Paper Group ANR 510
Deep learning for molecular design - a review of the state of the art. Procedural Generation of Initial States of Sokoban. Scalable Hyperbolic Recommender Systems. How far should self-driving cars see? Effect of observation range on vehicle self-localization. Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLA …
Deep learning for molecular design - a review of the state of the art
| Title | Deep learning for molecular design - a review of the state of the art |
| Authors | Daniel C. Elton, Zois Boukouvalas, Mark D. Fuge, Peter W. Chung |
| Abstract | In the space of only a few years, deep generative modeling has revolutionized how we think of artificial creativity, yielding autonomous systems which produce original images, music, and text. Inspired by these successes, researchers are now applying deep generative modeling techniques to the generation and optimization of molecules - in our review we found 45 papers on the subject published in the past two years. These works point to a future where such systems will be used to generate lead molecules, greatly reducing resources spent downstream synthesizing and characterizing bad leads in the lab. In this review we survey the increasingly complex landscape of models and representation schemes that have been proposed. The four classes of techniques we describe are recursive neural networks, autoencoders, generative adversarial networks, and reinforcement learning. After first discussing some of the mathematical fundamentals of each technique, we draw high level connections and comparisons with other techniques and expose the pros and cons of each. Several important high level themes emerge as a result of this work, including the shift away from the SMILES string representation of molecules towards more sophisticated representations such as graph grammars and 3D representations, the importance of reward function design, the need for better standards for benchmarking and testing, and the benefits of adversarial training and reinforcement learning over maximum likelihood based training. |
| Tasks | |
| Published | 2019-03-11 |
| URL | https://arxiv.org/abs/1903.04388v3 |
| https://arxiv.org/pdf/1903.04388v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-molecular-generation-and |
| Repo | |
| Framework | |
Procedural Generation of Initial States of Sokoban
| Title | Procedural Generation of Initial States of Sokoban |
| Authors | Dâmaris S. Bento, André G. Pereira, Levi H. S. Lelis |
| Abstract | Procedural generation of initial states of state-space search problems have applications in human and machine learning as well as in the evaluation of planning systems. In this paper we deal with the task of generating hard and solvable initial states of Sokoban puzzles. We propose hardness metrics based on pattern database heuristics and the use of novelty to improve the exploration of search methods in the task of generating initial states. We then present a system called Beta that uses our hardness metrics and novelty to generate initial states. Experiments show that Beta is able to generate initial states that are harder to solve by a specialized solver than those designed by human experts. |
| Tasks | |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.02548v1 |
| https://arxiv.org/pdf/1907.02548v1.pdf | |
| PWC | https://paperswithcode.com/paper/procedural-generation-of-initial-states-of |
| Repo | |
| Framework | |
Scalable Hyperbolic Recommender Systems
| Title | Scalable Hyperbolic Recommender Systems |
| Authors | Benjamin Paul Chamberlain, Stephen R. Hardwick, David R. Wardrope, Fabon Dzogang, Fabio Daolio, Saúl Vargas |
| Abstract | We present a large scale hyperbolic recommender system. We discuss why hyperbolic geometry is a more suitable underlying geometry for many recommendation systems and cover the fundamental milestones and insights that we have gained from its development. In doing so, we demonstrate the viability of hyperbolic geometry for recommender systems, showing that they significantly outperform Euclidean models on datasets with the properties of complex networks. Key to the success of our approach are the novel choice of underlying hyperbolic model and the use of the Einstein midpoint to define an asymmetric recommender system in hyperbolic space. These choices allow us to scale to millions of users and hundreds of thousands of items. |
| Tasks | Recommendation Systems |
| Published | 2019-02-22 |
| URL | http://arxiv.org/abs/1902.08648v1 |
| http://arxiv.org/pdf/1902.08648v1.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-hyperbolic-recommender-systems |
| Repo | |
| Framework | |
How far should self-driving cars see? Effect of observation range on vehicle self-localization
| Title | How far should self-driving cars see? Effect of observation range on vehicle self-localization |
| Authors | Mahdi Javanmardi, Ehsan Javanmardi, Shunsuke Kamijo |
| Abstract | Accuracy and time efficiency are two essential requirements for the self-localization of autonomous vehicles. While the observation range considered for simultaneous localization and mapping (SLAM) has a significant effect on both accuracy and computation time, its effect is not well investigated in the literature. In this paper, we will answer the question: How far should a driverless car observe during self-localization? We introduce a framework to dynamically define the observation range for localization to meet the accuracy requirement for autonomous driving, while keeping the computation time low. To model the effect of scanning range on the localization accuracy for every point on the map, several map factors were employed. The capability of the proposed framework was verified using field data, demonstrating that it is able to improve the average matching time from 142.2 ms to 39.3 ms while keeping the localization accuracy around 8.1 cm. |
| Tasks | Autonomous Driving, Autonomous Vehicles, Self-Driving Cars, Simultaneous Localization and Mapping |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.06588v1 |
| https://arxiv.org/pdf/1908.06588v1.pdf | |
| PWC | https://paperswithcode.com/paper/how-far-should-self-driving-cars-see-effect |
| Repo | |
| Framework | |
Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM
| Title | Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM |
| Authors | Bingbing Zhuang, Quoc-Huy Tran, Pan Ji, Gim Hee Lee, Loong Fah Cheong, Manmohan Chandraker |
| Abstract | Self-calibration of camera intrinsics and radial distortion has a long history of research in the computer vision community. However, it remains rare to see real applications of such techniques to modern Simultaneous Localization And Mapping (SLAM) systems, especially in driving scenarios. In this paper, we revisit the geometric approach to this problem, and provide a theoretical proof that explicitly shows the ambiguity between radial distortion and scene depth when two-view geometry is used to self-calibrate the radial distortion. In view of such geometric degeneracy, we propose a learning approach that trains a convolutional neural network (CNN) on a large amount of synthetic data. We demonstrate the utility of our proposed method by applying it as a checkerboard-free calibration tool for SLAM, achieving comparable or superior performance to previous learning and hand-crafted methods. |
| Tasks | Calibration, Simultaneous Localization and Mapping |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.13185v1 |
| https://arxiv.org/pdf/1907.13185v1.pdf | |
| PWC | https://paperswithcode.com/paper/degeneracy-in-self-calibration-revisited-and |
| Repo | |
| Framework | |
Katyusha Acceleration for Convex Finite-Sum Compositional Optimization
| Title | Katyusha Acceleration for Convex Finite-Sum Compositional Optimization |
| Authors | Yibo Xu, Yangyang Xu |
| Abstract | Structured problems arise in many applications. To solve these problems, it is important to leverage the structure information. This paper focuses on convex problems with a finite-sum compositional structure. Finite-sum problems appear as the sample average approximation of a stochastic optimization problem and also arise in machine learning with a huge amount of training data. One popularly used numerical approach for finite-sum problems is the stochastic gradient method (SGM). However, the additional compositional structure prohibits easy access to unbiased stochastic approximation of the gradient, so directly applying the SGM to a finite-sum compositional optimization problem (COP) is often inefficient. We design new algorithms for solving strongly-convex and also convex two-level finite-sum COPs. Our design incorporates the Katyusha acceleration technique and adopts the mini-batch sampling from both outer-level and inner-level finite-sum. We first analyze the algorithm for strongly-convex finite-sum COPs. Similar to a few existing works, we obtain linear convergence rate in terms of the expected objective error, and from the convergence rate result, we then establish complexity results of the algorithm to produce an $\varepsilon$-solution. Our complexity results have the same dependence on the number of component functions as existing works. However, due to the use of Katyusha acceleration, our results have better dependence on the condition number $\kappa$ and improve to $\kappa^{2.5}$ from the best-known $\kappa^3$. Finally, we analyze the algorithm for convex finite-sum COPs, which uses as a subroutine the algorithm for strongly-convex finite-sum COPs. Again, we obtain better complexity results than existing works in terms of the dependence on $\varepsilon$, improving to $\varepsilon^{-2.5}$ from the best-known $\varepsilon^{-3}$. |
| Tasks | Stochastic Optimization |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.11217v1 |
| https://arxiv.org/pdf/1910.11217v1.pdf | |
| PWC | https://paperswithcode.com/paper/katyusha-acceleration-for-convex-finite-sum |
| Repo | |
| Framework | |
Drug Repurposing for Cancer: An NLP Approach to Identify Low-Cost Therapies
| Title | Drug Repurposing for Cancer: An NLP Approach to Identify Low-Cost Therapies |
| Authors | Shivashankar Subramanian, Ioana Baldini, Sushma Ravichandran, Dmitriy A. Katz-Rogozhnikov, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Kush R. Varshney, Annmarie Wang, Pradeep Mangalath, Laura B. Kleiman |
| Abstract | More than 200 generic drugs approved by the U.S. Food and Drug Administration for non-cancer indications have shown promise for treating cancer. Due to their long history of safe patient use, low cost, and widespread availability, repurposing of generic drugs represents a major opportunity to rapidly improve outcomes for cancer patients and reduce healthcare costs worldwide. Evidence on the efficacy of non-cancer generic drugs being tested for cancer exists in scientific publications, but trying to manually identify and extract such evidence is intractable. In this paper, we introduce a system to automate this evidence extraction from PubMed abstracts. Our primary contribution is to define the natural language processing pipeline required to obtain such evidence, comprising the following modules: querying, filtering, cancer type entity extraction, therapeutic association classification, and study type classification. Using the subject matter expertise on our team, we create our own datasets for these specialized domain-specific tasks. We obtain promising performance in each of the modules by utilizing modern language modeling techniques and plan to treat them as baseline approaches for future improvement of individual components. |
| Tasks | Entity Extraction, Language Modelling |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07819v2 |
| https://arxiv.org/pdf/1911.07819v2.pdf | |
| PWC | https://paperswithcode.com/paper/drug-repurposing-for-cancer-an-nlp-approach |
| Repo | |
| Framework | |
Conductor Galloping Prediction on Imbalanced Datasets: SVM with Smart Sampling
| Title | Conductor Galloping Prediction on Imbalanced Datasets: SVM with Smart Sampling |
| Authors | Kui Wang, Jian Sun, Chenye Wu, Yang Yu |
| Abstract | Conductor galloping is the high-amplitude, low-frequency oscillation of overhead power lines due to wind. Such movements may lead to severe damages to transmission lines, and hence pose significant risks to the power system operation. In this paper, we target to design a prediction framework for conductor galloping. The difficulty comes from imbalanced dataset as galloping happens rarely. By examining the impacts of data balance and data volume on the prediction performance, we propose to employ proper sample adjustment methods to achieve better performance. Numerical study suggests that using only three features, together with over sampling, the SVM based prediction framework achieves an F_1-score of 98.9%. |
| Tasks | |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.04467v1 |
| https://arxiv.org/pdf/1911.04467v1.pdf | |
| PWC | https://paperswithcode.com/paper/conductor-galloping-prediction-on-imbalanced |
| Repo | |
| Framework | |
Transfer Learning in 4D for Breast Cancer Diagnosis using Dynamic Contrast-Enhanced Magnetic Resonance Imaging
| Title | Transfer Learning in 4D for Breast Cancer Diagnosis using Dynamic Contrast-Enhanced Magnetic Resonance Imaging |
| Authors | Qiyuan Hu, Heather M. Whitney, Maryellen L. Giger |
| Abstract | Deep transfer learning using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has shown strong predictive power in characterization of breast lesions. However, pretrained convolutional neural networks (CNNs) require 2D inputs, limiting the ability to exploit the rich 4D (volumetric and temporal) image information inherent in DCE-MRI that is clinically valuable for lesion assessment. Training 3D CNNs from scratch, a common method to utilize high-dimensional information in medical images, is computationally expensive and is not best suited for moderately sized healthcare datasets. Therefore, we propose a novel approach using transfer learning that incorporates the 4D information from DCE-MRI, where volumetric information is collapsed at feature level by max pooling along the projection perpendicular to the transverse slices and the temporal information is contained either in second-post contrast subtraction images. Our methodology yielded an area under the receiver operating characteristic curve of 0.89+/-0.01 on a dataset of 1161 breast lesions, significantly outperforming a previous approach that incorporates the 4D information in DCE-MRI by the use of maximum intensity projection (MIP) images. |
| Tasks | Transfer Learning |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03022v1 |
| https://arxiv.org/pdf/1911.03022v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-in-4d-for-breast-cancer |
| Repo | |
| Framework | |
Template co-updating in multi-modal human activity recognition systems
| Title | Template co-updating in multi-modal human activity recognition systems |
| Authors | Annalisa Franco, Antonio Magnani, Dario Maio |
| Abstract | Multi-modal systems are quite common in the context of human activity recognition; widely used RGB-D sensors (Kinect is the most prominent example) give access to parallel data streams, typically RGB images, depth data, skeleton information. The richness of multimodal information has been largely exploited in many works in the literature, while an analysis of their effectiveness for incremental template updating has not been investigated so far. This paper is aimed at defining a general framework for unsupervised template updating in multi-modal systems, where the different data sources can provide complementary information, increasing the effectiveness of the updating procedure and reducing at the same time the probability of incorrect template modifications. |
| Tasks | Activity Recognition, Human Activity Recognition |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.02024v1 |
| https://arxiv.org/pdf/1912.02024v1.pdf | |
| PWC | https://paperswithcode.com/paper/template-co-updating-in-multi-modal-human |
| Repo | |
| Framework | |
Playing Flappy Bird via Asynchronous Advantage Actor Critic Algorithm
| Title | Playing Flappy Bird via Asynchronous Advantage Actor Critic Algorithm |
| Authors | Elit Cenk Alp, Mehmet Serdar Guzel |
| Abstract | Flappy Bird, which has a very high popularity, has been trained in many algorithms. Some of these studies were trained from raw pixel values of game and some from specific attributes. In this study, the model was trained with raw game images, which had not been seen before. The trained model has learned as reinforcement when to make which decision. As an input to the model, the reward or penalty at the end of each step was returned and the training was completed. Flappy Bird game was trained with the Reinforcement Learning algorithm Deep Q-Network and Asynchronous Advantage Actor Critic (A3C) algorithms. |
| Tasks | |
| Published | 2019-07-06 |
| URL | https://arxiv.org/abs/1907.03098v1 |
| https://arxiv.org/pdf/1907.03098v1.pdf | |
| PWC | https://paperswithcode.com/paper/playing-flappy-bird-via-asynchronous |
| Repo | |
| Framework | |
BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation
| Title | BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation |
| Authors | Wanhua Li, Jiwen Lu, Jianjiang Feng, Chunjing Xu, Jie Zhou, Qi Tian |
| Abstract | Age estimation is an important yet very challenging problem in computer vision. Existing methods for age estimation usually apply a divide-and-conquer strategy to deal with heterogeneous data caused by the non-stationary aging process. However, the facial aging process is also a continuous process, and the continuity relationship between different components has not been effectively exploited. In this paper, we propose BridgeNet for age estimation, which aims to mine the continuous relation between age labels effectively. The proposed BridgeNet consists of local regressors and gating networks. Local regressors partition the data space into multiple overlapping subspaces to tackle heterogeneous data and gating networks learn continuity aware weights for the results of local regressors by employing the proposed bridge-tree structure, which introduces bridge connections into tree models to enforce the similarity between neighbor nodes. Moreover, these two components of BridgeNet can be jointly learned in an end-to-end way. We show experimental results on the MORPH II, FG-NET and Chalearn LAP 2015 datasets and find that BridgeNet outperforms the state-of-the-art methods. |
| Tasks | Age Estimation |
| Published | 2019-04-06 |
| URL | http://arxiv.org/abs/1904.03358v1 |
| http://arxiv.org/pdf/1904.03358v1.pdf | |
| PWC | https://paperswithcode.com/paper/bridgenet-a-continuity-aware-probabilistic |
| Repo | |
| Framework | |
Automated Surgical Activity Recognition with One Labeled Sequence
| Title | Automated Surgical Activity Recognition with One Labeled Sequence |
| Authors | Robert DiPietro, Gregory D. Hager |
| Abstract | Prior work has demonstrated the feasibility of automated activity recognition in robot-assisted surgery from motion data. However, these efforts have assumed the availability of a large number of densely-annotated sequences, which must be provided manually by experts. This process is tedious, expensive, and error-prone. In this paper, we present the first analysis under the assumption of scarce annotations, where as little as one annotated sequence is available for training. We demonstrate feasibility of automated recognition in this challenging setting, and we show that learning representations in an unsupervised fashion, before the recognition phase, leads to significant gains in performance. In addition, our paper poses a new challenge to the community: how much further can we push performance in this important yet relatively unexplored regime? |
| Tasks | Activity Recognition |
| Published | 2019-07-20 |
| URL | https://arxiv.org/abs/1907.08825v1 |
| https://arxiv.org/pdf/1907.08825v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-surgical-activity-recognition-with |
| Repo | |
| Framework | |
Classical and Quantum Algorithms for Tensor Principal Component Analysis
| Title | Classical and Quantum Algorithms for Tensor Principal Component Analysis |
| Authors | M. B. Hastings |
| Abstract | We present classical and quantum algorithms based on spectral methods for a problem in tensor principal component analysis. The quantum algorithm achieves a quartic speedup while using exponentially smaller space than the fastest classical spectral algorithm, and a super-polynomial speedup over classical algorithms that use only polynomial space. The classical algorithms that we present are related to, but slightly different from those presented recently in Ref. 1. In particular, we have an improved threshold for recovery and the algorithms we present work for both even and odd order tensors. These results suggest that large-scale inference problems are a promising future application for quantum computers. |
| Tasks | |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.12724v2 |
| https://arxiv.org/pdf/1907.12724v2.pdf | |
| PWC | https://paperswithcode.com/paper/classical-and-quantum-algorithms-for-tensor |
| Repo | |
| Framework | |
A Recurrent Variational Autoencoder for Speech Enhancement
| Title | A Recurrent Variational Autoencoder for Speech Enhancement |
| Authors | Simon Leglaive, Xavier Alameda-Pineda, Laurent Girin, Radu Horaud |
| Abstract | This paper presents a generative approach to speech enhancement based on a recurrent variational autoencoder (RVAE). The deep generative speech model is trained using clean speech signals only, and it is combined with a nonnegative matrix factorization noise model for speech enhancement. We propose a variational expectation-maximization algorithm where the encoder of the RVAE is fine-tuned at test time, to approximate the distribution of the latent variables given the noisy speech observations. Compared with previous approaches based on feed-forward fully-connected architectures, the proposed recurrent deep generative speech model induces a posterior temporal dynamic over the latent variables, which is shown to improve the speech enhancement results. |
| Tasks | Speech Enhancement |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.10942v2 |
| https://arxiv.org/pdf/1910.10942v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-recurrent-variational-autoencoder-for |
| Repo | |
| Framework | |
