January 31, 2020

3138 words 15 mins read

Paper Group ANR 171

An Axiomatic Approach to Regularizing Neural Ranking Models. Dense RepPoints: Representing Visual Objects with Dense Point Sets. Opportunities for artificial intelligence in advancing precision medicine. A Neurally-Inspired Hierarchical Prediction Network for Spatiotemporal Sequence Learning and Prediction. Neural Review Rating Prediction with Hier …

An Axiomatic Approach to Regularizing Neural Ranking Models


Title	An Axiomatic Approach to Regularizing Neural Ranking Models
Authors	Corby Rosset, Bhaskar Mitra, Chenyan Xiong, Nick Craswell, Xia Song, Saurabh Tiwary
Abstract	Axiomatic information retrieval (IR) seeks a set of principle properties desirable in IR models. These properties when formally expressed provide guidance in the search for better relevance estimation functions. Neural ranking models typically contain a large number of parameters. The training of these models involve a search for appropriate parameter values based on large quantities of labeled examples. Intuitively, axioms that can guide the search for better traditional IR models should also help in better parameter estimation for machine learning based rankers. This work explores the use of IR axioms to augment the direct supervision from labeled data for training neural ranking models. We modify the documents in our dataset along the lines of well-known axioms during training and add a regularization loss based on the agreement between the ranking model and the axioms on which version of the document—the original or the perturbed—should be preferred. Our experiments show that the neural ranking model achieves faster convergence and better generalization with axiomatic regularization.
Tasks	Information Retrieval
Published	2019-04-15
URL	http://arxiv.org/abs/1904.06808v1
PDF	http://arxiv.org/pdf/1904.06808v1.pdf
PWC	https://paperswithcode.com/paper/an-axiomatic-approach-to-regularizing-neural
Repo
Framework

Dense RepPoints: Representing Visual Objects with Dense Point Sets


Title	Dense RepPoints: Representing Visual Objects with Dense Point Sets
Authors	Ze Yang, Yinghao Xu, Han Xue, Zheng Zhang, Raquel Urtasun, Liwei Wang, Stephen Lin, Han Hu
Abstract	We present an object representation, called \textbf{Dense RepPoints}, for flexible and detailed modeling of object appearance and geometry. In contrast to the coarse geometric localization and feature extraction of bounding boxes, Dense RepPoints adaptively distributes a dense set of points to semantically and geometrically significant positions on an object, providing informative cues for object analysis. Techniques are developed to address challenges related to supervised training for dense point sets from image segments annotations and making this extensive representation computationally practical. In addition, the versatility of this representation is exploited to model object structure over multiple levels of granularity. Dense RepPoints significantly improves performance on geometrically-oriented visual understanding tasks, including a $1.6$ AP gain in object detection on the challenging COCO benchmark.
Tasks	Object Detection
Published	2019-12-24
URL	https://arxiv.org/abs/1912.11473v1
PDF	https://arxiv.org/pdf/1912.11473v1.pdf
PWC	https://paperswithcode.com/paper/dense-reppoints-representing-visual-objects
Repo
Framework

Opportunities for artificial intelligence in advancing precision medicine


Title	Opportunities for artificial intelligence in advancing precision medicine
Authors	Fabian V. Filipp
Abstract	Machine learning (ML), deep learning (DL), and artificial intelligence (AI) are of increasing importance in biomedicine. The goal of this work is to show progress in ML in digital health, to exemplify future needs and trends, and to identify any essential prerequisites of AI and ML for precision health. High-throughput technologies are delivering growing volumes of biomedical data, such as large-scale genome-wide sequencing assays, libraries of medical images, or drug perturbation screens of healthy, developing, and diseased tissue. Multi-omics data in biomedicine is deep and complex, offering an opportunity for data-driven insights and automated disease classification. Learning from these data will open our understanding and definition of healthy baselines and disease signatures. State-of-the-art applications of deep neural networks include digital image recognition, single cell clustering, and virtual drug screens, demonstrating breadths and power of ML in biomedicine. Significantly, AI and systems biology have embraced big data challenges and may enable novel biotechnology-derived therapies to facilitate the implementation of precision medicine approaches.
Tasks
Published	2019-11-17
URL	https://arxiv.org/abs/1911.07125v1
PDF	https://arxiv.org/pdf/1911.07125v1.pdf
PWC	https://paperswithcode.com/paper/opportunities-for-artificial-intelligence-in
Repo
Framework

A Neurally-Inspired Hierarchical Prediction Network for Spatiotemporal Sequence Learning and Prediction


Title	A Neurally-Inspired Hierarchical Prediction Network for Spatiotemporal Sequence Learning and Prediction
Authors	Jielin Qiu, Ge Huang, Tai Sing Lee
Abstract	In this paper we developed a hierarchical network model, called Hierarchical Prediction Network (HPNet), to understand how spatiotemporal memories might be learned and encoded in the recurrent circuits in the visual cortical hierarchy for predicting future video frames. This neurally inspired model operates in the analysis-by-synthesis framework. It contains a feed-forward path that computes and encodes spatiotemporal features of successive complexity and a feedback path for the successive levels to project their interpretations to the level below. Within each level, the feed-forward path and the feedback path intersect in a recurrent gated circuit, instantiated in a LSTM module, to generate a prediction or explanation of the incoming signals. The network learns its internal model of the world by minimizing the errors of its prediction of the incoming signals at each level of the hierarchy. We found that hierarchical interaction in the network increases semantic clustering of global movement patterns in the population codes of the units along the hierarchy, even in the earliest module. This facilitates the learning of relationships among movement patterns, yielding state-of-the-art performance in long range video sequence predictions in the benchmark datasets. The network model automatically reproduces a variety of prediction suppression and familiarity suppression neurophysiological phenomena observed in the visual cortex, suggesting that hierarchical prediction might indeed be an important principle for representational learning in the visual cortex.
Tasks
Published	2019-01-25
URL	http://arxiv.org/abs/1901.09002v1
PDF	http://arxiv.org/pdf/1901.09002v1.pdf
PWC	https://paperswithcode.com/paper/a-neurally-inspired-hierarchical-prediction
Repo
Framework

Neural Review Rating Prediction with Hierarchical Attentions and Latent Factors


Title	Neural Review Rating Prediction with Hierarchical Attentions and Latent Factors
Authors	Xianchen Wang, Hongtao Liu, Peiyi Wang, Fangzhao Wu, Hongyan Xu, Wenjun Wang, Xing Xie
Abstract	Text reviews can provide rich useful semantic information for modeling users and items, which can benefit rating prediction in recommendation. Different words and reviews may have different informativeness for users or items. Besides, different users and items should be personalized. Most existing works regard all reviews equally or utilize a general attention mechanism. In this paper, we propose a hierarchical attention model fusing latent factor model for rating prediction with reviews, which can focus on important words and informative reviews. Specially, we use the factor vectors of Latent Factor Model to guide the attention network and combine the factor vectors with feature representation learned from reviews to predict the final ratings. Experiments on real-world datasets validate the effectiveness of our approach.
Tasks
Published	2019-05-29
URL	https://arxiv.org/abs/1906.01511v1
PDF	https://arxiv.org/pdf/1906.01511v1.pdf
PWC	https://paperswithcode.com/paper/190601511
Repo
Framework

Collaboration based Multi-Label Learning


Title	Collaboration based Multi-Label Learning
Authors	Lei Feng, Bo An, Shuo He
Abstract	It is well-known that exploiting label correlations is crucially important to multi-label learning. Most of the existing approaches take label correlations as prior knowledge, which may not correctly characterize the real relationships among labels. Besides, label correlations are normally used to regularize the hypothesis space, while the final predictions are not explicitly correlated. In this paper, we suggest that for each individual label, the final prediction involves the collaboration between its own prediction and the predictions of other labels. Based on this assumption, we first propose a novel method to learn the label correlations via sparse reconstruction in the label space. Then, by seamlessly integrating the learned label correlations into model training, we propose a novel multi-label learning approach that aims to explicitly account for the correlated predictions of labels while training the desired model simultaneously. Extensive experimental results show that our approach outperforms the state-of-the-art counterparts.
Tasks	Multi-Label Learning
Published	2019-02-08
URL	http://arxiv.org/abs/1902.03047v1
PDF	http://arxiv.org/pdf/1902.03047v1.pdf
PWC	https://paperswithcode.com/paper/collaboration-based-multi-label-learning
Repo
Framework

Value-Added Chemical Discovery Using Reinforcement Learning


Title	Value-Added Chemical Discovery Using Reinforcement Learning
Authors	Peihong Jiang, Hieu Doan, Sandeep Madireddy, Rajeev Surendran Assary, Prasanna Balaprakash
Abstract	Computer-assisted synthesis planning aims to help chemists find better reaction pathways faster. Finding viable and short pathways from sugar molecules to value-added chemicals can be modeled as a retrosynthesis planning problem with a catalyst allowed. This is a crucial step in efficient biomass conversion. The traditional computational chemistry approach to identifying possible reaction pathways involves computing the reaction energies of hundreds of intermediates, which is a critical bottleneck in silico reaction discovery. Deep reinforcement learning has shown in other domains that a well-trained agent with little or no prior human knowledge can surpass human performance. While some effort has been made to adapt machine learning techniques to the retrosynthesis planning problem, value-added chemical discovery presents unique challenges. Specifically, the reaction can occur in several different sites in a molecule, a subtle case that has never been treated in previous works. With a more versatile formulation of the problem as a Markov decision process, we address the problem using deep reinforcement learning techniques and present promising preliminary results.
Tasks
Published	2019-11-10
URL	https://arxiv.org/abs/1911.07630v1
PDF	https://arxiv.org/pdf/1911.07630v1.pdf
PWC	https://paperswithcode.com/paper/value-added-chemical-discovery-using
Repo
Framework

Recursive Prediction of Graph Signals with Incoming Nodes


Title	Recursive Prediction of Graph Signals with Incoming Nodes
Authors	Arun Venkitaraman, Saikat Chatterjee, Bo Wahlberg
Abstract	Kernel and linear regression have been recently explored in the prediction of graph signals as the output, given arbitrary input signals that are agnostic to the graph. In many real-world problems, the graph expands over time as new nodes get introduced. Keeping this premise in mind, we propose a method to recursively obtain the optimal prediction or regression coefficients for the recently propose Linear Regression over Graphs (LRG), as the graph expands with incoming nodes. This comes as a natural consequence of the structure C(W)= of the regression problem, and obviates the need to solve a new regression problem each time a new node is added. Experiments with real-world graph signals show that our approach results in good prediction performance which tends to be close to that obtained from knowing the entire graph apriori.
Tasks
Published	2019-11-26
URL	https://arxiv.org/abs/1911.11542v1
PDF	https://arxiv.org/pdf/1911.11542v1.pdf
PWC	https://paperswithcode.com/paper/recursive-prediction-of-graph-signals-with
Repo
Framework

A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images


Title	A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images
Authors	Yunzhe Xue, Fadi G. Farhat, Olga Boukrina, A . M. Barrett, Jeffrey R. Binder, Usman W. Roshan, William W. Graves
Abstract	Automatic identification of brain lesions from magnetic resonance imaging (MRI) scans of stroke survivors would be a useful aid in patient diagnosis and treatment planning. We propose a multi-modal multi-path convolutional neural network system for automating stroke lesion segmentation. Our system has nine end-to-end UNets that take as input 2-dimensional (2D) slices and examines all three planes with three different normalizations. Outputs from these nine total paths are concatenated into a 3D volume that is then passed to a 3D convolutional neural network to output a final lesion mask. We trained and tested our method on datasets from three sources: Medical College of Wisconsin (MCW), Kessler Foundation (KF), and the publicly available Anatomical Tracings of Lesions After Stroke (ATLAS) dataset. Cross-study validation results (with independent training and validation datasets) were obtained to compare with previous methods based on naive Bayes, random forests, and three recently published convolutional neural networks. Model performance was quantified in terms of the Dice coefficient. Training on the KF and MCW images and testing on the ATLAS images yielded a mean Dice coefficient of 0.54. This was reliably better than the next best previous model, UNet, at 0.47. Reversing the train and test datasets yields a mean Dice of 0.47 on KF and MCW images, whereas the next best UNet reaches 0.45. With all three datasets combined, the current system compared to previous methods also attained a reliably higher cross-validation accuracy. It also achieved high Dice values for many smaller lesions that existing methods have difficulty identifying. Overall, our system is a clear improvement over previous methods for automating stroke lesion segmentation, bringing us an important step closer to the inter-rater accuracy level of human experts.
Tasks	Lesion Segmentation
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10835v1
PDF	https://arxiv.org/pdf/1905.10835v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-path-25-dimensional-convolutional
Repo
Framework

Learning Factored Markov Decision Processes with Unawareness


Title	Learning Factored Markov Decision Processes with Unawareness
Authors	Craig Innes, Alex Lascarides
Abstract	Methods for learning and planning in sequential decision problems often assume the learner is aware of all possible states and actions in advance. This assumption is sometimes untenable. In this paper, we give a method to learn factored markov decision problems from both domain exploration and expert assistance, which guarantees convergence to near-optimal behaviour, even when the agent begins unaware of factors critical to success. Our experiments show our agent learns optimal behaviour on small and large problems, and that conserving information on discovering new possibilities results in faster convergence.
Tasks
Published	2019-02-27
URL	http://arxiv.org/abs/1902.10619v1
PDF	http://arxiv.org/pdf/1902.10619v1.pdf
PWC	https://paperswithcode.com/paper/learning-factored-markov-decision-processes
Repo
Framework

Gmail Smart Compose: Real-Time Assisted Writing


Title	Gmail Smart Compose: Real-Time Assisted Writing
Authors	Mia Xu Chen, Benjamin N Lee, Gagan Bansal, Yuan Cao, Shuyuan Zhang, Justin Lu, Jackie Tsay, Yinan Wang, Andrew M. Dai, Zhifeng Chen, Timothy Sohn, Yonghui Wu
Abstract	In this paper, we present Smart Compose, a novel system for generating interactive, real-time suggestions in Gmail that assists users in writing mails by reducing repetitive typing. In the design and deployment of such a large-scale and complicated system, we faced several challenges including model selection, performance evaluation, serving and other practical issues. At the core of Smart Compose is a large-scale neural language model. We leveraged state-of-the-art machine learning techniques for language model training which enabled high-quality suggestion prediction, and constructed novel serving infrastructure for high-throughput and real-time inference. Experimental results show the effectiveness of our proposed system design and deployment approach. This system is currently being served in Gmail.
Tasks	Language Modelling, Model Selection
Published	2019-05-17
URL	https://arxiv.org/abs/1906.00080v1
PDF	https://arxiv.org/pdf/1906.00080v1.pdf
PWC	https://paperswithcode.com/paper/190600080
Repo
Framework

On-chip Few-shot Learning with Surrogate Gradient Descent on a Neuromorphic Processor


Title	On-chip Few-shot Learning with Surrogate Gradient Descent on a Neuromorphic Processor
Authors	Kenneth Stewart, Garrick Orchard, Sumit Bam Shrestha, Emre Neftci
Abstract	Recent work suggests that synaptic plasticity dynamics in biological models of neurons and neuromorphic hardware are compatible with gradient-based learning (Neftci et al., 2019). Gradient-based learning requires iterating several times over a dataset, which is both time-consuming and constrains the training samples to be independently and identically distributed. This is incompatible with learning systems that do not have boundaries between training and inference, such as in neuromorphic hardware. One approach to overcome these constraints is transfer learning, where a portion of the network is pre-trained and mapped into hardware and the remaining portion is trained online. Transfer learning has the advantage that pre-training can be accelerated offline if the task domain is known, and few samples of each class are sufficient for learning the target task at reasonable accuracies. Here, we demonstrate on-line surrogate gradient few-shot learning on Intel’s Loihi neuromorphic research processor using features pre-trained with spike-based gradient backpropagation-through-time. Our experimental results show that the Loihi chip can learn gestures online using a small number of shots and achieve results that are comparable to the models simulated on a conventional processor.
Tasks	Few-Shot Learning, Transfer Learning
Published	2019-10-11
URL	https://arxiv.org/abs/1910.04972v6
PDF	https://arxiv.org/pdf/1910.04972v6.pdf
PWC	https://paperswithcode.com/paper/on-chip-few-shot-learning-with-surrogate
Repo
Framework

Spatially Regularized Parametric Map Reconstruction for Fast Magnetic Resonance Fingerprinting


Title	Spatially Regularized Parametric Map Reconstruction for Fast Magnetic Resonance Fingerprinting
Authors	Fabian Balsiger, Alain Jungo, Olivier Scheidegger, Pierre G. Carlier, Mauricio Reyes, Benjamin Marty
Abstract	Magnetic resonance fingerprinting (MRF) provides a unique concept for simultaneous and fast acquisition of multiple quantitative MR parameters. Despite acquisition efficiency, adoption of MRF into the clinics is hindered by its dictionary-based reconstruction, which is computationally demanding and lacks scalability. Here, we propose a convolutional neural network-based reconstruction, which enables both accurate and fast reconstruction of parametric maps, and is adaptable based on the needs of spatial regularization and the capacity for the reconstruction. We evaluated the method using MRF T1-FF, an MRF sequence for T1 relaxation time of water and fat fraction mapping. We demonstrate the method’s performance on a highly heterogeneous dataset consisting of 164 patients with various neuromuscular diseases imaged at thighs and legs. We empirically show the benefit of incorporating spatial regularization during the reconstruction and demonstrate that the method learns meaningful features from MR physics perspective. Further, we investigate the ability of the method to handle highly heterogeneous morphometric variations and its generalization to anatomical regions unseen during training. The obtained results outperform the state-of-the-art in deep learning-based MRF reconstruction. Coupled with fast MRF sequences, the proposed method has the potential of enabling multiparametric MR imaging in clinically feasible time.
Tasks	Magnetic Resonance Fingerprinting
Published	2019-11-09
URL	https://arxiv.org/abs/1911.03786v1
PDF	https://arxiv.org/pdf/1911.03786v1.pdf
PWC	https://paperswithcode.com/paper/spatially-regularized-parametric-map
Repo
Framework

Ocular Diseases Diagnosis in Fundus Images using a Deep Learning: Approaches, tools and Performance evaluation


Title	Ocular Diseases Diagnosis in Fundus Images using a Deep Learning: Approaches, tools and Performance evaluation
Authors	Yaroub Elloumi, Mohamed Akil, Henda Boudegga
Abstract	Ocular pathology detection from fundus images presents an important challenge on health care. In fact, each pathology has different severity stages that may be deduced by verifying the existence of specific lesions. Each lesion is characterized by morphological features. Moreover, several lesions of different pathologies have similar features. We note that patient may be affected simultaneously by several pathologies. Consequently, the ocular pathology detection presents a multi-class classification with a complex resolution principle. Several detection methods of ocular pathologies from fundus images have been proposed. The methods based on deep learning are distinguished by higher performance detection, due to their capability to configure the network with respect to the detection objective. This work proposes a survey of ocular pathology detection methods based on deep learning. First, we study the existing methods either for lesion segmentation or pathology classification. Afterwards, we extract the principle steps of processing and we analyze the proposed neural network structures. Subsequently, we identify the hardware and software environment required to employ the deep learning architecture. Thereafter, we investigate about the experimentation principles involved to evaluate the methods and the databases used either for training and testing phases. The detection performance ratios and execution times are also reported and discussed.
Tasks	Lesion Segmentation
Published	2019-05-07
URL	https://arxiv.org/abs/1905.02544v1
PDF	https://arxiv.org/pdf/1905.02544v1.pdf
PWC	https://paperswithcode.com/paper/ocular-diseases-diagnosis-in-fundus-images
Repo
Framework

SimVAE: Simulator-Assisted Training forInterpretable Generative Models


Title	SimVAE: Simulator-Assisted Training forInterpretable Generative Models
Authors	Akash Srivastava, Jessie Rosenberg, Dan Gutfreund, David D. Cox
Abstract	This paper presents a simulator-assisted training method (SimVAE) for variational autoencoders (VAE) that leads to a disentangled and interpretable latent space. Training SimVAE is a two-step process in which first a deep generator network(decoder) is trained to approximate the simulator. During this step, the simulator acts as the data source or as a teacher network. Then an inference network (encoder)is trained to invert the decoder. As such, upon complete training, the encoder represents an approximately inverted simulator. By decoupling the training of the encoder and decoder we bypass some of the difficulties that arise in training generative models such as VAEs and generative adversarial networks (GANs). We show applications of our approach in a variety of domains such as circuit design, graphics de-rendering and other natural science problems that involve inference via simulation.
Tasks
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08051v1
PDF	https://arxiv.org/pdf/1911.08051v1.pdf
PWC	https://paperswithcode.com/paper/simvae-simulator-assisted-training
Repo
Framework