Paper Group ANR 979
Contextual Bandits Evolving Over Finite Time. Cross-Domain Conditional Generative Adversarial Networks for Stereoscopic Hyperrealism in Surgical Training. Making Neural Machine Reading Comprehension Faster. Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs. Machine Reading Comprehension for Answer Re-Ranking i …
Contextual Bandits Evolving Over Finite Time
| Title | Contextual Bandits Evolving Over Finite Time |
| Authors | Harsh Deshpande, Vishal Jain, Sharayu Moharir |
| Abstract | Contextual bandits have the same exploration-exploitation trade-off as standard multi-armed bandits. On adding positive externalities that decay with time, this problem becomes much more difficult as wrong decisions at the start are hard to recover from. We explore existing policies in this setting and highlight their biases towards the inherent reward matrix. We propose a rejection based policy that achieves a low regret irrespective of the structure of the reward probability matrix. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.05956v1 |
| https://arxiv.org/pdf/1911.05956v1.pdf | |
| PWC | https://paperswithcode.com/paper/contextual-bandits-evolving-over-finite-time |
| Repo | |
| Framework | |
Cross-Domain Conditional Generative Adversarial Networks for Stereoscopic Hyperrealism in Surgical Training
| Title | Cross-Domain Conditional Generative Adversarial Networks for Stereoscopic Hyperrealism in Surgical Training |
| Authors | Sandy Engelhardt, Lalith Sharan, Matthias Karck, Raffaele De Simone, Ivo Wolf |
| Abstract | Phantoms for surgical training are able to mimic cutting and suturing properties and patient-individual shape of organs, but lack a realistic visual appearance that captures the heterogeneity of surgical scenes. In order to overcome this in endoscopic approaches, hyperrealistic concepts have been proposed to be used in an augmented reality-setting, which are based on deep image-to-image transformation methods. Such concepts are able to generate realistic representations of phantoms learned from real intraoperative endoscopic sequences. Conditioned on frames from the surgical training process, the learned models are able to generate impressive results by transforming unrealistic parts of the image (e.g.\ the uniform phantom texture is replaced by the more heterogeneous texture of the tissue). Image-to-image synthesis usually learns a mapping $G:X~\to~Y$ such that the distribution of images from $G(X)$ is indistinguishable from the distribution $Y$. However, it does not necessarily force the generated images to be consistent and without artifacts. In the endoscopic image domain this can affect depth cues and stereo consistency of a stereo image pair, which ultimately impairs surgical vision. We propose a cross-domain conditional generative adversarial network approach (GAN) that aims to generate more consistent stereo pairs. The results show substantial improvements in depth perception and realism evaluated by 3 domain experts and 3 medical students on a 3D monitor over the baseline method. In 84 of 90 instances our proposed method was preferred or rated equal to the baseline. |
| Tasks | Image Generation |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.10011v1 |
| https://arxiv.org/pdf/1906.10011v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-domain-conditional-generative |
| Repo | |
| Framework | |
Making Neural Machine Reading Comprehension Faster
| Title | Making Neural Machine Reading Comprehension Faster |
| Authors | Debajyoti Chatterjee |
| Abstract | This study aims at solving the Machine Reading Comprehension problem where questions have to be answered given a context passage. The challenge is to develop a computationally faster model which will have improved inference time. State of the art in many natural language understanding tasks, BERT model, has been used and knowledge distillation method has been applied to train two smaller models. The developed models are compared with other models which have been developed with the same intention. |
| Tasks | Machine Reading Comprehension, Reading Comprehension |
| Published | 2019-03-29 |
| URL | http://arxiv.org/abs/1904.00796v1 |
| http://arxiv.org/pdf/1904.00796v1.pdf | |
| PWC | https://paperswithcode.com/paper/making-neural-machine-reading-comprehension |
| Repo | |
| Framework | |
Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs
| Title | Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs |
| Authors | Zhibin Liu, Zheng-Yu Niu, Hua Wu, Haifeng Wang |
| Abstract | Two types of knowledge, triples from knowledge graphs and texts from documents, have been studied for knowledge aware open-domain conversation generation, in which graph paths can narrow down vertex candidates for knowledge selection decision, and texts can provide rich information for response generation. Fusion of a knowledge graph and texts might yield mutually reinforcing advantages, but there is less study on that. To address this challenge, we propose a knowledge aware chatting machine with three components, an augmented knowledge graph with both triples and texts, knowledge selector, and knowledge aware response generator. For knowledge selection on the graph, we formulate it as a problem of multi-hop graph reasoning to effectively capture conversation flow, which is more explainable and flexible in comparison with previous work. To fully leverage long text information that differentiates our graph from others, we improve a state of the art reasoning algorithm with machine reading comprehension technology. We demonstrate the effectiveness of our system on two datasets in comparison with state-of-the-art models. |
| Tasks | Knowledge Graphs, Machine Reading Comprehension, Reading Comprehension |
| Published | 2019-03-25 |
| URL | https://arxiv.org/abs/1903.10245v4 |
| https://arxiv.org/pdf/1903.10245v4.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-aware-conversation-generation-with |
| Repo | |
| Framework | |
Machine Reading Comprehension for Answer Re-Ranking in Customer Support Chatbots
| Title | Machine Reading Comprehension for Answer Re-Ranking in Customer Support Chatbots |
| Authors | Momchil Hardalov, Ivan Koychev, Preslav Nakov |
| Abstract | Recent advances in deep neural networks, language modeling and language generation have introduced new ideas to the field of conversational agents. As a result, deep neural models such as sequence-to-sequence, Memory Networks, and the Transformer have become key ingredients of state-of-the-art dialog systems. While those models are able to generate meaningful responses even in unseen situation, they need a lot of training data to build a reliable model. Thus, most real-world systems stuck to traditional approaches based on information retrieval and even hand-crafted rules, due to their robustness and effectiveness, especially for narrow-focused conversations. Here, we present a method that adapts a deep neural architecture from the domain of machine reading comprehension to re-rank the suggested answers from different models using the question as context. We train our model using negative sampling based on question-answer pairs from the Twitter Customer Support Dataset.The experimental results show that our re-ranking framework can improve the performance in terms of word overlap and semantics both for individual models as well as for model combinations. |
| Tasks | Information Retrieval, Language Modelling, Machine Reading Comprehension, Reading Comprehension, Text Generation |
| Published | 2019-02-12 |
| URL | http://arxiv.org/abs/1902.04574v2 |
| http://arxiv.org/pdf/1902.04574v2.pdf | |
| PWC | https://paperswithcode.com/paper/machine-reading-comprehension-for-answer-re |
| Repo | |
| Framework | |
Object as Distribution
| Title | Object as Distribution |
| Authors | Li Ding, Lex Fridman |
| Abstract | Object detection is a critical part of visual scene understanding. The representation of the object in the detection task has important implications on the efficiency and feasibility of annotation, robustness to occlusion, pose, lighting, and other visual sources of semantic uncertainty, and effectiveness in real-world applications (e.g., autonomous driving). Popular object representations include 2D and 3D bounding boxes, polygons, splines, pixels, and voxels. Each have their strengths and weakness. In this work, we propose a new representation of objects based on the bivariate normal distribution. This distribution-based representation has the benefit of robust detection of highly-overlapping objects and the potential for improved downstream tracking and instance segmentation tasks due to the statistical representation of object edges. We provide qualitative evaluation of this representation for the object detection task and quantitative evaluation of its use in a baseline algorithm for the instance segmentation task. |
| Tasks | Autonomous Driving, Instance Segmentation, Object Detection, Scene Understanding, Semantic Segmentation |
| Published | 2019-07-25 |
| URL | https://arxiv.org/abs/1907.12929v1 |
| https://arxiv.org/pdf/1907.12929v1.pdf | |
| PWC | https://paperswithcode.com/paper/object-as-distribution |
| Repo | |
| Framework | |
DeepSearch: Simple and Effective Blackbox Fuzzing of Deep Neural Networks
| Title | DeepSearch: Simple and Effective Blackbox Fuzzing of Deep Neural Networks |
| Authors | Fuyuan Zhang, Sankalan Pal Chowdhury, Maria Christakis |
| Abstract | Although deep neural networks have been successful in image classification, they are prone to adversarial attacks. To generate misclassified inputs, there has emerged a wide variety of techniques, such as black- and whitebox testing of neural networks. In this paper, we present DeepSearch, a novel blackbox-fuzzing technique for image classifiers. Despite its simplicity, DeepSearch is shown to be more effective in finding adversarial examples than closely related black- and whitebox approaches. DeepSearch is additionally able to generate the most subtle adversarial examples in comparison to these approaches. |
| Tasks | Image Classification |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.06296v1 |
| https://arxiv.org/pdf/1910.06296v1.pdf | |
| PWC | https://paperswithcode.com/paper/deepsearch-simple-and-effective-blackbox |
| Repo | |
| Framework | |
Predicting the properties of black holes merger remnants with Deep Neural Networks
| Title | Predicting the properties of black holes merger remnants with Deep Neural Networks |
| Authors | Leïla Haegel, Sascha Husa |
| Abstract | We present the first estimation of the mass and spin of Kerr black holes resulting from the coalescence of binary black holes using a deep neural network. The network is trained on the full publicly available catalog of numerical simulations of gravitational waves emission by binary black hole systems. The network prediction for non-precessing binaries as well as precessing binaries is compared with existing fits in the LIGO-Virgo software package when existing. For the non-precessing case, the absolute error distribution has a root mean square error of $2.6 \cdot 10^{-3}$ for the final mass (twice lower than the existing fits) and $3 \cdot 10^{-3}$ for the final spin (similarly to the existing fits). We also estimate of the final mass in the precessing case, where we obtain a RMSE of $1 \cdot 10^{-3}$ of the absolute error distribution. It is $8 \cdot 10^{-3}$ when predicting the spin of the black hole resulting from a precessing binary, against $1.1 \cdot 10^{-2}$ for the existing fits. |
| Tasks | |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01496v1 |
| https://arxiv.org/pdf/1911.01496v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-the-properties-of-black-holes |
| Repo | |
| Framework | |
PLIT: An alignment-free computational tool for identification of long non-coding RNAs in plant transcriptomic datasets
| Title | PLIT: An alignment-free computational tool for identification of long non-coding RNAs in plant transcriptomic datasets |
| Authors | S. Deshpande, J. Shuttleworth, J. Yang, S. Taramonli, M. England |
| Abstract | Long non-coding RNAs (lncRNAs) are a class of non-coding RNAs which play a significant role in several biological processes. RNA-seq based transcriptome sequencing has been extensively used for identification of lncRNAs. However, accurate identification of lncRNAs in RNA-seq datasets is crucial for exploring their characteristic functions in the genome as most coding potential computation (CPC) tools fail to accurately identify them in transcriptomic data. Well-known CPC tools such as CPC2, lncScore, CPAT are primarily designed for prediction of lncRNAs based on the GENCODE, NONCODE and CANTATAdb databases. The prediction accuracy of these tools often drops when tested on transcriptomic datasets. This leads to higher false positive results and inaccuracy in the function annotation process. In this study, we present a novel tool, PLIT, for the identification of lncRNAs in plants RNA-seq datasets. PLIT implements a feature selection method based on L1 regularization and iterative Random Forests (iRF) classification for selection of optimal features. Based on sequence and codon-bias features, it classifies the RNA-seq derived FASTA sequences into coding or long non-coding transcripts. Using L1 regularization, 31 optimal features were obtained based on lncRNA and protein-coding transcripts from 8 plant species. The performance of the tool was evaluated on 7 plant RNA-seq datasets using 10-fold cross-validation. The analysis exhibited superior accuracy when evaluated against currently available state-of-the-art CPC tools. |
| Tasks | Feature Selection |
| Published | 2019-02-12 |
| URL | http://arxiv.org/abs/1902.05064v1 |
| http://arxiv.org/pdf/1902.05064v1.pdf | |
| PWC | https://paperswithcode.com/paper/plit-an-alignment-free-computational-tool-for |
| Repo | |
| Framework | |
Improving IT Support by Enhancing Incident Management Process with Multi-modal Analysis
| Title | Improving IT Support by Enhancing Incident Management Process with Multi-modal Analysis |
| Authors | Atri Mandal, Shivali Agarwal, Nikhil Malhotra, Giriprasad Sridhara, Anupama Ray, Daivik Swarup |
| Abstract | IT support services industry is going through a major transformation with AI becoming commonplace. There has been a lot of effort in the direction of automation at every human touchpoint in the IT support processes. Incident management is one such process which has been a beacon process for AI based automation. The vision is to automate the process from the time an incident/ticket arrives till it is resolved and closed. While text is the primary mode of communicating the incidents, there has been a growing trend of using alternate modalities like image to communicate the problem. A large fraction of IT support tickets today contain attached image data in the form of screenshots, log messages, invoices and so on. These attachments help in better explanation of the problem which aids in faster resolution. Anybody who aspires to provide AI based IT support, it is essential to build systems which can handle multi-modal content. In this paper we present how incident management in IT support domain can be made much more effective using multi-modal analysis. The information extracted from different modalities are correlated to enrich the information in the ticket and used for better ticket routing and resolution. We evaluate our system using about 25000 real tickets containing attachments from selected problem areas. Our results demonstrate significant improvements in both routing and resolution with the use of multi-modal ticket analysis compared to only text based analysis. |
| Tasks | |
| Published | 2019-08-04 |
| URL | https://arxiv.org/abs/1908.01351v1 |
| https://arxiv.org/pdf/1908.01351v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-it-support-by-enhancing-incident |
| Repo | |
| Framework | |
Data Augmentation Using GANs
| Title | Data Augmentation Using GANs |
| Authors | Fabio Henrique Kiyoiti dos Santos Tanaka, Claus Aranha |
| Abstract | In this paper we propose the use of Generative Adversarial Networks (GAN) to generate artificial training data for machine learning tasks. The generation of artificial training data can be extremely useful in situations such as imbalanced data sets, performing a role similar to SMOTE or ADASYN. It is also useful when the data contains sensitive information, and it is desirable to avoid using the original data set as much as possible (example: medical data). We test our proposal on benchmark data sets using different network architectures, and show that a Decision Tree (DT) classifier trained using the training data generated by the GAN reached the same, (and surprisingly sometimes better), accuracy and recall than a DT trained on the original data set. |
| Tasks | Data Augmentation |
| Published | 2019-04-19 |
| URL | http://arxiv.org/abs/1904.09135v1 |
| http://arxiv.org/pdf/1904.09135v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-augmentation-using-gans |
| Repo | |
| Framework | |
Learning Algebraic Models of Quantum Entanglement
| Title | Learning Algebraic Models of Quantum Entanglement |
| Authors | Hamza Jaffali, Luke Oeding |
| Abstract | We give a thorough overview of supervised learning and network design for learning membership on algebraic varieties via deep neural networks. We show how artificial neural networks can be trained to predict the entanglement type for quantum states. We give examples for detecting degenerate states, as well as border rank classification for up to 5 binary qubits and 3 qutrits (ternary qubits). |
| Tasks | |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10247v1 |
| https://arxiv.org/pdf/1908.10247v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-algebraic-models-of-quantum |
| Repo | |
| Framework | |
The Channel Attention based Context Encoder Network for Inner Limiting Membrane Detection
| Title | The Channel Attention based Context Encoder Network for Inner Limiting Membrane Detection |
| Authors | Hao Qiu, Zaiwang Gu, Lei Mou, Xiaoqian Mao, Liyang Fang, Yitian Zhao, Jiang Liu, Jun Cheng |
| Abstract | The optic disc segmentation is an important step for retinal image-based disease diagnosis such as glaucoma. The inner limiting membrane (ILM) is the first boundary in the OCT, which can help to extract the retinal pigment epithelium (RPE) through gradient edge information to locate the boundary of the optic disc. Thus, the ILM layer segmentation is of great importance for optic disc localization. In this paper, we build a new optic disc centered dataset from 20 volunteers and manually annotated the ILM boundary in each OCT scan as ground-truth. We also propose a channel attention based context encoder network modified from the CE-Net to segment the optic disc. It mainly contains three phases: the encoder module, the channel attention based context encoder module, and the decoder module. Finally, we demonstrate that our proposed method achieves state-of-the-art disc segmentation performance on our dataset mentioned above. |
| Tasks | |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.04413v1 |
| https://arxiv.org/pdf/1908.04413v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-channel-attention-based-context-encoder |
| Repo | |
| Framework | |
Decentralized Stochastic Gradient Tracking for Non-convex Empirical Risk Minimization
| Title | Decentralized Stochastic Gradient Tracking for Non-convex Empirical Risk Minimization |
| Authors | Jiaqi Zhang, Keyou You |
| Abstract | This paper studies a decentralized stochastic gradient tracking (DSGT) algorithm for a non-convex empirical risk minimization problem over a peer-to-peer network, which is in sharp contrast to the existing DSGT works only for the convex problem. To handle the variance among decentralized datasets, the mini-batch in each node of the network is designed to be proportional to the size of its local dataset. We explicitly evaluate the convergence rate of DSGT in terms of algebraic connectivity of the network, mini-batch size, and learning rate. Importantly, our theoretical rate has an optimal dependence on the algebraic connectivity and can exactly recover the rate of the centralized stochastic gradient method. Moreover, we demonstrate that DSGT could achieve a linear speedup while a sublinear speedup is also possible, depending on the problem at hand. Numerical experiments for neural networks and logistic regression problems on CIFAR-10 finally illustrate the advantages of DSGT for decentralized training. |
| Tasks | |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.02712v2 |
| https://arxiv.org/pdf/1909.02712v2.pdf | |
| PWC | https://paperswithcode.com/paper/decentralized-stochastic-gradient-tracking |
| Repo | |
| Framework | |
Weighted second-order cone programming twin support vector machine for imbalanced data classification
| Title | Weighted second-order cone programming twin support vector machine for imbalanced data classification |
| Authors | Saeideh Roshanfekr, Shahriar Esmaeili, Hassan Ataeian, Ali Amiri |
| Abstract | We propose a method of using a Weighted second-order cone programming twin support vector machine (WSOCP-TWSVM) for imbalanced data classification. This method constructs a graph based under-sampling method which is utilized to remove outliers and reduce the dispensable majority samples. Then, appropriate weights are set in order to decrease the impact of samples of the majority class and increase the effect of the minority class in the optimization formula of the classifier. These weights are embedded in the optimization problem of the Second Order Cone Programming (SOCP) Twin Support Vector Machine formulations. This method is tested, and its performance is compared to previous methods on standard datasets. Results of experiments confirm the feasibility and efficiency of the proposed method. |
| Tasks | |
| Published | 2019-04-26 |
| URL | https://arxiv.org/abs/1904.11634v2 |
| https://arxiv.org/pdf/1904.11634v2.pdf | |
| PWC | https://paperswithcode.com/paper/weighted-second-order-cone-programming-twin |
| Repo | |
| Framework | |
