October 17, 2019

3001 words 15 mins read

Paper Group ANR 732

Diffusion Based Network Embedding. Model Aggregation via Good-Enough Model Spaces. Improving Implicit Discourse Relation Classification by Modeling Inter-dependencies of Discourse Units in a Paragraph. GAN-EM: GAN based EM learning framework. Capturing Ambiguity in Crowdsourcing Frame Disambiguation. Tracing in 2D to Reduce the Annotation Effort fo …

Diffusion Based Network Embedding


Title	Diffusion Based Network Embedding
Authors	Yong Shi, Minglong Lei, Peng Zhang, Lingfeng Niu
Abstract	In network embedding, random walks play a fundamental role in preserving network structures. However, random walk based embedding methods have two limitations. First, random walk methods are fragile when the sampling frequency or the number of node sequences changes. Second, in disequilibrium networks such as highly biases networks, random walk methods often perform poorly due to the lack of global network information. In order to solve the limitations, we propose in this paper a network diffusion based embedding method. To solve the first limitation, our method employs a diffusion driven process to capture both depth information and breadth information. The time dimension is also attached to node sequences that can strengthen information preserving. To solve the second limitation, our method uses the network inference technique based on cascades to capture the global network information. To verify the performance, we conduct experiments on node classification tasks using the learned representations. Results show that compared with random walk based methods, diffusion based models are more robust when samplings under each node is rare. We also conduct experiments on a highly imbalanced network. Results shows that the proposed model are more robust under the biased network structure.
Tasks	Network Embedding, Node Classification
Published	2018-05-09
URL	http://arxiv.org/abs/1805.03504v2
PDF	http://arxiv.org/pdf/1805.03504v2.pdf
PWC	https://paperswithcode.com/paper/diffusion-based-network-embedding
Repo
Framework

Model Aggregation via Good-Enough Model Spaces


Title	Model Aggregation via Good-Enough Model Spaces
Authors	Neel Guha, Virginia Smith
Abstract	In many applications, the training data for a machine learning task is partitioned across multiple nodes, and aggregating this data may be infeasible due to communication, privacy, or storage constraints. Existing distributed optimization methods for learning global models in these settings typically aggregate local updates from each node in an iterative fashion. However, these approaches require many rounds of communication between nodes, and assume that updates can be synchronously shared across a connected network. In this work, we present Good-Enough Model Spaces (GEMS), a novel framework for learning a global model by carefully intersecting the sets of “good-enough” models across each node. Our approach utilizes minimal communication and does not require sharing of data between nodes. We present methods for learning both convex models and neural networks within this framework and discuss how small samples of held-out data can be used for post-learning fine-tuning. In experiments on image and medical datasets, our approach on average improves upon other baseline aggregation techniques such as ensembling or model averaging by as much as 15 points (accuracy).
Tasks	Distributed Optimization, Sentiment Analysis
Published	2018-05-20
URL	https://arxiv.org/abs/1805.07782v3
PDF	https://arxiv.org/pdf/1805.07782v3.pdf
PWC	https://paperswithcode.com/paper/knowledge-aggregation-via-good-enough-model
Repo
Framework

Improving Implicit Discourse Relation Classification by Modeling Inter-dependencies of Discourse Units in a Paragraph


Title	Improving Implicit Discourse Relation Classification by Modeling Inter-dependencies of Discourse Units in a Paragraph
Authors	Zeyu Dai, Ruihong Huang
Abstract	We argue that semantic meanings of a sentence or clause can not be interpreted independently from the rest of a paragraph, or independently from all discourse relations and the overall paragraph-level discourse structure. With the goal of improving implicit discourse relation classification, we introduce a paragraph-level neural networks that model inter-dependencies between discourse units as well as discourse relation continuity and patterns, and predict a sequence of discourse relations in a paragraph. Experimental results show that our model outperforms the previous state-of-the-art systems on the benchmark corpus of PDTB.
Tasks	Implicit Discourse Relation Classification, Relation Classification
Published	2018-04-16
URL	http://arxiv.org/abs/1804.05918v1
PDF	http://arxiv.org/pdf/1804.05918v1.pdf
PWC	https://paperswithcode.com/paper/improving-implicit-discourse-relation
Repo
Framework

GAN-EM: GAN based EM learning framework


Title	GAN-EM: GAN based EM learning framework
Authors	Wentian Zhao, Shaojie Wang, Zhihuai Xie, Jing Shi, Chenliang Xu
Abstract	Expectation maximization (EM) algorithm is to find maximum likelihood solution for models having latent variables. A typical example is Gaussian Mixture Model (GMM) which requires Gaussian assumption, however, natural images are highly non-Gaussian so that GMM cannot be applied to perform clustering task on pixel space. To overcome such limitation, we propose a GAN based EM learning framework that can maximize the likelihood of images and estimate the latent variables with only the constraint of L-Lipschitz continuity. We call this model GAN-EM, which is a framework for image clustering, semi-supervised classification and dimensionality reduction. In M-step, we design a novel loss function for discriminator of GAN to perform maximum likelihood estimation (MLE) on data with soft class label assignments. Specifically, a conditional generator captures data distribution for $K$ classes, and a discriminator tells whether a sample is real or fake for each class. Since our model is unsupervised, the class label of real data is regarded as latent variable, which is estimated by an additional network (E-net) in E-step. The proposed GAN-EM achieves state-of-the-art clustering and semi-supervised classification results on MNIST, SVHN and CelebA, as well as comparable quality of generated images to other recently developed generative models.
Tasks	Dimensionality Reduction, Image Clustering
Published	2018-12-02
URL	http://arxiv.org/abs/1812.00335v1
PDF	http://arxiv.org/pdf/1812.00335v1.pdf
PWC	https://paperswithcode.com/paper/gan-em-gan-based-em-learning-framework
Repo
Framework

Capturing Ambiguity in Crowdsourcing Frame Disambiguation


Title	Capturing Ambiguity in Crowdsourcing Frame Disambiguation
Authors	Anca Dumitrache, Lora Aroyo, Chris Welty
Abstract	FrameNet is a computational linguistics resource composed of semantic frames, high-level concepts that represent the meanings of words. In this paper, we present an approach to gather frame disambiguation annotations in sentences using a crowdsourcing approach with multiple workers per sentence to capture inter-annotator disagreement. We perform an experiment over a set of 433 sentences annotated with frames from the FrameNet corpus, and show that the aggregated crowd annotations achieve an F1 score greater than 0.67 as compared to expert linguists. We highlight cases where the crowd annotation was correct even though the expert is in disagreement, arguing for the need to have multiple annotators per sentence. Most importantly, we examine cases in which crowd workers could not agree, and demonstrate that these cases exhibit ambiguity, either in the sentence, frame, or the task itself, and argue that collapsing such cases to a single, discrete truth value (i.e. correct or incorrect) is inappropriate, creating arbitrary targets for machine learning.
Tasks
Published	2018-05-01
URL	http://arxiv.org/abs/1805.00270v1
PDF	http://arxiv.org/pdf/1805.00270v1.pdf
PWC	https://paperswithcode.com/paper/capturing-ambiguity-in-crowdsourcing-frame
Repo
Framework

Tracing in 2D to Reduce the Annotation Effort for 3D Deep Delineation


Title	Tracing in 2D to Reduce the Annotation Effort for 3D Deep Delineation
Authors	Mateusz Koziński, Agata Mosinska, Mathieu Salzmann, Pascal Fua
Abstract	The difficulty of obtaining annotations to build training databases still slows down the adoption of recent deep learning approaches for biomedical image analysis. In this paper, we show that we can train a Deep Net to perform 3D volumetric delineation given only 2D annotations in Maximum Intensity Projections (MIP). As a consequence, we can decrease the amount of time spent annotating by a factor of two while maintaining similar performance. Our approach is inspired by space carving, a classical technique of reconstructing complex 3D shapes from arbitrarily-positioned cameras. We will demonstrate its effectiveness on 3D light microscopy images of neurons and retinal blood vessels and on Magnetic Resonance Angiography (MRA) brain scans.
Tasks
Published	2018-11-26
URL	http://arxiv.org/abs/1811.10508v1
PDF	http://arxiv.org/pdf/1811.10508v1.pdf
PWC	https://paperswithcode.com/paper/tracing-in-2d-to-reduce-the-annotation-effort
Repo
Framework

A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation


Title	A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation
Authors	Juraj Juraska, Panagiotis Karagiannis, Kevin K. Bowden, Marilyn A. Walker
Abstract	Natural language generation lies at the core of generative dialogue systems and conversational agents. We describe an ensemble neural language generator, and present several novel methods for data representation and augmentation that yield improved results in our model. We test the model on three datasets in the restaurant, TV and laptop domains, and report both objective and subjective evaluations of our best model. Using a range of automatic metrics, as well as human evaluators, we show that our approach achieves better results than state-of-the-art models on the same datasets.
Tasks	Data-to-Text Generation, Text Generation
Published	2018-05-16
URL	http://arxiv.org/abs/1805.06553v1
PDF	http://arxiv.org/pdf/1805.06553v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-ensemble-model-with-slot-alignment-for
Repo
Framework

Theory of Cognitive Relativity: A Promising Paradigm for True AI


Title	Theory of Cognitive Relativity: A Promising Paradigm for True AI
Authors	Yujian Li
Abstract	The rise of deep learning has brought artificial intelligence (AI) to the forefront. The ultimate goal of AI is to realize machines with human mind and consciousness, but existing achievements mainly simulate intelligent behavior on computer platforms. These achievements all belong to weak AI rather than strong AI. How to achieve strong AI is not known yet in the field of intelligence science. Currently, this field is calling for a new paradigm, especially Theory of Cognitive Relativity (TCR). The TCR aims to summarize a simple and elegant set of first principles about the nature of intelligence, at least including the Principle of World’s Relativity and the Principle of Symbol’s Relativity. The Principle of World’s Relativity states that the subjective world an intelligent agent can observe is strongly constrained by the way it perceives the objective world. The Principle of Symbol’s Relativity states that an intelligent agent can use any physical symbol system to express what it observes in its subjective world. The two principles are derived from scientific facts and life experience. Thought experiments show that they are important to understand high-level intelligence and necessary to establish a scientific theory of mind and consciousness. Rather than brain-like intelligence, the TCR indeed advocates a promising change in direction to realize true AI, i.e. artificial general intelligence or artificial consciousness, particularly different from humans’ and animals’. Furthermore, a TCR creed has been presented and extended to reveal the secrets of consciousness and to guide realization of conscious machines. In the sense that true AI could be diversely implemented in a brain-different way, the TCR would probably drive an intelligence revolution in combination with some additional first principles.
Tasks
Published	2018-12-01
URL	http://arxiv.org/abs/1812.00136v3
PDF	http://arxiv.org/pdf/1812.00136v3.pdf
PWC	https://paperswithcode.com/paper/theory-of-cognitive-relativity-a-promising
Repo
Framework

Prior-Knowledge and Attention-based Meta-Learning for Few-Shot Learning


Title	Prior-Knowledge and Attention-based Meta-Learning for Few-Shot Learning
Authors	Yunxiao Qin, Weiguo Zhang, Chenxu Zhao, Zezheng Wang, Xiangyu Zhu, Guojun Qi, Jingping Shi, Zhen Lei
Abstract	Recently, meta-learning has been shown as a promising way to solve few-shot learning. In this paper, inspired by the human cognition process which utilizes both prior-knowledge and vision attention in learning new knowledge, we present a novel paradigm of meta-learning approach with three developments to introduce attention mechanism and prior-knowledge for meta-learning. In our approach, prior-knowledge is responsible for helping meta-learner expressing the input data into high-level representation space, and attention mechanism enables meta-learner focusing on key features of the data in the representation space. Compared with existing meta-learning approaches that pay little attention to prior-knowledge and vision attention, our approach alleviates the meta-learner’s few-shot cognition burden. Furthermore, a Task-Over-Fitting (TOF) problem, which indicates that the meta-learner has poor generalization on different K-shot learning tasks, is discovered and we propose a Cross-Entropy across Tasks (CET) metric to model and solve the TOF problem. Extensive experiments demonstrate that we improve the meta-learner with state-of-the-art performance on several few-shot learning benchmarks, and at the same time the TOF problem can also be released greatly.
Tasks	Few-Shot Learning, Meta-Learning
Published	2018-12-11
URL	https://arxiv.org/abs/1812.04955v5
PDF	https://arxiv.org/pdf/1812.04955v5.pdf
PWC	https://paperswithcode.com/paper/rethink-and-redesign-meta-learning
Repo
Framework

Iterative Interaction Training for Segmentation Editing Networks


Title	Iterative Interaction Training for Segmentation Editing Networks
Authors	Gustav Bredell, Christine Tanner, Ender Konukoglu
Abstract	Automatic segmentation has great potential to facilitate morphological measurements while simultaneously increasing efficiency. Nevertheless often users want to edit the segmentation to their own needs and will need different tools for this. There has been methods developed to edit segmentations of automatic methods based on the user input, primarily for binary segmentations. Here however, we present an unique training strategy for convolutional neural networks (CNNs) trained on top of an automatic method to enable interactive segmentation editing that is not limited to binary segmentation. By utilizing a robot-user during training, we closely mimic realistic use cases to achieve optimal editing performance. In addition, we show that an increase of the iterative interactions during the training process up to ten improves the segmentation editing performance substantially. Furthermore, we compare our segmentation editing CNN (interCNN) to state-of-the-art interactive segmentation algorithms and show a superior or on par performance.
Tasks	Interactive Segmentation
Published	2018-07-23
URL	http://arxiv.org/abs/1807.08555v1
PDF	http://arxiv.org/pdf/1807.08555v1.pdf
PWC	https://paperswithcode.com/paper/iterative-interaction-training-for
Repo
Framework

SATR-DL: Improving Surgical Skill Assessment and Task Recognition in Robot-assisted Surgery with Deep Neural Networks


Title	SATR-DL: Improving Surgical Skill Assessment and Task Recognition in Robot-assisted Surgery with Deep Neural Networks
Authors	Ziheng Wang, Ann Majewicz Fey
Abstract	Purpose: This paper focuses on an automated analysis of surgical motion profiles for objective skill assessment and task recognition in robot-assisted surgery. Existing techniques heavily rely on conventional statistic measures or shallow modelings based on hand-engineered features and gesture segmentation. Such developments require significant expert knowledge, are prone to errors, and are less efficient in online adaptive training systems. Methods: In this work, we present an efficient analytic framework with a parallel deep learning architecture, SATR-DL, to assess trainee expertise and recognize surgical training activity. Through an end-to-end learning technique, abstract information of spatial representations and temporal dynamics is jointly obtained directly from raw motion sequences. Results: By leveraging a shared high-level representation learning, the resulting model is successful in the recognition of trainee skills and surgical tasks, suturing, needle-passing, and knot-tying. Meanwhile, we explore the use of ensemble in classification at the trial level, where the SATR-DL outperforms state-of-the-art performance by achieving accuracies of 0.960 and 1.000 in skill assessment and task recognition, respectively. Conclusion: This study highlights the potential of SATR-DL to provide improvements for an efficient data-driven assessment in intelligent robotic surgery.
Tasks	Representation Learning
Published	2018-06-15
URL	http://arxiv.org/abs/1806.05798v1
PDF	http://arxiv.org/pdf/1806.05798v1.pdf
PWC	https://paperswithcode.com/paper/satr-dl-improving-surgical-skill-assessment
Repo
Framework

Deep Learning with Mixed Supervision for Brain Tumor Segmentation


Title	Deep Learning with Mixed Supervision for Brain Tumor Segmentation
Authors	Pawel Mlynarski, Hervé Delingette, Antonio Criminisi, Nicholas Ayache
Abstract	Most of the current state-of-the-art methods for tumor segmentation are based on machine learning models trained on manually segmented images. This type of training data is particularly costly, as manual delineation of tumors is not only time-consuming but also requires medical expertise. On the other hand, images with a provided global label (indicating presence or absence of a tumor) are less informative but can be obtained at a substantially lower cost. In this paper, we propose to use both types of training data (fully-annotated and weakly-annotated) to train a deep learning model for segmentation. The idea of our approach is to extend segmentation networks with an additional branch performing image-level classification. The model is jointly trained for segmentation and classification tasks in order to exploit information contained in weakly-annotated images while preventing the network to learn features which are irrelevant for the segmentation task. We evaluate our method on the challenging task of brain tumor segmentation in Magnetic Resonance images from BRATS 2018 challenge. We show that the proposed approach provides a significant improvement of segmentation performance compared to the standard supervised learning. The observed improvement is proportional to the ratio between weakly-annotated and fully-annotated images available for training.
Tasks	Brain Tumor Segmentation
Published	2018-12-10
URL	http://arxiv.org/abs/1812.04571v1
PDF	http://arxiv.org/pdf/1812.04571v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-with-mixed-supervision-for
Repo
Framework

Multi-Task Generative Adversarial Network for Handling Imbalanced Clinical Data


Title	Multi-Task Generative Adversarial Network for Handling Imbalanced Clinical Data
Authors	Mina Rezaei, Haojin Yang, Christoph Meinel
Abstract	We propose a new generative adversarial architecture to mitigate imbalance data problem for the task of medical image semantic segmentation where the majority of pixels belong to a healthy region and few belong to lesion or non-health region. A model trained with imbalanced data tends to bias towards healthy data which is not desired in clinical applications. We design a new conditional GAN with two components: a generative model and a discriminative model to mitigate imbalanced data problem through selective weighted loss. While the generator is trained on sequential magnetic resonance images (MRI) to learn semantic segmentation and disease classification, the discriminator classifies whether a generated output is real or fake. The proposed architecture achieved state-of-the-art results on ACDC-2017 for cardiac segmentation and diseases classification. We have achieved competitive results on BraTS-2017 for brain tumor segmentation and brain diseases classification.
Tasks	Brain Tumor Segmentation, Cardiac Segmentation, Semantic Segmentation
Published	2018-11-22
URL	http://arxiv.org/abs/1811.10419v1
PDF	http://arxiv.org/pdf/1811.10419v1.pdf
PWC	https://paperswithcode.com/paper/multi-task-generative-adversarial-network-for
Repo
Framework

On The Stability of Interpretable Models


Title	On The Stability of Interpretable Models
Authors	Riccardo Guidotti, Salvatore Ruggieri
Abstract	Interpretable classification models are built with the purpose of providing a comprehensible description of the decision logic to an external oversight agent. When considered in isolation, a decision tree, a set of classification rules, or a linear model, are widely recognized as human-interpretable. However, such models are generated as part of a larger analytical process. Bias in data collection and preparation, or in model’s construction may severely affect the accountability of the design process. We conduct an experimental study of the stability of interpretable models with respect to feature selection, instance selection, and model selection. Our conclusions should raise awareness and attention of the scientific community on the need of a stability impact assessment of interpretable models.
Tasks	Feature Selection, Model Selection
Published	2018-10-22
URL	http://arxiv.org/abs/1810.09352v2
PDF	http://arxiv.org/pdf/1810.09352v2.pdf
PWC	https://paperswithcode.com/paper/assessing-the-stability-of-interpretable
Repo
Framework

Spoken Language Understanding on the Edge


Title	Spoken Language Understanding on the Edge
Authors	Alaa Saade, Alice Coucke, Alexandre Caulier, Joseph Dureau, Adrien Ball, Théodore Bluche, David Leroy, Clément Doumouro, Thibault Gisselbrecht, Francesco Caltagirone, Thibaut Lavril, Maël Primet
Abstract	We consider the problem of performing Spoken Language Understanding (SLU) on small devices typical of IoT applications. Our contributions are twofold. First, we outline the design of an embedded, private-by-design SLU system and show that it has performance on par with cloud-based commercial solutions. Second, we release the datasets used in our experiments in the interest of reproducibility and in the hope that they can prove useful to the SLU community.
Tasks	Spoken Language Understanding
Published	2018-10-30
URL	https://arxiv.org/abs/1810.12735v2
PDF	https://arxiv.org/pdf/1810.12735v2.pdf
PWC	https://paperswithcode.com/paper/spoken-language-understanding-on-the-edge
Repo
Framework