Paper Group ANR 453
Using association rule mining and ontologies to generate metadata recommendations from multiple biomedical databases. Constrained Generative Adversarial Networks for Interactive Image Generation. Multi-Gradient Descent for Multi-Objective Recommender Systems. Reinforcement Learning of Minimalist Numeral Grammars. Detecting Multiple Speech Disfluenc …
Using association rule mining and ontologies to generate metadata recommendations from multiple biomedical databases
| Title | Using association rule mining and ontologies to generate metadata recommendations from multiple biomedical databases |
| Authors | Marcos Martínez-Romero, Martin J. O’Connor, Attila L. Egyedi, Debra Willrett, Josef Hardi, John Graybeal, Mark A. Musen |
| Abstract | Metadata-the machine-readable descriptions of the data-are increasingly seen as crucial for describing the vast array of biomedical datasets that are currently being deposited in public repositories. While most public repositories have firm requirements that metadata must accompany submitted datasets, the quality of those metadata is generally very poor. A key problem is that the typical metadata acquisition process is onerous and time consuming, with little interactive guidance or assistance provided to users. Secondary problems include the lack of validation and sparse use of standardized terms or ontologies when authoring metadata. There is a pressing need for improvements to the metadata acquisition process that will help users to enter metadata quickly and accurately. In this paper we outline a recommendation system for metadata that aims to address this challenge. Our approach uses association rule mining to uncover hidden associations among metadata values and to represent them in the form of association rules. These rules are then used to present users with real-time recommendations when authoring metadata. The novelties of our method are that it is able to combine analyses of metadata from multiple repositories when generating recommendations and can enhance those recommendations by aligning them with ontology terms. We implemented our approach as a service integrated into the CEDAR Workbench metadata authoring platform, and evaluated it using metadata from two public biomedical repositories: US-based National Center for Biotechnology Information (NCBI) BioSample and European Bioinformatics Institute (EBI) BioSamples. The results show that our approach is able to use analyses of previous entered metadata coupled with ontology-based mappings to present users with accurate recommendations when authoring metadata. |
| Tasks | |
| Published | 2019-03-21 |
| URL | http://arxiv.org/abs/1903.09270v1 |
| http://arxiv.org/pdf/1903.09270v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-association-rule-mining-and-ontologies |
| Repo | |
| Framework | |
Constrained Generative Adversarial Networks for Interactive Image Generation
| Title | Constrained Generative Adversarial Networks for Interactive Image Generation |
| Authors | Eric Heim |
| Abstract | Generative Adversarial Networks (GANs) have received a great deal of attention due in part to recent success in generating original, high-quality samples from visual domains. However, most current methods only allow for users to guide this image generation process through limited interactions. In this work we develop a novel GAN framework that allows humans to be “in-the-loop” of the image generation process. Our technique iteratively accepts relative constraints of the form “Generate an image more like image A than image B”. After each constraint is given, the user is presented with new outputs from the GAN, informing the next round of feedback. This feedback is used to constrain the output of the GAN with respect to an underlying semantic space that can be designed to model a variety of different notions of similarity (e.g. classes, attributes, object relationships, color, etc.). In our experiments, we show that our GAN framework is able to generate images that are of comparable quality to equivalent unsupervised GANs while satisfying a large number of the constraints provided by users, effectively changing a GAN into one that allows users interactive control over image generation without sacrificing image quality. |
| Tasks | Image Generation |
| Published | 2019-04-03 |
| URL | http://arxiv.org/abs/1904.02526v1 |
| http://arxiv.org/pdf/1904.02526v1.pdf | |
| PWC | https://paperswithcode.com/paper/constrained-generative-adversarial-networks |
| Repo | |
| Framework | |
Multi-Gradient Descent for Multi-Objective Recommender Systems
| Title | Multi-Gradient Descent for Multi-Objective Recommender Systems |
| Authors | Nikola Milojkovic, Diego Antognini, Giancarlo Bergamin, Boi Faltings, Claudiu Musat |
| Abstract | Recommender systems need to mirror the complexity of the environment they are applied in. The more we know about what might benefit the user, the more objectives the recommender system has. In addition there may be multiple stakeholders - sellers, buyers, shareholders - in addition to legal and ethical constraints. Simultaneously optimizing for a multitude of objectives, correlated and not correlated, having the same scale or not, has proven difficult so far. We introduce a stochastic multi-gradient descent approach to recommender systems (MGDRec) to solve this problem. We show that this exceeds state-of-the-art methods in traditional objective mixtures, like revenue and recall. Not only that, but through gradient normalization we can combine fundamentally different objectives, having diverse scales, into a single coherent framework. We show that uncorrelated objectives, like the proportion of quality products, can be improved alongside accuracy. Through the use of stochasticity, we avoid the pitfalls of calculating full gradients and provide a clear setting for its applicability. |
| Tasks | Recommendation Systems |
| Published | 2019-12-09 |
| URL | https://arxiv.org/abs/2001.00846v2 |
| https://arxiv.org/pdf/2001.00846v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-gradient-descent-for-multi-objective |
| Repo | |
| Framework | |
Reinforcement Learning of Minimalist Numeral Grammars
| Title | Reinforcement Learning of Minimalist Numeral Grammars |
| Authors | Peter beim Graben, Ronald Römer, Werner Meyer, Markus Huber, Matthias Wolff |
| Abstract | Speech-controlled user interfaces facilitate the operation of devices and household functions to laymen. State-of-the-art language technology scans the acoustically analyzed speech signal for relevant keywords that are subsequently inserted into semantic slots to interpret the user’s intent. In order to develop proper cognitive information and communication technologies, simple slot-filling should be replaced by utterance meaning transducers (UMT) that are based on semantic parsers and a \emph{mental lexicon}, comprising syntactic, phonetic and semantic features of the language under consideration. This lexicon must be acquired by a cognitive agent during interaction with its users. We outline a reinforcement learning algorithm for the acquisition of the syntactic morphology and arithmetic semantics of English numerals, based on minimalist grammar (MG), a recent computational implementation of generative linguistics. Number words are presented to the agent by a teacher in form of utterance meaning pairs (UMP) where the meanings are encoded as arithmetic terms from a suitable term algebra. Since MG encodes universal linguistic competence through inference rules, thereby separating innate linguistic knowledge from the contingently acquired lexicon, our approach unifies generative grammar and reinforcement learning, hence potentially resolving the still pending Chomsky-Skinner controversy. |
| Tasks | Slot Filling |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04447v1 |
| https://arxiv.org/pdf/1906.04447v1.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-of-minimalist-numeral |
| Repo | |
| Framework | |
Detecting Multiple Speech Disfluencies using a Deep Residual Network with Bidirectional Long Short-Term Memory
| Title | Detecting Multiple Speech Disfluencies using a Deep Residual Network with Bidirectional Long Short-Term Memory |
| Authors | Tedd Kourkounakis, Amirhossein Hajavi, Ali Etemad |
| Abstract | Stuttering is a speech impediment affecting tens of millions of people on an everyday basis. Even with its commonality, there is minimal data and research on the identification and classification of stuttered speech. This paper tackles the problem of detection and classification of different forms of stutter. As opposed to most existing works that identify stutters with language models, our work proposes a model that relies solely on acoustic features, allowing for identification of several variations of stutter disfluencies without the need for speech recognition. Our model uses a deep residual network and bidirectional long short-term memory layers to classify different types of stutters and achieves an average miss rate of 10.03%, outperforming the state-of-the-art by almost 27% |
| Tasks | Speech Recognition |
| Published | 2019-10-17 |
| URL | https://arxiv.org/abs/1910.12590v1 |
| https://arxiv.org/pdf/1910.12590v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-multiple-speech-disfluencies-using |
| Repo | |
| Framework | |
Online Pedestrian Group Walking Event Detection Using Spectral Analysis of Motion Similarity Graph
| Title | Online Pedestrian Group Walking Event Detection Using Spectral Analysis of Motion Similarity Graph |
| Authors | Vahid Bastani, Damian Campo, Lucio Marcenaro, Carlo S. Regazzoni |
| Abstract | A method for online identification of group of moving objects in the video is proposed in this paper. This method at each frame identifies group of tracked objects with similar local instantaneous motion pattern using spectral clustering on motion similarity graph. Then, the output of the algorithm is used to detect the event of more than two object moving together as required by PETS2015 challenge. The performance of the algorithm is evaluated on the PETS2015 dataset. |
| Tasks | |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.01258v1 |
| https://arxiv.org/pdf/1909.01258v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-pedestrian-group-walking-event |
| Repo | |
| Framework | |
A Formal Axiomatization of Computation
| Title | A Formal Axiomatization of Computation |
| Authors | Rasoul Ramezanian |
| Abstract | We introduce an axiomatization for the notion of computation. Based on the idea of Brouwer choice sequences, we construct a model, denoted by $E$, which satisfies our axioms and $E \models \mathrm{ P \neq NP}$. In other words, regarding “effective computability” in Brouwer intuitionism viewpoint, we show $\mathrm{ P \neq NP}$. |
| Tasks | |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.03533v2 |
| https://arxiv.org/pdf/1907.03533v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-formal-axiomatization-of-computation |
| Repo | |
| Framework | |
Inverse Attention Guided Deep Crowd Counting Network
| Title | Inverse Attention Guided Deep Crowd Counting Network |
| Authors | Vishwanath A. Sindagi, Vishal M. Patel |
| Abstract | In this paper, we address the challenging problem of crowd counting in congested scenes. Specifically, we present Inverse Attention Guided Deep Crowd Counting Network (IA-DCCN) that efficiently infuses segmentation information through an inverse attention mechanism into the counting network, resulting in significant improvements. The proposed method, which is based on VGG-16, is a single-step training framework and is simple to implement. The use of segmentation information results in minimal computational overhead and does not require any additional annotations. We demonstrate the significance of segmentation guided inverse attention through a detailed analysis and ablation study. Furthermore, the proposed method is evaluated on three challenging crowd counting datasets and is shown to achieve significant improvements over several recent methods. |
| Tasks | Crowd Counting |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01193v2 |
| https://arxiv.org/pdf/1907.01193v2.pdf | |
| PWC | https://paperswithcode.com/paper/inverse-attention-guided-deep-crowd-counting |
| Repo | |
| Framework | |
Link Stream Graph for Temporal Recommendations
| Title | Link Stream Graph for Temporal Recommendations |
| Authors | Armel Jacques Nzekon Nzeko’o, Maurice Tchuente, Matthieu Latapy |
| Abstract | Several researches on recommender systems are based on explicit rating data, but in many real world e-commerce platforms, ratings are not always available, and in those situations, recommender systems have to deal with implicit data such as users’ purchase history, browsing history and streaming history. In this context, classical bipartite user-item graphs (BIP) are widely used to compute top-N recommendations. However, these graphs have some limitations, particularly in terms of taking temporal dynamic into account. This is not good because users’ preference change over time. To overcome this limit, the Session-based Temporal Graph (STG) was proposed by Xiang et al. to combine long- and short-term preferences in a graph-based recommender system. But in the STG, time is divided into slices and therefore considered discontinuously. This approach loses details of the real temporal dynamics of user actions. To address this challenge, we propose the Link Stream Graph (LSG) which is an extension of link stream representation proposed by Latapy et al. and which allows to model interactions between users and items by considering time continuously. Experiments conducted on four real world implicit datasets for temporal recommendation, with 3 evaluation metrics, show that LSG is the best in 9 out of 12 cases compared to BIP and STG which are the most used state-of-the-art recommender graphs. |
| Tasks | Recommendation Systems |
| Published | 2019-03-27 |
| URL | http://arxiv.org/abs/1904.12576v1 |
| http://arxiv.org/pdf/1904.12576v1.pdf | |
| PWC | https://paperswithcode.com/paper/190412576 |
| Repo | |
| Framework | |
Singing Synthesis: with a little help from my attention
| Title | Singing Synthesis: with a little help from my attention |
| Authors | Orazio Angelini, Alexis Moinet, Kayoko Yanagisawa, Thomas Drugman |
| Abstract | We present a novel system for singing synthesis, based on attention. Starting from a musical score with notes and lyrics, we build a phoneme-level multi stream note embedding. The embedding contains the information encoded in the score regarding pitch, duration and the phonemes to be pronounced on each note. This note representation is used to condition an attention-based sequence-to-sequence architecture, in order to generate mel-spectrograms. Our model demonstrates attention can be successfully applied to the singing synthesis field. The system requires considerably less explicit modelling of voice features such as F0 patterns, vibratos, and note and phoneme durations, than most models in the literature. However, we observe that completely dispensing with any duration modelling introduces occasional instabilities in the generated spectrograms. We train an autoregressive WaveNet to be used as a neural vocoder to synthesise the mel-spectrograms produced by the sequence-to-sequence architecture, using a combination of speech and singing data. |
| Tasks | |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.05881v1 |
| https://arxiv.org/pdf/1912.05881v1.pdf | |
| PWC | https://paperswithcode.com/paper/singing-synthesis-with-a-little-help-from-my |
| Repo | |
| Framework | |
Back Attention Knowledge Transfer for Low-resource Named Entity Recognition
| Title | Back Attention Knowledge Transfer for Low-resource Named Entity Recognition |
| Authors | Linghao Sun, Huixiong Yi, Yong Liu, Huanhuan Chen, Chunyan Miao |
| Abstract | In recent years, great success has been achieved in the field of natural language processing (NLP), thanks in part to the considerable amount of annotated resources. For named entity recognition (NER), most languages do not have such an abundance of labeled data as English, so the performances of those languages are relatively lower. To improve the performance, we propose a general approach called Back Attention Network (BAN). BAN uses a translation system to translate other language sentences into English and then applies a new mechanism named back attention knowledge transfer to obtain task-specific information from pre-trained high-resource languages NER model. This strategy can transfer high-layer features of well-trained model and enrich the semantic representations of the original language. Experiments on three different language datasets indicate that the proposed approach outperforms other state-of-the-art methods. |
| Tasks | Named Entity Recognition, Transfer Learning |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01183v2 |
| https://arxiv.org/pdf/1906.01183v2.pdf | |
| PWC | https://paperswithcode.com/paper/back-attention-knowledge-transfer-for-low |
| Repo | |
| Framework | |
Generative Adversarial Network for Handwritten Text
| Title | Generative Adversarial Network for Handwritten Text |
| Authors | Bo Ji, Tianyi Chen |
| Abstract | Generative adversarial networks (GANs) have proven hugely successful in variety of applications of image processing. However, generative adversarial networks for handwriting is relatively rare somehow because of difficulty of handling sequential handwriting data by Convolutional Neural Network (CNN). In this paper, we propose a handwriting generative adversarial network framework (HWGANs) for synthesizing handwritten stroke data. The main features of the new framework include: (i) A discriminator consists of an integrated CNN-Long-Short-Term- Memory (LSTM) based feature extraction with Path Signature Features (PSF) as input and a Feedforward Neural Network (FNN) based binary classifier; (ii) A recurrent latent variable model as generator for synthesizing sequential handwritten data. The numerical experiments show the effectivity of the new model. Moreover, comparing with sole handwriting generator, the HWGANs synthesize more natural and realistic handwritten text. |
| Tasks | |
| Published | 2019-07-27 |
| URL | https://arxiv.org/abs/1907.11845v3 |
| https://arxiv.org/pdf/1907.11845v3.pdf | |
| PWC | https://paperswithcode.com/paper/generative-adversarial-network-for-2 |
| Repo | |
| Framework | |
Classifying Signals on Irregular Domains via Convolutional Cluster Pooling
| Title | Classifying Signals on Irregular Domains via Convolutional Cluster Pooling |
| Authors | Angelo Porrello, Davide Abati, Simone Calderara, Rita Cucchiara |
| Abstract | We present a novel and hierarchical approach for supervised classification of signals spanning over a fixed graph, reflecting shared properties of the dataset. To this end, we introduce a Convolutional Cluster Pooling layer exploiting a multi-scale clustering in order to highlight, at different resolutions, locally connected regions on the input graph. Our proposal generalises well-established neural models such as Convolutional Neural Networks (CNNs) on irregular and complex domains, by means of the exploitation of the weight sharing property in a graph-oriented architecture. In this work, such property is based on the centrality of each vertex within its soft-assigned cluster. Extensive experiments on NTU RGB+D, CIFAR-10 and 20NEWS demonstrate the effectiveness of the proposed technique in capturing both local and global patterns in graph-structured data out of different domains. |
| Tasks | |
| Published | 2019-02-13 |
| URL | http://arxiv.org/abs/1902.04850v1 |
| http://arxiv.org/pdf/1902.04850v1.pdf | |
| PWC | https://paperswithcode.com/paper/classifying-signals-on-irregular-domains-via |
| Repo | |
| Framework | |
Distributional Reinforcement Learning for Efficient Exploration
| Title | Distributional Reinforcement Learning for Efficient Exploration |
| Authors | Borislav Mavrin, Shangtong Zhang, Hengshuai Yao, Linglong Kong, Kaiwen Wu, Yaoliang Yu |
| Abstract | In distributional reinforcement learning (RL), the estimated distribution of value function models both the parametric and intrinsic uncertainties. We propose a novel and efficient exploration method for deep RL that has two components. The first is a decaying schedule to suppress the intrinsic uncertainty. The second is an exploration bonus calculated from the upper quantiles of the learned distribution. In Atari 2600 games, our method outperforms QR-DQN in 12 out of 14 hard games (achieving 483 % average gain across 49 games in cumulative rewards over QR-DQN with a big win in Venture). We also compared our algorithm with QR-DQN in a challenging 3D driving simulator (CARLA). Results show that our algorithm achieves near-optimal safety rewards twice faster than QRDQN. |
| Tasks | Atari Games, Distributional Reinforcement Learning, Efficient Exploration |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.06125v1 |
| https://arxiv.org/pdf/1905.06125v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributional-reinforcement-learning-for |
| Repo | |
| Framework | |
Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Space
| Title | Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Space |
| Authors | AkshatKumar Nigam, Pascal Friederich, Mario Krenn, Alán Aspuru-Guzik |
| Abstract | Challenges in natural sciences can often be phrased as optimization problems. Machine learning techniques have recently been applied to solve such problems. One example in chemistry is the design of tailor-made organic materials and molecules, which requires efficient methods to explore the chemical space. We present a genetic algorithm (GA) that is enhanced with a neural network (DNN) based discriminator model to improve the diversity of generated molecules and at the same time steer the GA. We show that our algorithm outperforms other generative models in optimization tasks. We furthermore present a way to increase interpretability of genetic algorithms, which helped us to derive design principles. |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11655v4 |
| https://arxiv.org/pdf/1909.11655v4.pdf | |
| PWC | https://paperswithcode.com/paper/augmenting-genetic-algorithms-with-deep |
| Repo | |
| Framework | |
