build statistical models to support clinical practice. Time-to-event analysis, also called survival analysis, stands as one of the most representative examples of such statistical models. We present a deep-network-based approach that leverages adversarial learning to address a key challenge in modern time-to-event modeling: nonparametric estimation of event-time distributions. We also introduce a principled cost function to exploit information from censored events (events that occur subsequent to the observation window). Unlike most time-to-event models, we focus on the estimation of time-to-event distributions, rather than time ordering. We validate our model on both benchmark and real datasets, demonstrating that the proposed formulation yields significant performance gains relative to a parametric alternative, which we also propose. |
Tasks | Survival Analysis |
Published | 2018-04-09 |
URL | http://arxiv.org/abs/1804.03184v2 |
http://arxiv.org/pdf/1804.03184v2.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-time-to-event-modeling |
Repo | https://github.com/paidamoyo/survival_cluster_analysis |
Framework | tf |
Summarizing Videos with Attention
Title | Summarizing Videos with Attention |
Authors | Jiri Fajtl, Hajar Sadeghi Sokeh, Vasileios Argyriou, Dorothy Monekosso, Paolo Remagnino |
Abstract | In this work we propose a novel method for supervised, keyshots based video summarization by applying a conceptually simple and computationally efficient soft, self-attention mechanism. Current state of the art methods leverage bi-directional recurrent networks such as BiLSTM combined with attention. These networks are complex to implement and computationally demanding compared to fully connected networks. To that end we propose a simple, self-attention based network for video summarization which performs the entire sequence to sequence transformation in a single feed forward pass and single backward pass during training. Our method sets a new state of the art results on two benchmarks TvSum and SumMe, commonly used in this domain. |
Tasks | Video Summarization |
Published | 2018-12-05 |
URL | http://arxiv.org/abs/1812.01969v2 |
http://arxiv.org/pdf/1812.01969v2.pdf | |
PWC | https://paperswithcode.com/paper/summarizing-videos-with-attention |
Repo | https://github.com/ok1zjf/VASNet |
Framework | pytorch |
Extracting Arguments from Korean Question and Command: An Annotated Corpus for Structured Paraphrasing
Title | Extracting Arguments from Korean Question and Command: An Annotated Corpus for Structured Paraphrasing |
Authors | Won Ik Cho, Young Ki Moon, Woo Hyun Kang, Nam Soo Kim |
Abstract | Intention identification is a core issue in dialog management. However, due to the non-canonicality of the spoken language, it is difficult to extract the content automatically from the conversation-style utterances. This is much more challenging for languages like Korean and Japanese since the agglutination between morphemes make it difficult for the machines to parse the sentence and understand the intention. To suggest a guideline for this problem, and to merge the issue flexibly with the neural paraphrasing systems introduced recently, we propose a structured annotation scheme for Korean question/commands and the resulting corpus which are widely applicable to the field of argument mining. The scheme and dataset are expected to help machines understand the intention of natural language and grasp the core meaning of conversation-style instructions. |
Tasks | Argument Mining, Slot Filling |
Published | 2018-10-10 |
URL | https://arxiv.org/abs/1810.04631v3 |
https://arxiv.org/pdf/1810.04631v3.pdf | |
PWC | https://paperswithcode.com/paper/structured-argument-extraction-of-korean |
Repo | https://github.com/warnikchow/sae4k |
Framework | none |
Netizen-Style Commenting on Fashion Photos: Dataset and Diversity Measures
Title | Netizen-Style Commenting on Fashion Photos: Dataset and Diversity Measures |
Authors | Wen Hua Lin, Kuan-Ting Chen, Hung Yueh Chiang, Winston Hsu |
Abstract | Recently, deep neural network models have achieved promising results in image captioning task. Yet, “vanilla” sentences, only describing shallow appearances (e.g., types, colors), generated by current works are not satisfied netizen style resulting in lacking engagements, contexts, and user intentions. To tackle this problem, we propose Netizen Style Commenting (NSC), to automatically generate characteristic comments to a user-contributed fashion photo. We are devoted to modulating the comments in a vivid “netizen” style which reflects the culture in a designated social community and hopes to facilitate more engagement with users. In this work, we design a novel framework that consists of three major components: (1) We construct a large-scale clothing dataset named NetiLook, which contains 300K posts (photos) with 5M comments to discover netizen-style comments. (2) We propose three unique measures to estimate the diversity of comments. (3) We bring diversity by marrying topic models with neural networks to make up the insufficiency of conventional image captioning works. Experimenting over Flickr30k and our NetiLook datasets, we demonstrate our proposed approaches benefit fashion photo commenting and improve image captioning tasks both in accuracy and diversity. |
Tasks | Image Captioning, Topic Models |
Published | 2018-01-31 |
URL | http://arxiv.org/abs/1801.10300v1 |
http://arxiv.org/pdf/1801.10300v1.pdf | |
PWC | https://paperswithcode.com/paper/netizen-style-commenting-on-fashion-photos |
Repo | https://github.com/yiyang92/sam_caption |
Framework | tf |
Learning Sentiment Memories for Sentiment Modification without Parallel Data
Title | Learning Sentiment Memories for Sentiment Modification without Parallel Data |
Authors | Yi Zhang, Jingjing Xu, Pengcheng Yang, Xu Sun |
Abstract | The task of sentiment modification requires reversing the sentiment of the input and preserving the sentiment-independent content. However, aligned sentences with the same content but different sentiments are usually unavailable. Due to the lack of such parallel data, it is hard to extract sentiment independent content and reverse the sentiment in an unsupervised way. Previous work usually can not reconcile sentiment transformation and content preservation. In this paper, motivated by the fact the non-emotional context (e.g., “staff”) provides strong cues for the occurrence of emotional words (e.g., “friendly”), we propose a novel method that automatically extracts appropriate sentiment information from learned sentiment memories according to specific context. Experiments show that our method substantially improves the content preservation degree and achieves the state-of-the-art performance. |
Tasks | Text Style Transfer |
Published | 2018-08-22 |
URL | http://arxiv.org/abs/1808.07311v1 |
http://arxiv.org/pdf/1808.07311v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-sentiment-memories-for-sentiment |
Repo | https://github.com/lancopku/SMAE |
Framework | tf |
Russian word sense induction by clustering averaged word embeddings
Title | Russian word sense induction by clustering averaged word embeddings |
Authors | Andrey Kutuzov |
Abstract | The paper reports our participation in the shared task on word sense induction and disambiguation for the Russian language (RUSSE-2018). Our team was ranked 2nd for the wiki-wiki dataset (containing mostly homonyms) and 5th for the bts-rnc and active-dict datasets (containing mostly polysemous words) among all 19 participants. The method we employed was extremely naive. It implied representing contexts of ambiguous words as averaged word embedding vectors, using off-the-shelf pre-trained distributional models. Then, these vector representations were clustered with mainstream clustering techniques, thus producing the groups corresponding to the ambiguous word senses. As a side result, we show that word embedding models trained on small but balanced corpora can be superior to those trained on large but noisy data - not only in intrinsic evaluation, but also in downstream tasks like word sense induction. |
Tasks | Word Embeddings, Word Sense Induction |
Published | 2018-05-06 |
URL | http://arxiv.org/abs/1805.02258v1 |
http://arxiv.org/pdf/1805.02258v1.pdf | |
PWC | https://paperswithcode.com/paper/russian-word-sense-induction-by-clustering |
Repo | https://github.com/akutuzov/russian_wsi |
Framework | none |