Paper Group ANR 374
Networked Fairness in Cake Cutting. Adversarial Deep Structured Nets for Mass Segmentation from Mammograms. Adversarial Symmetric Variational Autoencoder. Machine Learning Approaches to Energy Consumption Forecasting in Households. MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval. Simple to Complex Cross-modal Learning to R …
Networked Fairness in Cake Cutting
| Title | Networked Fairness in Cake Cutting |
| Authors | Xiaohui Bei, Youming Qiao, Shengyu Zhang |
| Abstract | We introduce a graphical framework for fair division in cake cutting, where comparisons between agents are limited by an underlying network structure. We generalize the classical fairness notions of envy-freeness and proportionality to this graphical setting. Given a simple undirected graph G, an allocation is envy-free on G if no agent envies any of her neighbor’s share, and is proportional on G if every agent values her own share no less than the average among her neighbors, with respect to her own measure. These generalizations open new research directions in developing simple and efficient algorithms that can produce fair allocations under specific graph structures. On the algorithmic frontier, we first propose a moving-knife algorithm that outputs an envy-free allocation on trees. The algorithm is significantly simpler than the discrete and bounded envy-free algorithm recently designed by Aziz and Mackenzie for complete graphs. Next, we give a discrete and bounded algorithm for computing a proportional allocation on descendant graphs, a class of graphs by taking a rooted tree and connecting all its ancestor-descendant pairs. |
| Tasks | |
| Published | 2017-07-07 |
| URL | http://arxiv.org/abs/1707.02033v1 |
| http://arxiv.org/pdf/1707.02033v1.pdf | |
| PWC | https://paperswithcode.com/paper/networked-fairness-in-cake-cutting |
| Repo | |
| Framework | |
Adversarial Deep Structured Nets for Mass Segmentation from Mammograms
| Title | Adversarial Deep Structured Nets for Mass Segmentation from Mammograms |
| Authors | Wentao Zhu, Xiang Xiang, Trac D. Tran, Gregory D. Hager, Xiaohui Xie |
| Abstract | Mass segmentation provides effective morphological features which are important for mass diagnosis. In this work, we propose a novel end-to-end network for mammographic mass segmentation which employs a fully convolutional network (FCN) to model a potential function, followed by a CRF to perform structured learning. Because the mass distribution varies greatly with pixel position, the FCN is combined with a position priori. Further, we employ adversarial training to eliminate over-fitting due to the small sizes of mammogram datasets. Multi-scale FCN is employed to improve the segmentation performance. Experimental results on two public datasets, INbreast and DDSM-BCRP, demonstrate that our end-to-end network achieves better performance than state-of-the-art approaches. \footnote{https://github.com/wentaozhu/adversarial-deep-structural-networks.git} |
| Tasks | Mass Segmentation From Mammograms |
| Published | 2017-10-24 |
| URL | http://arxiv.org/abs/1710.09288v2 |
| http://arxiv.org/pdf/1710.09288v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-deep-structured-nets-for-mass |
| Repo | |
| Framework | |
Adversarial Symmetric Variational Autoencoder
| Title | Adversarial Symmetric Variational Autoencoder |
| Authors | Yunchen Pu, Weiyao Wang, Ricardo Henao, Liqun Chen, Zhe Gan, Chunyuan Li, Lawrence Carin |
| Abstract | A new form of variational autoencoder (VAE) is developed, in which the joint distribution of data and codes is considered in two (symmetric) forms: ($i$) from observed data fed through the encoder to yield codes, and ($ii$) from latent codes drawn from a simple prior and propagated through the decoder to manifest data. Lower bounds are learned for marginal log-likelihood fits observed data and latent codes. When learning with the variational bound, one seeks to minimize the symmetric Kullback-Leibler divergence of joint density functions from ($i$) and ($ii$), while simultaneously seeking to maximize the two marginal log-likelihoods. To facilitate learning, a new form of adversarial training is developed. An extensive set of experiments is performed, in which we demonstrate state-of-the-art data reconstruction and generation on several image benchmark datasets. |
| Tasks | |
| Published | 2017-11-14 |
| URL | http://arxiv.org/abs/1711.04915v2 |
| http://arxiv.org/pdf/1711.04915v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-symmetric-variational-autoencoder |
| Repo | |
| Framework | |
Machine Learning Approaches to Energy Consumption Forecasting in Households
| Title | Machine Learning Approaches to Energy Consumption Forecasting in Households |
| Authors | Riccardo Bonetto, Michele Rossi |
| Abstract | We consider the problem of power demand forecasting in residential micro-grids. Several approaches using ARMA models, support vector machines, and recurrent neural networks that perform one-step ahead predictions have been proposed in the literature. Here, we extend them to perform multi-step ahead forecasting and we compare their performance. Toward this end, we implement a parallel and efficient training framework, using power demand traces from real deployments to gauge the accuracy of the considered techniques. Our results indicate that machine learning schemes achieve smaller prediction errors in the mean and the variance with respect to ARMA, but there is no clear algorithm of choice among them. Pros and cons of these approaches are discussed and the solution of choice is found to depend on the specific use case requirements. A hybrid approach, that is driven by the prediction interval, the target error, and its uncertainty, is then recommended. |
| Tasks | |
| Published | 2017-06-29 |
| URL | http://arxiv.org/abs/1706.09648v1 |
| http://arxiv.org/pdf/1706.09648v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-approaches-to-energy |
| Repo | |
| Framework | |
MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval
| Title | MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval |
| Authors | Xin Huang, Yuxin Peng, Mingkuan Yuan |
| Abstract | Cross-modal retrieval has drawn wide interest for retrieval across different modalities of data. However, existing methods based on DNN face the challenge of insufficient cross-modal training data, which limits the training effectiveness and easily leads to overfitting. Transfer learning is for relieving the problem of insufficient training data, but it mainly focuses on knowledge transfer only from large-scale datasets as single-modal source domain to single-modal target domain. Such large-scale single-modal datasets also contain rich modal-independent semantic knowledge that can be shared across different modalities. Besides, large-scale cross-modal datasets are very labor-consuming to collect and label, so it is significant to fully exploit the knowledge in single-modal datasets for boosting cross-modal retrieval. This paper proposes modal-adversarial hybrid transfer network (MHTN), which to the best of our knowledge is the first work to realize knowledge transfer from single-modal source domain to cross-modal target domain, and learn cross-modal common representation. It is an end-to-end architecture with two subnetworks: (1) Modal-sharing knowledge transfer subnetwork is proposed to jointly transfer knowledge from a large-scale single-modal dataset in source domain to all modalities in target domain with a star network structure, which distills modal-independent supplementary knowledge for promoting cross-modal common representation learning. (2) Modal-adversarial semantic learning subnetwork is proposed to construct an adversarial training mechanism between common representation generator and modality discriminator, making the common representation discriminative for semantics but indiscriminative for modalities to enhance cross-modal semantic consistency during transfer process. Comprehensive experiments on 4 widely-used datasets show its effectiveness and generality. |
| Tasks | Cross-Modal Retrieval, Representation Learning, Transfer Learning |
| Published | 2017-08-08 |
| URL | http://arxiv.org/abs/1708.04308v1 |
| http://arxiv.org/pdf/1708.04308v1.pdf | |
| PWC | https://paperswithcode.com/paper/mhtn-modal-adversarial-hybrid-transfer |
| Repo | |
| Framework | |
Simple to Complex Cross-modal Learning to Rank
| Title | Simple to Complex Cross-modal Learning to Rank |
| Authors | Minnan Luo, Xiaojun Chang, Zhihui Li, Liqiang Nie, Alexander G. Hauptmann, Qinghua Zheng |
| Abstract | The heterogeneity-gap between different modalities brings a significant challenge to multimedia information retrieval. Some studies formalize the cross-modal retrieval tasks as a ranking problem and learn a shared multi-modal embedding space to measure the cross-modality similarity. However, previous methods often establish the shared embedding space based on linear mapping functions which might not be sophisticated enough to reveal more complicated inter-modal correspondences. Additionally, current studies assume that the rankings are of equal importance, and thus all rankings are used simultaneously, or a small number of rankings are selected randomly to train the embedding space at each iteration. Such strategies, however, always suffer from outliers as well as reduced generalization capability due to their lack of insightful understanding of procedure of human cognition. In this paper, we involve the self-paced learning theory with diversity into the cross-modal learning to rank and learn an optimal multi-modal embedding space based on non-linear mapping functions. This strategy enhances the model’s robustness to outliers and achieves better generalization via training the model gradually from easy rankings by diverse queries to more complex ones. An efficient alternative algorithm is exploited to solve the proposed challenging problem with fast convergence in practice. Extensive experimental results on several benchmark datasets indicate that the proposed method achieves significant improvements over the state-of-the-arts in this literature. |
| Tasks | Cross-Modal Retrieval, Information Retrieval, Learning-To-Rank |
| Published | 2017-02-04 |
| URL | http://arxiv.org/abs/1702.01229v2 |
| http://arxiv.org/pdf/1702.01229v2.pdf | |
| PWC | https://paperswithcode.com/paper/simple-to-complex-cross-modal-learning-to |
| Repo | |
| Framework | |
Hidden Tree Markov Networks: Deep and Wide Learning for Structured Data
| Title | Hidden Tree Markov Networks: Deep and Wide Learning for Structured Data |
| Authors | Davide Bacciu |
| Abstract | The paper introduces the Hidden Tree Markov Network (HTN), a neuro-probabilistic hybrid fusing the representation power of generative models for trees with the incremental and discriminative learning capabilities of neural networks. We put forward a modular architecture in which multiple generative models of limited complexity are trained to learn structural feature detectors whose outputs are then combined and integrated by neural layers at a later stage. In this respect, the model is both deep, thanks to the unfolding of the generative models on the input structures, as well as wide, given the potentially large number of generative modules that can be trained in parallel. Experimental results show that the proposed approach can outperform state-of-the-art syntactic kernels as well as generative kernels built on the same probabilistic model as the HTN. |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.07784v1 |
| http://arxiv.org/pdf/1711.07784v1.pdf | |
| PWC | https://paperswithcode.com/paper/hidden-tree-markov-networks-deep-and-wide |
| Repo | |
| Framework | |
Sequential 3D U-Nets for Biologically-Informed Brain Tumor Segmentation
| Title | Sequential 3D U-Nets for Biologically-Informed Brain Tumor Segmentation |
| Authors | Andrew Beers, Ken Chang, James Brown, Emmett Sartor, CP Mammen, Elizabeth Gerstner, Bruce Rosen, Jayashree Kalpathy-Cramer |
| Abstract | Deep learning has quickly become the weapon of choice for brain lesion segmentation. However, few existing algorithms pre-configure any biological context of their chosen segmentation tissues, and instead rely on the neural network’s optimizer to develop such associations de novo. We present a novel method for applying deep neural networks to the problem of glioma tissue segmentation that takes into account the structured nature of gliomas - edematous tissue surrounding mutually-exclusive regions of enhancing and non-enhancing tumor. We trained multiple deep neural networks with a 3D U-Net architecture in a tree structure to create segmentations for edema, non-enhancing tumor, and enhancing tumor regions. Specifically, training was configured such that the whole tumor region including edema was predicted first, and its output segmentation was fed as input into separate models to predict enhancing and non-enhancing tumor. Our method was trained and evaluated on the publicly available BraTS dataset, achieving Dice scores of 0.882, 0.732, and 0.730 for whole tumor, enhancing tumor and tumor core respectively. |
| Tasks | Brain Tumor Segmentation, Lesion Segmentation |
| Published | 2017-09-09 |
| URL | http://arxiv.org/abs/1709.02967v1 |
| http://arxiv.org/pdf/1709.02967v1.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-3d-u-nets-for-biologically |
| Repo | |
| Framework | |
What Automated Planning can do for Business Process Management
| Title | What Automated Planning can do for Business Process Management |
| Authors | Andrea Marrella |
| Abstract | Business Process Management (BPM) is a central element of today organizations. Despite over the years its main focus has been the support of processes in highly controlled domains, nowadays many domains of interest to the BPM community are characterized by ever-changing requirements, unpredictable environments and increasing amounts of data that influence the execution of process instances. Under such dynamic conditions, BPM systems must increase their level of automation to provide the reactivity and flexibility necessary for process management. On the other hand, the Artificial Intelligence (AI) community has concentrated its efforts on investigating dynamic domains that involve active control of computational entities and physical devices (e.g., robots, software agents, etc.). In this context, Automated Planning, which is one of the oldest areas in AI, is conceived as a model-based approach to synthesize autonomous behaviours in automated way from a model. In this paper, we discuss how automated planning techniques can be leveraged to enable new levels of automation and support for business processing, and we show some concrete examples of their successful application to the different stages of the BPM life cycle. |
| Tasks | |
| Published | 2017-09-29 |
| URL | http://arxiv.org/abs/1709.10482v2 |
| http://arxiv.org/pdf/1709.10482v2.pdf | |
| PWC | https://paperswithcode.com/paper/what-automated-planning-can-do-for-business |
| Repo | |
| Framework | |
Deep Neural Networks - A Brief History
| Title | Deep Neural Networks - A Brief History |
| Authors | Krzysztof J. Cios |
| Abstract | Introduction to deep neural networks and their history. |
| Tasks | |
| Published | 2017-01-19 |
| URL | http://arxiv.org/abs/1701.05549v1 |
| http://arxiv.org/pdf/1701.05549v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-neural-networks-a-brief-history |
| Repo | |
| Framework | |
Encoding CNN Activations for Writer Recognition
| Title | Encoding CNN Activations for Writer Recognition |
| Authors | Vincent Christlein, Andreas Maier |
| Abstract | The encoding of local features is an essential part for writer identification and writer retrieval. While CNN activations have already been used as local features in related works, the encoding of these features has attracted little attention so far. In this work, we compare the established VLAD encoding with triangulation embedding. We further investigate generalized max pooling as an alternative to sum pooling and the impact of decorrelation and Exemplar SVMs. With these techniques, we set new standards on two publicly available datasets (ICDAR13, KHATT). |
| Tasks | |
| Published | 2017-12-21 |
| URL | http://arxiv.org/abs/1712.07923v2 |
| http://arxiv.org/pdf/1712.07923v2.pdf | |
| PWC | https://paperswithcode.com/paper/encoding-cnn-activations-for-writer |
| Repo | |
| Framework | |
Fast Stochastic Variance Reduced Gradient Method with Momentum Acceleration for Machine Learning
| Title | Fast Stochastic Variance Reduced Gradient Method with Momentum Acceleration for Machine Learning |
| Authors | Fanhua Shang, Yuanyuan Liu, James Cheng, Jiacheng Zhuo |
| Abstract | Recently, research on accelerated stochastic gradient descent methods (e.g., SVRG) has made exciting progress (e.g., linear convergence for strongly convex problems). However, the best-known methods (e.g., Katyusha) requires at least two auxiliary variables and two momentum parameters. In this paper, we propose a fast stochastic variance reduction gradient (FSVRG) method, in which we design a novel update rule with the Nesterov’s momentum and incorporate the technique of growing epoch size. FSVRG has only one auxiliary variable and one momentum weight, and thus it is much simpler and has much lower per-iteration complexity. We prove that FSVRG achieves linear convergence for strongly convex problems and the optimal $\mathcal{O}(1/T^2)$ convergence rate for non-strongly convex problems, where $T$ is the number of outer-iterations. We also extend FSVRG to directly solve the problems with non-smooth component functions, such as SVM. Finally, we empirically study the performance of FSVRG for solving various machine learning problems such as logistic regression, ridge regression, Lasso and SVM. Our results show that FSVRG outperforms the state-of-the-art stochastic methods, including Katyusha. |
| Tasks | |
| Published | 2017-03-23 |
| URL | http://arxiv.org/abs/1703.07948v2 |
| http://arxiv.org/pdf/1703.07948v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-stochastic-variance-reduced-gradient |
| Repo | |
| Framework | |
Avoidance of Manual Labeling in Robotic Autonomous Navigation Through Multi-Sensory Semi-Supervised Learning
| Title | Avoidance of Manual Labeling in Robotic Autonomous Navigation Through Multi-Sensory Semi-Supervised Learning |
| Authors | Junhong Xu, Shangyue Zhu, Hanqing Guo, Shaoen Wu |
| Abstract | Imitation learning holds the promise to address challenging robotic tasks such as autonomous navigation. It however requires a human supervisor to oversee the training process and send correct control commands to robots without feedback, which is always prone to error and expensive. To minimize human involvement and avoid manual labeling of data in the robotic autonomous navigation with imitation learning, this paper proposes a novel semi-supervised imitation learning solution based on a multi-sensory design. This solution includes a suboptimal sensor policy based on sensor fusion to automatically label states encountered by a robot to avoid human supervision during training. In addition, a recording policy is developed to throttle the adversarial affect of learning too much from the suboptimal sensor policy. This solution allows the robot to learn a navigation policy in a self-supervised manner. With extensive experiments in indoor environments, this solution can achieve near human performance in most of the tasks and even surpasses human performance in case of unexpected events such as hardware failures or human operation errors. To best of our knowledge, this is the first work that synthesizes sensor fusion and imitation learning to enable robotic autonomous navigation in the real world without human supervision. |
| Tasks | Autonomous Navigation, Imitation Learning, Sensor Fusion |
| Published | 2017-09-22 |
| URL | http://arxiv.org/abs/1709.07911v4 |
| http://arxiv.org/pdf/1709.07911v4.pdf | |
| PWC | https://paperswithcode.com/paper/avoidance-of-manual-labeling-in-robotic |
| Repo | |
| Framework | |
Zero-Shot Deep Domain Adaptation
| Title | Zero-Shot Deep Domain Adaptation |
| Authors | Kuan-Chuan Peng, Ziyan Wu, Jan Ernst |
| Abstract | Domain adaptation is an important tool to transfer knowledge about a task (e.g. classification) learned in a source domain to a second, or target domain. Current approaches assume that task-relevant target-domain data is available during training. We demonstrate how to perform domain adaptation when no such task-relevant target-domain data is available. To tackle this issue, we propose zero-shot deep domain adaptation (ZDDA), which uses privileged information from task-irrelevant dual-domain pairs. ZDDA learns a source-domain representation which is not only tailored for the task of interest but also close to the target-domain representation. Therefore, the source-domain task of interest solution (e.g. a classifier for classification tasks) which is jointly trained with the source-domain representation can be applicable to both the source and target representations. Using the MNIST, Fashion-MNIST, NIST, EMNIST, and SUN RGB-D datasets, we show that ZDDA can perform domain adaptation in classification tasks without access to task-relevant target-domain training data. We also extend ZDDA to perform sensor fusion in the SUN RGB-D scene classification task by simulating task-relevant target-domain representations with task-relevant source-domain data. To the best of our knowledge, ZDDA is the first domain adaptation and sensor fusion method which requires no task-relevant target-domain data. The underlying principle is not particular to computer vision data, but should be extensible to other domains. |
| Tasks | Domain Adaptation, Scene Classification, Sensor Fusion |
| Published | 2017-07-06 |
| URL | http://arxiv.org/abs/1707.01922v5 |
| http://arxiv.org/pdf/1707.01922v5.pdf | |
| PWC | https://paperswithcode.com/paper/zero-shot-deep-domain-adaptation |
| Repo | |
| Framework | |
Learning End-to-end Multimodal Sensor Policies for Autonomous Navigation
| Title | Learning End-to-end Multimodal Sensor Policies for Autonomous Navigation |
| Authors | Guan-Horng Liu, Avinash Siravuru, Sai Prabhakar, Manuela Veloso, George Kantor |
| Abstract | Multisensory polices are known to enhance both state estimation and target tracking. However, in the space of end-to-end sensorimotor control, this multi-sensor outlook has received limited attention. Moreover, systematic ways to make policies robust to partial sensor failure are not well explored. In this work, we propose a specific customization of Dropout, called \textit{Sensor Dropout}, to improve multisensory policy robustness and handle partial failure in the sensor-set. We also introduce an additional auxiliary loss on the policy network in order to reduce variance in the band of potential multi- and uni-sensory policies to reduce jerks during policy switching triggered by an abrupt sensor failure or deactivation/activation. Finally, through the visualization of gradients, we show that the learned policies are conditioned on the same latent states representation despite having diverse observations spaces - a hallmark of true sensor-fusion. Simulation results of the multisensory policy, as visualized in TORCS racing game, can be seen here: https://youtu.be/QAK2lcXjNZc. |
| Tasks | Autonomous Navigation, Sensor Fusion |
| Published | 2017-05-30 |
| URL | http://arxiv.org/abs/1705.10422v2 |
| http://arxiv.org/pdf/1705.10422v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-end-to-end-multimodal-sensor |
| Repo | |
| Framework | |
