Paper Group ANR 1343
Efficient Structurally-Strengthened Generative Adversarial Network for MRI Reconstruction. Computer aided detection of tuberculosis on chest radiographs: An evaluation of the CAD4TB v6 system. Multi-Agent Deep Reinforcement Learning with Adaptive Policies. SocialIQA: Commonsense Reasoning about Social Interactions. GENN: Predicting Correlated Drug- …
Efficient Structurally-Strengthened Generative Adversarial Network for MRI Reconstruction
| Title | Efficient Structurally-Strengthened Generative Adversarial Network for MRI Reconstruction |
| Authors | Wenzhong Zhou, Huiqian Du, Wenbo Mei, Liping Fang |
| Abstract | Compressed sensing based magnetic resonance imaging (CS-MRI) provides an efficient way to reduce scanning time of MRI. Recently deep learning has been introduced into CS-MRI to further improve the image quality and shorten reconstruction time. In this paper, we propose an efficient structurally strengthened Generative Adversarial Network, termed ESSGAN, for reconstructing MR images from highly under-sampled k-space data. ESSGAN consists of a structurally strengthened generator (SG) and a discriminator. In SG, we introduce strengthened connections (SCs) to improve the utilization of the feature maps between the proposed strengthened convolutional autoencoders (SCAEs), where each SCAE is a variant of a typical convolutional autoencoder. In addition, we creatively introduce a residual in residual block (RIRB) to SG. RIRB increases the depth of SG, thus enhances feature expression ability of SG. Moreover, it can give the encoder blocks and the decoder blocks richer texture features. To further reduce artifacts and preserve more image details, we introduce an enhanced structural loss to SG. ESSGAN can provide higher image quality with less model parameters than the state-of-the-art deep learning-based methods at different undersampling rates of different subsampling masks, and reconstruct a 256*256 MR image in tens of milliseconds. |
| Tasks | |
| Published | 2019-08-11 |
| URL | https://arxiv.org/abs/1908.03858v1 |
| https://arxiv.org/pdf/1908.03858v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-structurally-strengthened |
| Repo | |
| Framework | |
Computer aided detection of tuberculosis on chest radiographs: An evaluation of the CAD4TB v6 system
| Title | Computer aided detection of tuberculosis on chest radiographs: An evaluation of the CAD4TB v6 system |
| Authors | Keelin Murphy, Shifa Salman Habib, Syed Mohammad Asad Zaidi, Saira Khowaja, Aamir Khan, Jaime Melendez, Ernst T. Scholten, Farhan Amad, Steven Schalekamp, Maurits Verhagen, Rick H. H. M. Philipsen, Annet Meijers, Bram van Ginneken |
| Abstract | There is a growing interest in the automated analysis of chest X-Ray (CXR) as a sensitive and inexpensive means of screening susceptible populations for pulmonary tuberculosis. In this work we evaluate the latest version of CAD4TB, a software platform designed for this purpose. Version 6 of CAD4TB was released in 2018 and is here tested on an independent dataset of 5565 CXR images with GeneXpert (Xpert) sputum test results available (854 Xpert positive subjects). A subset of 500 subjects (50% Xpert positive) was reviewed and annotated by 5 expert observers independently to obtain a radiological reference standard. The latest version of CAD4TB is found to outperform all previous versions in terms of area under receiver operating curve (ROC) with respect to both Xpert and radiological reference standards. Improvements with respect to Xpert are most apparent at high sensitivity levels with a specificity of 76% obtained at 90% sensitivity. When compared with the radiological reference standard, CAD4TB v6 also outperformed previous versions by a considerable margin and achieved 98% specificity at 90% sensitivity. No substantial difference was found between the performance of CAD4TB v6 and any of the various expert observers against the Xpert reference standard. A cost and efficiency analysis on this dataset demonstrates that in a standard clinical situation, operating at 90% sensitivity, users of CAD4TB v6 can process 132 subjects per day at an average cost per screen of $5.95 per subject, while users of version 3 process only 85 subjects per day at a cost of $8.41 per subject. At all tested operating points version 6 is shown to be more efficient and cost effective than any other version. |
| Tasks | |
| Published | 2019-03-08 |
| URL | http://arxiv.org/abs/1903.03349v1 |
| http://arxiv.org/pdf/1903.03349v1.pdf | |
| PWC | https://paperswithcode.com/paper/computer-aided-detection-of-tuberculosis-on |
| Repo | |
| Framework | |
Multi-Agent Deep Reinforcement Learning with Adaptive Policies
| Title | Multi-Agent Deep Reinforcement Learning with Adaptive Policies |
| Authors | Yixiang Wang, Feng Wu |
| Abstract | We propose a novel approach to address one aspect of the non-stationarity problem in multi-agent reinforcement learning (RL), where the other agents may alter their policies due to environment changes during execution. This violates the Markov assumption that governs most single-agent RL methods and is one of the key challenges in multi-agent RL. To tackle this, we propose to train multiple policies for each agent and postpone the selection of the best policy at execution time. Specifically, we model the environment non-stationarity with a finite set of scenarios and train policies fitting each scenario. In addition to multiple policies, each agent also learns a policy predictor to determine which policy is the best with its local information. By doing so, each agent is able to adapt its policy when the environment changes and consequentially the other agents alter their policies during execution. We empirically evaluated our method on a variety of common benchmark problems proposed for multi-agent deep RL in the literature. Our experimental results show that the agents trained by our algorithm have better adaptiveness in changing environments and outperform the state-of-the-art methods in all the tested environments. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1912.00949v1 |
| https://arxiv.org/pdf/1912.00949v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-agent-deep-reinforcement-learning-with-2 |
| Repo | |
| Framework | |
SocialIQA: Commonsense Reasoning about Social Interactions
| Title | SocialIQA: Commonsense Reasoning about Social Interactions |
| Authors | Maarten Sap, Hannah Rashkin, Derek Chen, Ronan LeBras, Yejin Choi |
| Abstract | We introduce Social IQa, the first largescale benchmark for commonsense reasoning about social situations. Social IQa contains 38,000 multiple choice questions for probing emotional and social intelligence in a variety of everyday situations (e.g., Q: “Jordan wanted to tell Tracy a secret, so Jordan leaned towards Tracy. Why did Jordan do this?” A: “Make sure no one else could hear”). Through crowdsourcing, we collect commonsense questions along with correct and incorrect answers about social interactions, using a new framework that mitigates stylistic artifacts in incorrect answers by asking workers to provide the right answer to a different but related question. Empirical results show that our benchmark is challenging for existing question-answering models based on pretrained language models, compared to human performance (>20% gap). Notably, we further establish Social IQa as a resource for transfer learning of commonsense knowledge, achieving state-of-the-art performance on multiple commonsense reasoning tasks (Winograd Schemas, COPA). |
| Tasks | Question Answering, Transfer Learning |
| Published | 2019-04-22 |
| URL | https://arxiv.org/abs/1904.09728v3 |
| https://arxiv.org/pdf/1904.09728v3.pdf | |
| PWC | https://paperswithcode.com/paper/socialiqa-commonsense-reasoning-about-social |
| Repo | |
| Framework | |
GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks
| Title | GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks |
| Authors | Tengfei Ma, Junyuan Shang, Cao Xiao, Jimeng Sun |
| Abstract | Gaining more comprehensive knowledge about drug-drug interactions (DDIs) is one of the most important tasks in drug development and medical practice. Recently graph neural networks have achieved great success in this task by modeling drugs as nodes and drug-drug interactions as links and casting DDI predictions as link prediction problems. However, correlations between link labels (e.g., DDI types) were rarely considered in existing works. We propose the graph energy neural network (GENN) to explicitly model link type correlations. We formulate the DDI prediction task as a structure prediction problem and introduce a new energy-based model where the energy function is defined by graph neural networks. Experiments on two real-world DDI datasets demonstrated that GENN is superior to many baselines without consideration of link type correlations and achieved $13.77%$ and $5.01%$ PR-AUC improvement on the two datasets, respectively. We also present a case study in which \mname can better capture meaningful DDI correlations compared with baseline models. |
| Tasks | Link Prediction |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.02107v2 |
| https://arxiv.org/pdf/1910.02107v2.pdf | |
| PWC | https://paperswithcode.com/paper/genn-predicting-correlated-drug-drug-1 |
| Repo | |
| Framework | |
Assistive System in Conversational Agent for Health Coaching: The CoachAI Approach
| Title | Assistive System in Conversational Agent for Health Coaching: The CoachAI Approach |
| Authors | Ahmed Fadhil |
| Abstract | With increasing physicians’ workload and patients’ needs for care, there is a need for technology that facilitates physicians work and performs continues follow-up with patients. Existing approaches focus merely on improving patient’s condition, and none have considered managing physician’s workload. This paper presents an initial evaluation of a conversational agent assisted coaching platform intended to manage physicians’ fatigue and provide continuous follow-up to patients. We highlight the approach adapted to build the chatbot dialogue and the coaching platform. We will particularly discuss the activity recommender algorithms used to suggest insights about patients’ condition and activities based on previously collected data. The paper makes three contributions: (1) present the conversational agent as an assistive virtual coach, (2) decrease physicians workload and continuous follow up with patients, all by handling some repetitive physician tasks and performing initial follow up with the patient, (3) present the activity recommender that tracks previous activities and patient information and provides useful insights about possible activity and patient match to the coach. Future work focuses on integrating the recommender model with the CoachAI platform and test the prototype with patient’s in collaboration with an ambulatory clinic. |
| Tasks | Chatbot |
| Published | 2019-04-25 |
| URL | http://arxiv.org/abs/1904.11412v1 |
| http://arxiv.org/pdf/1904.11412v1.pdf | |
| PWC | https://paperswithcode.com/paper/assistive-system-in-conversational-agent-for |
| Repo | |
| Framework | |
Learning from Dialogue after Deployment: Feed Yourself, Chatbot!
| Title | Learning from Dialogue after Deployment: Feed Yourself, Chatbot! |
| Authors | Braden Hancock, Antoine Bordes, Pierre-Emmanuel Mazaré, Jason Weston |
| Abstract | The majority of conversations a dialogue agent sees over its lifetime occur after it has already been trained and deployed, leaving a vast store of potential training signal untapped. In this work, we propose the self-feeding chatbot, a dialogue agent with the ability to extract new training examples from the conversations it participates in. As our agent engages in conversation, it also estimates user satisfaction in its responses. When the conversation appears to be going well, the user’s responses become new training examples to imitate. When the agent believes it has made a mistake, it asks for feedback; learning to predict the feedback that will be given improves the chatbot’s dialogue abilities further. On the PersonaChat chit-chat dataset with over 131k training examples, we find that learning from dialogue with a self-feeding chatbot significantly improves performance, regardless of the amount of traditional supervision. |
| Tasks | Chatbot |
| Published | 2019-01-16 |
| URL | https://arxiv.org/abs/1901.05415v4 |
| https://arxiv.org/pdf/1901.05415v4.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-dialogue-after-deployment-feed |
| Repo | |
| Framework | |
The Lingering of Gradients: Theory and Applications
| Title | The Lingering of Gradients: Theory and Applications |
| Authors | Zeyuan Allen-Zhu, David Simchi-Levi, Xinshang Wang |
| Abstract | Classically, the time complexity of a first-order method is estimated by its number of gradient computations. In this paper, we study a more refined complexity by taking into account the lingering' of gradients: once a gradient is computed at $x_k$, the additional time to compute gradients at $x_{k+1},x_{k+2},\dots$ may be reduced. We show how this improves the running time of several first-order methods. For instance, if the additional time’ scales linearly with respect to the traveled distance, then the `convergence rate’ of gradient descent can be improved from $1/T$ to $\exp(-T^{1/3})$. On the application side, we solve a hypothetical revenue management problem on the Yahoo! Front Page Today Module with 4.6m users to $10^{-6}$ error using only 6 passes of the dataset; and solve a real-life support vector machine problem to an accuracy that is two orders of magnitude better comparing to the state-of-the-art algorithm. | |
| Tasks | |
| Published | 2019-01-09 |
| URL | https://arxiv.org/abs/1901.02871v2 |
| https://arxiv.org/pdf/1901.02871v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-lingering-of-gradients-how-to-reuse |
| Repo | |
| Framework | |
Learning Context Graph for Person Search
| Title | Learning Context Graph for Person Search |
| Authors | Yichao Yan, Qiang Zhang, Bingbing Ni, Wendong Zhang, Minghao Xu, Xiaokang Yang |
| Abstract | Person re-identification has achieved great progress with deep convolutional neural networks. However, most previous methods focus on learning individual appearance feature embedding, and it is hard for the models to handle difficult situations with different illumination, large pose variance and occlusion. In this work, we take a step further and consider employing context information for person search. For a probe-gallery pair, we first propose a contextual instance expansion module, which employs a relative attention module to search and filter useful context information in the scene. We also build a graph learning framework to effectively employ context pairs to update target similarity. These two modules are built on top of a joint detection and instance feature learning framework, which improves the discriminativeness of the learned features. The proposed framework achieves state-of-the-art performance on two widely used person search datasets. |
| Tasks | Person Re-Identification, Person Search |
| Published | 2019-04-03 |
| URL | http://arxiv.org/abs/1904.01830v1 |
| http://arxiv.org/pdf/1904.01830v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-context-graph-for-person-search |
| Repo | |
| Framework | |
Stochastic proximal splitting algorithm for composite minimization
| Title | Stochastic proximal splitting algorithm for composite minimization |
| Authors | Andrei Patrascu, Paul Irofti |
| Abstract | Supported by the recent contributions in multiple branches, the first-order splitting algorithms became central for structured nonsmooth optimization. In the large-scale or noisy contexts, when only stochastic information on the smooth part of the objective function is available, the extension of proximal gradient schemes to stochastic oracles is based on proximal tractability of the nonsmooth component and it has been deeply analyzed in the literature. However, there remained gaps illustrated by composite models where the nonsmooth term is not proximally tractable anymore. In this note we tackle composite optimization problems, where the access only to stochastic information on both smooth and nonsmooth components is assumed, using a stochastic proximal first-order scheme with stochastic proximal updates. We provide $\mathcal{O}\left( \frac{1}{k} \right)$ the iteration complexity (in expectation of squared distance to the optimal set) under the strong convexity assumption on the objective function. Empirical behavior is illustrated by numerical tests on parametric sparse representation models. |
| Tasks | |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.02039v2 |
| https://arxiv.org/pdf/1912.02039v2.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-proximal-splitting-algorithm-for |
| Repo | |
| Framework | |
Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition
| Title | Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition |
| Authors | Wenhao Wu, Dongliang He, Xiao Tan, Shifeng Chen, Shilei Wen |
| Abstract | Video Recognition has drawn great research interest and great progress has been made. A suitable frame sampling strategy can improve the accuracy and efficiency of recognition. However, mainstream solutions generally adopt hand-crafted frame sampling strategies for recognition. It could degrade the performance, especially in untrimmed videos, due to the variation of frame-level saliency. To this end, we concentrate on improving untrimmed video classification via developing a learning-based frame sampling strategy. We intuitively formulate the frame sampling procedure as multiple parallel Markov decision processes, each of which aims at picking out a frame/clip by gradually adjusting an initial sampling. Then we propose to solve the problems with multi-agent reinforcement learning (MARL). Our MARL framework is composed of a novel RNN-based context-aware observation network which jointly models context information among nearby agents and historical states of a specific agent, a policy network which generates the probability distribution over a predefined action space at each step and a classification network for reward calculation as well as final recognition. Extensive experimental results show that our MARL-based scheme remarkably outperforms hand-crafted strategies with various 2D and 3D baseline methods. Our single RGB model achieves a comparable performance of ActivityNet v1.3 champion submission with multi-modal multi-model fusion and new state-of-the-art results on YouTube Birds and YouTube Cars. |
| Tasks | Multi-agent Reinforcement Learning, Video Classification, Video Recognition |
| Published | 2019-07-31 |
| URL | https://arxiv.org/abs/1907.13369v2 |
| https://arxiv.org/pdf/1907.13369v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-agent-reinforcement-learning-based |
| Repo | |
| Framework | |
LazyBum: Decision tree learning using lazy propositionalization
| Title | LazyBum: Decision tree learning using lazy propositionalization |
| Authors | Jonas Schouterden, Jesse Davis, Hendrik Blockeel |
| Abstract | Propositionalization is the process of summarizing relational data into a tabular (attribute-value) format. The resulting table can next be used by any propositional learner. This approach makes it possible to apply a wide variety of learning methods to relational data. However, the transformation from relational to propositional format is generally not lossless: different relational structures may be mapped onto the same feature vector. At the same time, features may be introduced that are not needed for the learning task at hand. In general, it is hard to define a feature space that contains all and only those features that are needed for the learning task. This paper presents LazyBum, a system that can be considered a lazy version of the recently proposed OneBM method for propositionalization. LazyBum interleaves OneBM’s feature construction method with a decision tree learner. This learner both uses and guides the propositionalization process. It indicates when and where to look for new features. This approach is similar to what has elsewhere been called dynamic propositionalization. In an experimental comparison with the original OneBM and with two other recently proposed propositionalization methods (nFOIL and MODL, which respectively perform dynamic and static propositionalization), LazyBum achieves a comparable accuracy with a lower execution time on most of the datasets. |
| Tasks | |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.05044v1 |
| https://arxiv.org/pdf/1909.05044v1.pdf | |
| PWC | https://paperswithcode.com/paper/lazybum-decision-tree-learning-using-lazy |
| Repo | |
| Framework | |
A complete formalized knowledge representation model for advanced digital forensics timeline analysis
| Title | A complete formalized knowledge representation model for advanced digital forensics timeline analysis |
| Authors | Yoan Chabot, Aurélie Bertaux, Christophe Nicollea, Tahar Kechadi |
| Abstract | Having a clear view of events that occurred over time is a difficult objective to achieve in digital investigations (DI). Event reconstruction, which allows investigators to understand the timeline of a crime, is one of the most important step of a DI process. This complex task requires exploration of a large amount of events due to the pervasiveness of new technologies nowadays. Any evidence produced at the end of the investigative process must also meet the requirements of the courts, such as reproducibility, verifiability, validation, etc. For this purpose, we propose a new methodology, supported by theoretical concepts, that can assist investigators through the whole process including the construction and the interpretation of the events describing the case. The proposed approach is based on a model which integrates knowledge of experts from the fields of digital forensics and software development to allow a semantically rich representation of events related to the incident. The main purpose of this model is to allow the analysis of these events in an automatic and efficient way. This paper describes the approach and then focuses on the main conceptual and formal aspects: a formal incident modelization and operators for timeline reconstruction and analysis. |
| Tasks | |
| Published | 2019-02-21 |
| URL | http://arxiv.org/abs/1903.01396v1 |
| http://arxiv.org/pdf/1903.01396v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-complete-formalized-knowledge |
| Repo | |
| Framework | |
Automatically Learning Data Augmentation Policies for Dialogue Tasks
| Title | Automatically Learning Data Augmentation Policies for Dialogue Tasks |
| Authors | Tong Niu, Mohit Bansal |
| Abstract | Automatic data augmentation (AutoAugment) (Cubuk et al., 2019) searches for optimal perturbation policies via a controller trained using performance rewards of a sampled policy on the target task, hence reducing data-level model bias. While being a powerful algorithm, their work has focused on computer vision tasks, where it is comparatively easy to apply imperceptible perturbations without changing an image’s semantic meaning. In our work, we adapt AutoAugment to automatically discover effective perturbation policies for natural language processing (NLP) tasks such as dialogue generation. We start with a pool of atomic operations that apply subtle semantic-preserving perturbations to the source inputs of a dialogue task (e.g., different POS-tag types of stopword dropout, grammatical errors, and paraphrasing). Next, we allow the controller to learn more complex augmentation policies by searching over the space of the various combinations of these atomic operations. Moreover, we also explore conditioning the controller on the source inputs of the target task, since certain strategies may not apply to inputs that do not contain that strategy’s required linguistic features. Empirically, we demonstrate that both our input-agnostic and input-aware controllers discover useful data augmentation policies, and achieve significant improvements over the previous state-of-the-art, including trained on manually-designed policies. |
| Tasks | Data Augmentation, Dialogue Generation |
| Published | 2019-09-27 |
| URL | https://arxiv.org/abs/1909.12868v1 |
| https://arxiv.org/pdf/1909.12868v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatically-learning-data-augmentation |
| Repo | |
| Framework | |
Context Vectors are Reflections of Word Vectors in Half the Dimensions
| Title | Context Vectors are Reflections of Word Vectors in Half the Dimensions |
| Authors | Zhenisbek Assylbekov, Rustem Takhanov |
| Abstract | This paper takes a step towards theoretical analysis of the relationship between word embeddings and context embeddings in models such as word2vec. We start from basic probabilistic assumptions on the nature of word vectors, context vectors, and text generation. These assumptions are well supported either empirically or theoretically by the existing literature. Next, we show that under these assumptions the widely-used word-word PMI matrix is approximately a random symmetric Gaussian ensemble. This, in turn, implies that context vectors are reflections of word vectors in approximately half the dimensions. As a direct application of our result, we suggest a theoretically grounded way of tying weights in the SGNS model. |
| Tasks | Text Generation, Word Embeddings |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1902.09859v1 |
| http://arxiv.org/pdf/1902.09859v1.pdf | |
| PWC | https://paperswithcode.com/paper/context-vectors-are-reflections-of-word |
| Repo | |
| Framework | |
