January 27, 2020

2908 words 14 mins read

Paper Group ANR 1103

Dixit: Interactive Visual Storytelling via Term Manipulation. Confidential Deep Learning: Executing Proprietary Models on Untrusted Devices. MTJ-Based Hardware Synapse Design for Quantized Deep Neural Networks. Predict Emoji Combination with Retrieval Strategy. Model-Based and Data-Driven Strategies in Medical Image Computing. SOSNet: Second Order …

Dixit: Interactive Visual Storytelling via Term Manipulation


Title	Dixit: Interactive Visual Storytelling via Term Manipulation
Authors	Chao-Chun Hsu, Yu-Hua Chen, Zi-Yuan Chen, Hsin-Yu Lin, Ting-Hao ‘Kenneth’ Huang, Lun-Wei Ku
Abstract	In this paper, we introduce Dixit, an interactive visual storytelling system that the user interacts with iteratively to compose a short story for a photo sequence. The user initiates the process by uploading a sequence of photos. Dixit first extracts text terms from each photo which describe the objects (e.g., boy, bike) or actions (e.g., sleep) in the photo, and then allows the user to add new terms or remove existing terms. Dixit then generates a short story based on these terms. Behind the scenes, Dixit uses an LSTM-based model trained on image caption data and FrameNet to distill terms from each image and utilizes a transformer decoder to compose a context-coherent story. Users change images or terms iteratively with Dixit to create the most ideal story. Dixit also allows users to manually edit and rate stories. The proposed procedure opens up possibilities for interpretable and controllable visual storytelling, allowing users to understand the story formation rationale and to intervene in the generation process.
Tasks	Visual Storytelling
Published	2019-03-06
URL	https://arxiv.org/abs/1903.02230v3
PDF	https://arxiv.org/pdf/1903.02230v3.pdf
PWC	https://paperswithcode.com/paper/dixit-interactive-visual-storytelling-via
Repo
Framework

Confidential Deep Learning: Executing Proprietary Models on Untrusted Devices


Title	Confidential Deep Learning: Executing Proprietary Models on Untrusted Devices
Authors	Peter M. VanNostrand, Ioannis Kyriazis, Michelle Cheng, Tian Guo, Robert J. Walls
Abstract	Performing deep learning on end-user devices provides fast offline inference results and can help protect the user’s privacy. However, running models on untrusted client devices reveals model information which may be proprietary, i.e., the operating system or other applications on end-user devices may be manipulated to copy and redistribute this information, infringing on the model provider’s intellectual property. We propose the use of ARM TrustZone, a hardware-based security feature present in most phones, to confidentially run a proprietary model on an untrusted end-user device. We explore the limitations and design challenges of using TrustZone and examine potential approaches for confidential deep learning within this environment. Of particular interest is providing robust protection of proprietary model information while minimizing total performance overhead.
Tasks
Published	2019-08-28
URL	https://arxiv.org/abs/1908.10730v1
PDF	https://arxiv.org/pdf/1908.10730v1.pdf
PWC	https://paperswithcode.com/paper/confidential-deep-learning-executing
Repo
Framework

MTJ-Based Hardware Synapse Design for Quantized Deep Neural Networks


Title	MTJ-Based Hardware Synapse Design for Quantized Deep Neural Networks
Authors	Tzofnat Greenberg Toledo, Ben Perach, Daniel Soudry, Shahar Kvatinsky
Abstract	Quantized neural networks (QNNs) are being actively researched as a solution for the computational complexity and memory intensity of deep neural networks. This has sparked efforts to develop algorithms that support both inference and training with quantized weight and activation values without sacrificing accuracy. A recent example is the GXNOR framework for stochastic training of ternary and binary neural networks. In this paper, we introduce a novel hardware synapse circuit that uses magnetic tunnel junction (MTJ) devices to support the GXNOR training. Our solution enables processing near memory (PNM) of QNNs, therefore can further reduce the data movements from and into the memory. We simulated MTJ-based stochastic training of a TNN over the MNIST and SVHN datasets and achieved an accuracy of 98.61% and 93.99%, respectively.
Tasks
Published	2019-12-29
URL	https://arxiv.org/abs/1912.12636v1
PDF	https://arxiv.org/pdf/1912.12636v1.pdf
PWC	https://paperswithcode.com/paper/mtj-based-hardware-synapse-design-for
Repo
Framework

Predict Emoji Combination with Retrieval Strategy


Title	Predict Emoji Combination with Retrieval Strategy
Authors	Weitsung Lin, Tinghsuan Chao, Jianmin Wu, Tianhuang Su
Abstract	As emojis are widely used in social media, people not only use an emoji to express their emotions or mention things but also extend its usage to represent complicate emotions, concepts or activities by combining multiple emojis. In this work, we study how emoji combination, a consecutive emoji sequence, is used like a new language. We propose a novel algorithm called Retrieval Strategy to predict what emoji combination follows given a short text as context. Our algorithm treats emoji combinations as phrase in language, ranking sets of emoji combinations like retrieving words from dictionary. We show that our algorithm largely improves the F1 score from 0.141 to 0.204 on emoji combination prediction task.
Tasks
Published	2019-08-21
URL	https://arxiv.org/abs/1908.07761v1
PDF	https://arxiv.org/pdf/1908.07761v1.pdf
PWC	https://paperswithcode.com/paper/190807761
Repo
Framework

Model-Based and Data-Driven Strategies in Medical Image Computing


Title	Model-Based and Data-Driven Strategies in Medical Image Computing
Authors	Daniel Rueckert, Julia A. Schnabel
Abstract	Model-based approaches for image reconstruction, analysis and interpretation have made significant progress over the last decades. Many of these approaches are based on either mathematical, physical or biological models. A challenge for these approaches is the modelling of the underlying processes (e.g. the physics of image acquisition or the patho-physiology of a disease) with appropriate levels of detail and realism. With the availability of large amounts of imaging data and machine learning (in particular deep learning) techniques, data-driven approaches have become more widespread for use in different tasks in reconstruction, analysis and interpretation. These approaches learn statistical models directly from labelled or unlabeled image data and have been shown to be very powerful for extracting clinically useful information from medical imaging. While these data-driven approaches often outperform traditional model-based approaches, their clinical deployment often poses challenges in terms of robustness, generalization ability and interpretability. In this article, we discuss what developments have motivated the shift from model-based approaches towards data-driven strategies and what potential problems are associated with the move towards purely data-driven approaches, in particular deep learning. We also discuss some of the open challenges for data-driven approaches, e.g. generalization to new unseen data (e.g. transfer learning), robustness to adversarial attacks and interpretability. Finally, we conclude with a discussion on how these approaches may lead to the development of more closely coupled imaging pipelines that are optimized in an end-to-end fashion.
Tasks	Image Reconstruction, Transfer Learning
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10391v3
PDF	https://arxiv.org/pdf/1909.10391v3.pdf
PWC	https://paperswithcode.com/paper/190910391
Repo
Framework

SOSNet: Second Order Similarity Regularization for Local Descriptor Learning


Title	SOSNet: Second Order Similarity Regularization for Local Descriptor Learning
Authors	Yurun Tian, Xin Yu, Bin Fan, Fuchao Wu, Huub Heijnen, Vassileios Balntas
Abstract	Despite the fact that Second Order Similarity (SOS) has been used with significant success in tasks such as graph matching and clustering, it has not been exploited for learning local descriptors. In this work, we explore the potential of SOS in the field of descriptor learning by building upon the intuition that a positive pair of matching points should exhibit similar distances with respect to other points in the embedding space. Thus, we propose a novel regularization term, named Second Order Similarity Regularization (SOSR), that follows this principle. By incorporating SOSR into training, our learned descriptor achieves state-of-the-art performance on several challenging benchmarks containing distinct tasks ranging from local patch retrieval to structure from motion. Furthermore, by designing a von Mises-Fischer distribution based evaluation method, we link the utilization of the descriptor space to the matching performance, thus demonstrating the effectiveness of our proposed SOSR. Extensive experimental results, empirical evidence, and in-depth analysis are provided, indicating that SOSR can significantly boost the matching performance of the learned descriptor.
Tasks	Graph Matching
Published	2019-04-10
URL	https://arxiv.org/abs/1904.05019v2
PDF	https://arxiv.org/pdf/1904.05019v2.pdf
PWC	https://paperswithcode.com/paper/sosnet-second-order-similarity-regularization
Repo
Framework

Bayesian Optimization for Multi-objective Optimization and Multi-point Search


Title	Bayesian Optimization for Multi-objective Optimization and Multi-point Search
Authors	Takashi Wada, Hideitsu Hino
Abstract	Bayesian optimization is an effective method to efficiently optimize unknown objective functions with high evaluation costs. Traditional Bayesian optimization algorithms select one point per iteration for single objective function, whereas in recent years, Bayesian optimization for multi-objective optimization or multi-point search per iteration have been proposed. However, Bayesian optimization that can deal with them at the same time in non-heuristic way is not known at present. We propose a Bayesian optimization algorithm that can deal with multi-objective optimization and multi-point search at the same time. First, we define an acquisition function that considers both multi-objective and multi-point search problems. It is difficult to analytically maximize the acquisition function as the computational cost is prohibitive even when approximate calculations such as sampling approximation are performed; therefore, we propose an accurate and computationally efficient method for estimating gradient of the acquisition function, and develop an algorithm for Bayesian optimization with multi-objective and multi-point search. It is shown via numerical experiments that the performance of the proposed method is comparable or superior to those of heuristic methods.
Tasks
Published	2019-05-07
URL	https://arxiv.org/abs/1905.02370v1
PDF	https://arxiv.org/pdf/1905.02370v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-optimization-for-multi-objective
Repo
Framework

Multi-class Multilingual Classification of Wikipedia Articles Using Extended Named Entity Tag Set


Title	Multi-class Multilingual Classification of Wikipedia Articles Using Extended Named Entity Tag Set
Authors	Hassan S. Shavarani, Satoshi Sekine
Abstract	Wikipedia is a great source of general world knowledge which can guide NLP models better understand their motivation to make predictions. Structuring Wikipedia is the initial step towards this goal which can facilitate fine-grain classification of articles. In this work, we introduce the Shinra 5-Language Categorization Dataset (SHINRA-5LDS), a large multi-lingual and multi-labeled set of annotated Wikipedia articles in Japanese, English, French, German, and Farsi using Extended Named Entity (ENE) tag set. We evaluate the dataset using the best models provided for ENE label set classification and show that the currently available classification models struggle with large datasets using fine-grained tag sets.
Tasks
Published	2019-09-14
URL	https://arxiv.org/abs/1909.06502v2
PDF	https://arxiv.org/pdf/1909.06502v2.pdf
PWC	https://paperswithcode.com/paper/multi-class-multilingual-classification-of
Repo
Framework

Enhanced Optimization with Composite Objectives and Novelty Pulsation


Title	Enhanced Optimization with Composite Objectives and Novelty Pulsation
Authors	Hormoz Shahrzad, Babak Hodjat, Camille Dollé, Andrei Denissov, Simon Lau, Donn Goodhew, Justin Dyer, Risto Miikkulainen
Abstract	An important benefit of multi-objective search is that it maintains a diverse population of candidates, which helps in deceptive problems in particular. Not all diversity is useful, however: candidates that optimize only one objective while ignoring others are rarely helpful. A recent solution is to replace the original objectives by their linear combinations, thus focusing the search on the most useful trade-offs between objectives. To compensate for the loss of diversity, this transformation is accompanied by a selection mechanism that favors novelty. This paper improves this approach further by introducing novelty pulsation, i.e. a systematic method to alternate between novelty selection and local optimization. In the highly deceptive problem of discovering minimal sorting networks, it finds state-of-the-art solutions significantly faster than before. In fact, our method so far has established a new world record for the 20-lines sorting network with 91 comparators. In the real-world problem of stock trading, it discovers solutions that generalize significantly better on unseen data. Composite Novelty Pulsation is therefore a promising approach to solving deceptive real-world problems through multi-objective optimization.
Tasks
Published	2019-06-07
URL	https://arxiv.org/abs/1906.04050v2
PDF	https://arxiv.org/pdf/1906.04050v2.pdf
PWC	https://paperswithcode.com/paper/enhanced-optimization-with-composite-1
Repo
Framework

Profile-based Resource Allocation for Virtualized Network Functions


Title	Profile-based Resource Allocation for Virtualized Network Functions
Authors	Steven Van Rossem, Wouter Tavernier, Didier Colle, Mario Pickavet, Piet Demeester
Abstract	The virtualization of compute and network resources enables an unseen flexibility for deploying network services. A wide spectrum of emerging technologies allows an ever-growing range of orchestration possibilities in cloud-based environments. But in this context it remains challenging to rhyme dynamic cloud configurations with deterministic performance. The service operator must somehow map the performance specification in the Service Level Agreement (SLA) to an adequate resource allocation in the virtualized infrastructure. We propose the use of a VNF profile to alleviate this process. This is illustrated by profiling the performance of four example network functions (a virtual router, switch, firewall and cache server) under varying workloads and resource configurations. We then compare several methods to derive a model from the profiled datasets. We select the most accurate method to further train a model which predicts the services’ performance, in function of incoming workload and allocated resources. Our presented method can offer the service operator a recommended resource allocation for the targeted service, in function of the targeted performance and maximum workload specified in the SLA. This helps to deploy the softwarized service with an optimal amount of resources to meet the SLA requirements, thereby avoiding unnecessary scaling steps.
Tasks
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07738v1
PDF	https://arxiv.org/pdf/1911.07738v1.pdf
PWC	https://paperswithcode.com/paper/profile-based-resource-allocation-for
Repo
Framework

Deep Fictitious Play for Stochastic Differential Games


Title	Deep Fictitious Play for Stochastic Differential Games
Authors	Ruimeng Hu
Abstract	In this paper, we apply the idea of fictitious play to design deep neural networks (DNNs), and develop deep learning theory and algorithms for computing the Nash equilibrium of asymmetric $N$-player non-zero-sum stochastic differential games, for which we refer as \emph{deep fictitious play}, a multi-stage learning process. Specifically at each stage, we propose the strategy of letting individual player optimize her own payoff subject to the other players’ previous actions, equivalent to solve $N$ decoupled stochastic control optimization problems, which are approximated by DNNs. Therefore, the fictitious play strategy leads to a structure consisting of $N$ DNNs, which only communicate at the end of each stage. The resulted deep learning algorithm based on fictitious play is scalable, parallel and model-free, {\it i.e.}, using GPU parallelization, it can be applied to any $N$-player stochastic differential game with different symmetries and heterogeneities ({\it e.g.}, existence of major players). We illustrate the performance of the deep learning algorithm by comparing to the closed-form solution of the linear quadratic game. Moreover, we prove the convergence of fictitious play under appropriate assumptions, and verify that the convergent limit forms an open-loop Nash equilibrium. We also discuss the extensions to other strategies designed upon fictitious play and closed-loop Nash equilibrium in the end.
Tasks
Published	2019-03-22
URL	https://arxiv.org/abs/1903.09376v2
PDF	https://arxiv.org/pdf/1903.09376v2.pdf
PWC	https://paperswithcode.com/paper/deep-fictitious-play-for-stochastic
Repo
Framework

A bag-of-concepts model improves relation extraction in a narrow knowledge domain with limited data


Title	A bag-of-concepts model improves relation extraction in a narrow knowledge domain with limited data
Authors	Jiyu Chen, Karin Verspoor, Zenan Zhai
Abstract	This paper focuses on a traditional relation extraction task in the context of limited annotated data and a narrow knowledge domain. We explore this task with a clinical corpus consisting of 200 breast cancer follow-up treatment letters in which 16 distinct types of relations are annotated. We experiment with an approach to extracting typed relations called window-bounded co-occurrence (WBC), which uses an adjustable context window around entity mentions of a relevant type, and compare its performance with a more typical intra-sentential co-occurrence baseline. We further introduce a new bag-of-concepts (BoC) approach to feature engineering based on the state-of-the-art word embeddings and word synonyms. We demonstrate the competitiveness of BoC by comparing with methods of higher complexity, and explore its effectiveness on this small dataset.
Tasks	Feature Engineering, Relation Extraction, Word Embeddings
Published	2019-04-24
URL	http://arxiv.org/abs/1904.10743v1
PDF	http://arxiv.org/pdf/1904.10743v1.pdf
PWC	https://paperswithcode.com/paper/a-bag-of-concepts-model-improves-relation
Repo
Framework

Deep clustering with concrete k-means


Title	Deep clustering with concrete k-means
Authors	Boyan Gao, Yongxin Yang, Henry Gouk, Timothy M. Hospedales
Abstract	We address the problem of simultaneously learning a k-means clustering and deep feature representation from unlabelled data, which is of interest due to the potential of deep k-means to outperform traditional two-step feature extraction and shallow-clustering strategies. We achieve this by developing a gradient-estimator for the non-differentiable k-means objective via the Gumbel-Softmax reparameterisation trick. In contrast to previous attempts at deep clustering, our concrete k-means model can be optimised with respect to the canonical k-means objective and is easily trained end-to-end without resorting to alternating optimisation. We demonstrate the efficacy of our method on standard clustering benchmarks.
Tasks
Published	2019-10-17
URL	https://arxiv.org/abs/1910.08031v1
PDF	https://arxiv.org/pdf/1910.08031v1.pdf
PWC	https://paperswithcode.com/paper/deep-clustering-with-concrete-k-means
Repo
Framework

History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms


Title	History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms
Authors	Kaiyi Ji, Zhe Wang, Bowen Weng, Yi Zhou, Wei Zhang, Yingbin Liang
Abstract	Variance-reduced algorithms, although achieve great theoretical performance, can run slowly in practice due to the periodic gradient estimation with a large batch of data. Batch-size adaptation thus arises as a promising approach to accelerate such algorithms. However, existing schemes either apply prescribed batch-size adaption rule or exploit the information along optimization path via additional backtracking and condition verification steps. In this paper, we propose a novel scheme, which eliminates backtracking line search but still exploits the information along optimization path by adapting the batch size via history stochastic gradients. We further theoretically show that such a scheme substantially reduces the overall complexity for popular variance-reduced algorithms SVRG and SARAH/SPIDER for both conventional nonconvex optimization and reinforcement learning problems. To this end, we develop a new convergence analysis framework to handle the dependence of the batch size on history stochastic gradients. Extensive experiments validate the effectiveness of the proposed batch-size adaptation scheme.
Tasks
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09670v3
PDF	https://arxiv.org/pdf/1910.09670v3.pdf
PWC	https://paperswithcode.com/paper/faster-stochastic-algorithms-via-history
Repo
Framework

Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation


Title	Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation
Authors	Eva Vanmassenhove, Dimitar Shterionov, Andy Way
Abstract	This work presents an empirical approach to quantifying the loss of lexical richness in Machine Translation (MT) systems compared to Human Translation (HT). Our experiments show how current MT systems indeed fail to render the lexical diversity of human generated or translated text. The inability of MT systems to generate diverse outputs and its tendency to exacerbate already frequent patterns while ignoring less frequent ones, might be the underlying cause for, among others, the currently heavily debated issues related to gender biased output. Can we indeed, aside from biased data, talk about an algorithm that exacerbates seen biases?
Tasks	Machine Translation
Published	2019-06-28
URL	https://arxiv.org/abs/1906.12068v1
PDF	https://arxiv.org/pdf/1906.12068v1.pdf
PWC	https://paperswithcode.com/paper/lost-in-translation-loss-and-decay-of
Repo
Framework