Paper Group ANR 1032
Generating protein sequences from antibiotic resistance genes data using Generative Adversarial Networks. Modeling Event Propagation via Graph Biased Temporal Point Process. The principles of adaptation in organisms and machines I: machine learning, information theory, and thermodynamics. Exact and fast inversion of the approximate discrete Radon t …
Generating protein sequences from antibiotic resistance genes data using Generative Adversarial Networks
| Title | Generating protein sequences from antibiotic resistance genes data using Generative Adversarial Networks |
| Authors | Prabal Chhibbar, Arpit Joshi |
| Abstract | We introduce a method to generate synthetic protein sequences which are predicted to be resistant to certain antibiotics. We did this using 6,023 genes that were predicted to be resistant to antibiotics in the intestinal region of the human gut and were fed as input to a Wasserstein generative adversarial network (W-GAN) model a variant to the original generative adversarial model which has been known to perform efficiently when it comes to mimicking the distribution of the real data in order to generate new data which is similar in style to the original data which was fed as the training data |
| Tasks | |
| Published | 2019-04-28 |
| URL | http://arxiv.org/abs/1904.13240v1 |
| http://arxiv.org/pdf/1904.13240v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-protein-sequences-from-antibiotic |
| Repo | |
| Framework | |
Modeling Event Propagation via Graph Biased Temporal Point Process
| Title | Modeling Event Propagation via Graph Biased Temporal Point Process |
| Authors | Weichang Wu, Huanxi Liu, Xiaohu Zhang, Yu Liu, Hongyuan Zha |
| Abstract | Temporal point process is widely used for sequential data modeling. In this paper, we focus on the problem of modeling sequential event propagation in graph, such as retweeting by social network users, news transmitting between websites, etc. Given a collection of event propagation sequences, conventional point process model consider only the event history, i.e. embed event history into a vector, not the latent graph structure. We propose a Graph Biased Temporal Point Process (GBTPP) leveraging the structural information from graph representation learning, where the direct influence between nodes and indirect influence from event history is modeled respectively. Moreover, the learned node embedding vector is also integrated into the embedded event history as side information. Experiments on a synthetic dataset and two real-world datasets show the efficacy of our model compared to conventional methods and state-of-the-art. |
| Tasks | Graph Representation Learning, Representation Learning |
| Published | 2019-08-05 |
| URL | https://arxiv.org/abs/1908.01623v1 |
| https://arxiv.org/pdf/1908.01623v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-event-propagation-via-graph-biased |
| Repo | |
| Framework | |
The principles of adaptation in organisms and machines I: machine learning, information theory, and thermodynamics
| Title | The principles of adaptation in organisms and machines I: machine learning, information theory, and thermodynamics |
| Authors | Hideaki Shimazaki |
| Abstract | How do organisms recognize their environment by acquiring knowledge about the world, and what actions do they take based on this knowledge? This article examines hypotheses about organisms’ adaptation to the environment from machine learning, information-theoretic, and thermodynamic perspectives. We start with constructing a hierarchical model of the world as an internal model in the brain, and review standard machine learning methods to infer causes by approximately learning the model under the maximum likelihood principle. This in turn provides an overview of the free energy principle for an organism, a hypothesis to explain perception and action from the principle of least surprise. Treating this statistical learning as communication between the world and brain, learning is interpreted as a process to maximize information about the world. We investigate how the classical theories of perception such as the infomax principle relates to learning the hierarchical model. We then present an approach to the recognition and learning based on thermodynamics, showing that adaptation by causal learning results in the second law of thermodynamics whereas inference dynamics that fuses observation with prior knowledge forms a thermodynamic process. These provide a unified view on the adaptation of organisms to the environment. |
| Tasks | |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.11233v1 |
| http://arxiv.org/pdf/1902.11233v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-principles-of-adaptation-in-organisms-and |
| Repo | |
| Framework | |
Exact and fast inversion of the approximate discrete Radon transform from partial data
| Title | Exact and fast inversion of the approximate discrete Radon transform from partial data |
| Authors | Donsub Rim |
| Abstract | We give an exact inversion formula for the approximate discrete Radon transform introduced in [Brady, SIAM J. Comput., 27(1), 107–119] that is of cost $O(N \log N)$ for a square 2D image with $N$ pixels and requires only partial data. |
| Tasks | |
| Published | 2019-08-02 |
| URL | https://arxiv.org/abs/1908.00887v2 |
| https://arxiv.org/pdf/1908.00887v2.pdf | |
| PWC | https://paperswithcode.com/paper/exact-and-fast-inversion-of-the-approximate |
| Repo | |
| Framework | |
Partition Pruning: Parallelization-Aware Pruning for Deep Neural Networks
| Title | Partition Pruning: Parallelization-Aware Pruning for Deep Neural Networks |
| Authors | Sina Shahhosseini, Ahmad Albaqsami, Masoomeh Jasemi, Nader Bagherzadeh |
| Abstract | Parameters of recent neural networks require a huge amount of memory. These parameters are used by neural networks to perform machine learning tasks when processing inputs. To speed up inference, we develop Partition Pruning, an innovative scheme to reduce the parameters used while taking into consideration parallelization. We evaluated the performance and energy consumption of parallel inference of partitioned models, which showed a 7.72x speed up of performance and a 2.73x reduction in the energy used for computing pruned layers of TinyVGG16 in comparison to running the unpruned model on a single accelerator. In addition, our method showed a limited reduction some numbers in accuracy while partitioning fully connected layers. |
| Tasks | |
| Published | 2019-01-21 |
| URL | http://arxiv.org/abs/1901.11391v2 |
| http://arxiv.org/pdf/1901.11391v2.pdf | |
| PWC | https://paperswithcode.com/paper/partition-pruning-parallelization-aware |
| Repo | |
| Framework | |
Towards Generalized Speech Enhancement with Generative Adversarial Networks
| Title | Towards Generalized Speech Enhancement with Generative Adversarial Networks |
| Authors | Santiago Pascual, Joan Serrà, Antonio Bonafonte |
| Abstract | The speech enhancement task usually consists of removing additive noise or reverberation that partially mask spoken utterances, affecting their intelligibility. However, little attention is drawn to other, perhaps more aggressive signal distortions like clipping, chunk elimination, or frequency-band removal. Such distortions can have a large impact not only on intelligibility, but also on naturalness or even speaker identity, and require of careful signal reconstruction. In this work, we give full consideration to this generalized speech enhancement task, and show it can be tackled with a time-domain generative adversarial network (GAN). In particular, we extend a previous GAN-based speech enhancement system to deal with mixtures of four types of aggressive distortions. Firstly, we propose the addition of an adversarial acoustic regression loss that promotes a richer feature extraction at the discriminator. Secondly, we also make use of a two-step adversarial training schedule, acting as a warm up-and-fine-tune sequence. Both objective and subjective evaluations show that these two additions bring improved speech reconstructions that better match the original speaker identity and naturalness. |
| Tasks | Speech Enhancement |
| Published | 2019-04-06 |
| URL | http://arxiv.org/abs/1904.03418v1 |
| http://arxiv.org/pdf/1904.03418v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-generalized-speech-enhancement-with |
| Repo | |
| Framework | |
The Herbarium Challenge 2019 Dataset
| Title | The Herbarium Challenge 2019 Dataset |
| Authors | Kiat Chuan Tan, Yulong Liu, Barbara Ambrose, Melissa Tulig, Serge Belongie |
| Abstract | Herbarium sheets are invaluable for botanical research, and considerable time and effort is spent by experts to label and identify specimens on them. In view of recent advances in computer vision and deep learning, developing an automated approach to help experts identify specimens could significantly accelerate research in this area. Whereas most existing botanical datasets comprise photos of specimens in the wild, herbarium sheets exhibit dried specimens, which poses new challenges. We present a challenge dataset of herbarium sheet images labeled by experts, with the intent of facilitating the development of automated identification techniques for this challenging scenario. |
| Tasks | |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.05372v2 |
| https://arxiv.org/pdf/1906.05372v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-herbarium-challenge-2019-dataset |
| Repo | |
| Framework | |
Towards Robust ResNet: A Small Step but A Giant Leap
| Title | Towards Robust ResNet: A Small Step but A Giant Leap |
| Authors | Jingfeng Zhang, Bo Han, Laura Wynter, Kian Hsiang Low, Mohan Kankanhalli |
| Abstract | This paper presents a simple yet principled approach to boosting the robustness of the residual network (ResNet) that is motivated by the dynamical system perspective. Namely, a deep neural network can be interpreted using a partial differential equation, which naturally inspires us to characterize ResNet by an explicit Euler method. Our analytical studies reveal that the step factor h in the Euler method is able to control the robustness of ResNet in both its training and generalization. Specifically, we prove that a small step factor h can benefit the training robustness for back-propagation; from the view of forward-propagation, a small h can aid in the robustness of the model generalization. A comprehensive empirical evaluation on both vision CIFAR-10 and text AG-NEWS datasets confirms that a small h aids both the training and generalization robustness. |
| Tasks | |
| Published | 2019-02-28 |
| URL | https://arxiv.org/abs/1902.10887v3 |
| https://arxiv.org/pdf/1902.10887v3.pdf | |
| PWC | https://paperswithcode.com/paper/towards-robust-resnet-a-small-step-but-a |
| Repo | |
| Framework | |
NatCSNN: A Convolutional Spiking Neural Network for recognition of objects extracted from natural images
| Title | NatCSNN: A Convolutional Spiking Neural Network for recognition of objects extracted from natural images |
| Authors | Pedro Machado, Georgina Cosma, T. M McGinnity |
| Abstract | Biological image processing is performed by complex neural networks composed of thousands of neurons interconnected via thousands of synapses, some of which are excitatory and others inhibitory. Spiking neural models are distinguished from classical neurons by being biological plausible and exhibiting the same dynamics as those observed in biological neurons. This paper proposes a Natural Convolutional Neural Network (NatCSNN) which is a 3-layer bio-inspired Convolutional Spiking Neural Network (CSNN), for classifying objects extracted from natural images. A two-stage training algorithm is proposed using unsupervised Spike Timing Dependent Plasticity (STDP) learning (phase 1) and ReSuMe supervised learning (phase 2). The NatCSNN was trained and tested on the CIFAR-10 dataset and achieved an average testing accuracy of 84.7% which is an improvement over the 2-layer neural networks previously applied to this dataset. |
| Tasks | |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.08288v1 |
| https://arxiv.org/pdf/1909.08288v1.pdf | |
| PWC | https://paperswithcode.com/paper/natcsnn-a-convolutional-spiking-neural |
| Repo | |
| Framework | |
Large-Scale Semi-Supervised Learning via Graph Structure Learning over High-Dense Points
| Title | Large-Scale Semi-Supervised Learning via Graph Structure Learning over High-Dense Points |
| Authors | Zitong Wang, Li Wang, Raymond Chan, Tieyong Zeng |
| Abstract | We focus on developing a novel scalable graph-based semi-supervised learning (SSL) method for a small number of labeled data and a large amount of unlabeled data. Due to the lack of labeled data and the availability of large-scale unlabeled data, existing SSL methods usually encounter either suboptimal performance because of an improper graph or the high computational complexity of the large-scale optimization problem. In this paper, we propose to address both challenging problems by constructing a proper graph for graph-based SSL methods. Different from existing approaches, we simultaneously learn a small set of vertexes to characterize the high-dense regions of the input data and a graph to depict the relationships among these vertexes. A novel approach is then proposed to construct the graph of the input data from the learned graph of a small number of vertexes with some preferred properties. Without explicitly calculating the constructed graph of inputs, two transductive graph-based SSL approaches are presented with the computational complexity in linear with the number of input data. Extensive experiments on synthetic data and real datasets of varied sizes demonstrate that the proposed method is not only scalable for large-scale data, but also achieve good classification performance, especially for extremely small number of labels. |
| Tasks | |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.02233v1 |
| https://arxiv.org/pdf/1912.02233v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-semi-supervised-learning-via |
| Repo | |
| Framework | |
Sample Complexity Bounds for Influence Maximization
| Title | Sample Complexity Bounds for Influence Maximization |
| Authors | Gal Sadeh, Edith Cohen, Haim Kaplan |
| Abstract | Influence maximization (IM) is the problem of finding for a given $s\geq 1$ a set $S$ of $S=s$ nodes in a network with maximum influence. With stochastic diffusion models, the influence of a set $S$ of seed nodes is defined as the expectation of its reachability over simulations, where each simulation specifies a deterministic reachability function. Two well-studied special cases are the Independent Cascade (IC) and the Linear Threshold (LT) models of Kempe, Kleinberg, and Tardos. The influence function in stochastic diffusion is unbiasedly estimated by averaging reachability values over i.i.d. simulations. We study the IM sample complexity: the number of simulations needed to determine a $(1-\epsilon)$-approximate maximizer with confidence $1-\delta$. Our main result is a surprising upper bound of $O( s \tau \epsilon^{-2} \ln \frac{n}{\delta})$ for a broad class of models that includes IC and LT models and their mixtures, where $n$ is the number of nodes and $\tau$ is the number of diffusion steps. Generally $\tau \ll n$, so this significantly improves over the generic upper bound of $O(s n \epsilon^{-2} \ln \frac{n}{\delta})$. Our sample complexity bounds are derived from novel upper bounds on the variance of the reachability that allow for small relative error for influential sets and additive error when influence is small. Moreover, we provide a data-adaptive method that can detect and utilize fewer simulations on models where it suffices. Finally, we provide an efficient greedy design that computes an $(1-1/e-\epsilon)$-approximate maximizer from simulations and applies to any submodular stochastic diffusion model that satisfies the variance bounds. |
| Tasks | |
| Published | 2019-07-31 |
| URL | https://arxiv.org/abs/1907.13301v2 |
| https://arxiv.org/pdf/1907.13301v2.pdf | |
| PWC | https://paperswithcode.com/paper/influence-maximization-with-few-simulations |
| Repo | |
| Framework | |
Copula-like Variational Inference
| Title | Copula-like Variational Inference |
| Authors | Marcel Hirt, Petros Dellaportas, Alain Durmus |
| Abstract | This paper considers a new family of variational distributions motivated by Sklar’s theorem. This family is based on new copula-like densities on the hypercube with non-uniform marginals which can be sampled efficiently, i.e. with a complexity linear in the dimension of state space. Then, the proposed variational densities that we suggest can be seen as arising from these copula-like densities used as base distributions on the hypercube with Gaussian quantile functions and sparse rotation matrices as normalizing flows. The latter correspond to a rotation of the marginals with complexity $\mathcal{O}(d \log d)$. We provide some empirical evidence that such a variational family can also approximate non-Gaussian posteriors and can be beneficial compared to Gaussian approximations. Our method performs largely comparably to state-of-the-art variational approximations on standard regression and classification benchmarks for Bayesian Neural Networks. |
| Tasks | |
| Published | 2019-04-15 |
| URL | https://arxiv.org/abs/1904.07153v2 |
| https://arxiv.org/pdf/1904.07153v2.pdf | |
| PWC | https://paperswithcode.com/paper/copula-like-variational-inference |
| Repo | |
| Framework | |
A psychophysics approach for quantitative comparison of interpretable computer vision models
| Title | A psychophysics approach for quantitative comparison of interpretable computer vision models |
| Authors | Felix Biessmann, Dionysius Irza Refiano |
| Abstract | The field of transparent Machine Learning (ML) has contributed many novel methods aiming at better interpretability for computer vision and ML models in general. But how useful the explanations provided by transparent ML methods are for humans remains difficult to assess. Most studies evaluate interpretability in qualitative comparisons, they use experimental paradigms that do not allow for direct comparisons amongst methods or they report only offline experiments with no humans in the loop. While there are clear advantages of evaluations with no humans in the loop, such as scalability, reproducibility and less algorithmic bias than with humans in the loop, these metrics are limited in their usefulness if we do not understand how they relate to other metrics that take human cognition into account. Here we investigate the quality of interpretable computer vision algorithms using techniques from psychophysics. In crowdsourced annotation tasks we study the impact of different interpretability approaches on annotation accuracy and task time. In order to relate these findings to quality measures for interpretability without humans in the loop we compare quality metrics with and without humans in the loop. Our results demonstrate that psychophysical experiments allow for robust quality assessment of transparency in machine learning. Interestingly the quality metrics computed without humans in the loop did not provide a consistent ranking of interpretability methods nor were they representative for how useful an explanation was for humans. These findings highlight the potential of methods from classical psychophysics for modern machine learning applications. We hope that our results provide convincing arguments for evaluating interpretability in its natural habitat, human-ML interaction, if the goal is to obtain an authentic assessment of interpretability. |
| Tasks | |
| Published | 2019-11-24 |
| URL | https://arxiv.org/abs/1912.05011v1 |
| https://arxiv.org/pdf/1912.05011v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-psychophysics-approach-for-quantitative |
| Repo | |
| Framework | |
Using Sequence-to-Sequence Learning for Repairing C Vulnerabilities
| Title | Using Sequence-to-Sequence Learning for Repairing C Vulnerabilities |
| Authors | Zimin Chen, Steve Kommrusch, Martin Monperrus |
| Abstract | Software vulnerabilities affect all businesses and research is being done to avoid, detect or repair them. In this article, we contribute a new technique for automatic vulnerability fixing. We present a system that uses the rich software development history that can be found on GitHub to train an AI system that generates patches. We apply sequence-to-sequence learning on a big dataset of code changes and we evaluate the trained system on real world vulnerabilities from the CVE database. The result shows the feasibility of using sequence-to-sequence learning for fixing software vulnerabilities. |
| Tasks | |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.02015v1 |
| https://arxiv.org/pdf/1912.02015v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-sequence-to-sequence-learning-for |
| Repo | |
| Framework | |
ParaFIS:A new online fuzzy inference system based on parallel drift anticipation
| Title | ParaFIS:A new online fuzzy inference system based on parallel drift anticipation |
| Authors | Clement Leroy, Eric Anquetil, Nathalie Girard |
| Abstract | This paper proposes a new architecture of incremen-tal fuzzy inference system (also called Evolving Fuzzy System-EFS). In the context of classifying data stream in non stationary environment, concept drifts problems must be addressed. Several studies have shown that EFS can deal with such environment thanks to their high structural flexibility. These EFS perform well with smooth drift (or incremental drift). The new architecture we propose is focused on improving the processing of brutal changes in the data distribution (often called brutal concept drift). More precisely, a generalized EFS is paired with a module of anticipation to improve the adaptation of new rules after a brutal drift. The proposed architecture is evaluated on three datasets from UCI repository where artificial brutal drifts have been applied. A fit model is also proposed to get a “reactivity time” needed to converge to the steady-state and the score at end. Both characteristics are compared between the same system with and without anticipation and with a similar EFS from state-of-the-art. The experiments demonstrates improvements in both cases. |
| Tasks | |
| Published | 2019-07-15 |
| URL | https://arxiv.org/abs/1907.09285v1 |
| https://arxiv.org/pdf/1907.09285v1.pdf | |
| PWC | https://paperswithcode.com/paper/parafisa-new-online-fuzzy-inference-system |
| Repo | |
| Framework | |
