Paper Group ANR 1366
Amortized Inference of Variational Bounds for Learning Noisy-OR. Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data. Transferable Neural Projection Representations. Decoding Molecular Graph Embeddings with Reinforcement Learning. The informal semantics of Answer Set Programming: A Tarskian perspective. Progressive Fas …
Amortized Inference of Variational Bounds for Learning Noisy-OR
| Title | Amortized Inference of Variational Bounds for Learning Noisy-OR |
| Authors | Yiming Yan, Melissa Ailem, Fei Sha |
| Abstract | Classical approaches for approximate inference depend on cleverly designed variational distributions and bounds. Modern approaches employ amortized variational inference, which uses a neural network to approximate any posterior without leveraging the structures of the generative models. In this paper, we propose Amortized Conjugate Posterior (ACP), a hybrid approach taking advantages of both types of approaches. Specifically, we use the classical methods to derive specific forms of posterior distributions and then learn the variational parameters using amortized inference. We study the effectiveness of the proposed approach on the noisy-or model and compare to both the classical and the modern approaches for approximate inference and parameter learning. Our results show that the proposed method outperforms or are at par with other approaches. |
| Tasks | |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02428v2 |
| https://arxiv.org/pdf/1906.02428v2.pdf | |
| PWC | https://paperswithcode.com/paper/amortized-inference-of-variational-bounds-for |
| Repo | |
| Framework | |
Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data
| Title | Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data |
| Authors | Ke Gu, Dacheng Tao, Junfei Qiao, Weisi Lin |
| Abstract | In this paper we investigate into the problem of image quality assessment (IQA) and enhancement via machine learning. This issue has long attracted a wide range of attention in computational intelligence and image processing communities, since, for many practical applications, e.g. object detection and recognition, raw images are usually needed to be appropriately enhanced to raise the visual quality (e.g. visibility and contrast). In fact, proper enhancement can noticeably improve the quality of input images, even better than originally captured images which are generally thought to be of the best quality. In this work, we present two most important contributions. The first contribution is to develop a new no-reference (NR) IQA model. Given an image, our quality measure first extracts 17 features through analysis of contrast, sharpness, brightness and more, and then yields a measre of visual quality using a regression module, which is learned with big-data training samples that are much bigger than the size of relevant image datasets. Results of experiments on nine datasets validate the superiority and efficiency of our blind metric compared with typical state-of-the-art full-, reduced- and no-reference IQA methods. The second contribution is that a robust image enhancement framework is established based on quality optimization. For an input image, by the guidance of the proposed NR-IQA measure, we conduct histogram modification to successively rectify image brightness and contrast to a proper level. Thorough tests demonstrate that our framework can well enhance natural images, low-contrast images, low-light images and dehazed images. The source code will be released at https://sites.google.com/site/guke198701/publications. |
| Tasks | Image Enhancement, Image Quality Assessment, Object Detection |
| Published | 2019-04-18 |
| URL | http://arxiv.org/abs/1904.08632v1 |
| http://arxiv.org/pdf/1904.08632v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-no-reference-quality-assessment |
| Repo | |
| Framework | |
Transferable Neural Projection Representations
| Title | Transferable Neural Projection Representations |
| Authors | Chinnadhurai Sankar, Sujith Ravi, Zornitsa Kozareva |
| Abstract | Neural word representations are at the core of many state-of-the-art natural language processing models. A widely used approach is to pre-train, store and look up word or character embedding matrices. While useful, such representations occupy huge memory making it hard to deploy on-device and often do not generalize to unknown words due to vocabulary pruning. In this paper, we propose a skip-gram based architecture coupled with Locality-Sensitive Hashing (LSH) projections to learn efficient dynamically computable representations. Our model does not need to store lookup tables as representations are computed on-the-fly and require low memory footprint. The representations can be trained in an unsupervised fashion and can be easily transferred to other NLP tasks. For qualitative evaluation, we analyze the nearest neighbors of the word representations and discover semantically similar words even with misspellings. For quantitative evaluation, we plug our transferable projections into a simple LSTM and run it on multiple NLP tasks and show how our transferable projections achieve better performance compared to prior work. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01605v1 |
| https://arxiv.org/pdf/1906.01605v1.pdf | |
| PWC | https://paperswithcode.com/paper/transferable-neural-projection |
| Repo | |
| Framework | |
Decoding Molecular Graph Embeddings with Reinforcement Learning
| Title | Decoding Molecular Graph Embeddings with Reinforcement Learning |
| Authors | Steven Kearnes, Li Li, Patrick Riley |
| Abstract | We present RL-VAE, a graph-to-graph variational autoencoder that uses reinforcement learning to decode molecular graphs from latent embeddings. Methods have been described previously for graph-to-graph autoencoding, but these approaches require sophisticated decoders that increase the complexity of training and evaluation (such as requiring parallel encoders and decoders or non-trivial graph matching). Here, we repurpose a simple graph generator to enable efficient decoding and generation of molecular graphs. |
| Tasks | Graph Matching |
| Published | 2019-04-18 |
| URL | https://arxiv.org/abs/1904.08915v2 |
| https://arxiv.org/pdf/1904.08915v2.pdf | |
| PWC | https://paperswithcode.com/paper/decoding-molecular-graph-embeddings-with |
| Repo | |
| Framework | |
The informal semantics of Answer Set Programming: A Tarskian perspective
| Title | The informal semantics of Answer Set Programming: A Tarskian perspective |
| Authors | Marc Denecker, Yuliya Lierler, Miroslaw truszczynski, Joost Vennekens |
| Abstract | In Knowledge Representation, it is crucial that knowledge engineers have a good understanding of the formal expressions that they write. What formal expressions state intuitively about the domain of discourse is studied in the theory of the informal semantics of a logic. In this paper we study the informal semantics of Answer Set Programming. The roots of answer set programming lie in the language of Extended Logic Programming, which was introduced initially as an epistemic logic for default and autoepistemic reasoning. In 1999, the seminal papers on answer set programming proposed to use this logic for a different purpose, namely, to model and solve search problems. Currently, the language is used primarily in this new role. However, the original epistemic intuitions lose their explanatory relevance in this new context. How answer set programs are connected to the specifications of problems they model is more easily explained in a classical Tarskian semantics, in which models correspond to possible worlds, rather than to belief states of an epistemic agent. In this paper, we develop a new theory of the informal semantics of answer set programming, which is formulated in the Tarskian setting and based on Frege’s compositionality principle. It differs substantially from the earlier epistemic theory of informal semantics, providing a different view on the meaning of the connectives in answer set programming and on its relation to other logics, in particular classical logic. |
| Tasks | |
| Published | 2019-01-26 |
| URL | http://arxiv.org/abs/1901.09125v1 |
| http://arxiv.org/pdf/1901.09125v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-informal-semantics-of-answer-set |
| Repo | |
| Framework | |
Progressive Fashion Attribute Extraction
| Title | Progressive Fashion Attribute Extraction |
| Authors | Sandeep Singh Adhikari, Sukhneer Singh, Anoop Rajagopal, Aruna Rajan |
| Abstract | Extracting fashion attributes from images of people wearing clothing/fashion accessories is a very hard multi-class classification problem. Most often, even catalogues of fashion do not have all the fine-grained attributes tagged due to prohibitive cost of annotation. Using images of fashion articles, running multi-class attribute extraction with a single model for all kinds of attributes (neck design detailing, sleeves detailing, etc) requires classifiers that are robust to missing and ambiguously labelled data. In this work, we propose a progressive training approach for such multi-class classification, where weights learnt from an attribute are fine tuned for another attribute of the same fashion article (say, dresses). We branch networks for each attributes from a base network progressively during training. While it may have many labels, an image doesn’t need to have all possible labels for fashion articles present in it. We also compare our approach to multi-label classification, and demonstrate improvements over overall classification accuracies using our approach. |
| Tasks | Multi-Label Classification |
| Published | 2019-06-29 |
| URL | https://arxiv.org/abs/1907.00157v1 |
| https://arxiv.org/pdf/1907.00157v1.pdf | |
| PWC | https://paperswithcode.com/paper/progressive-fashion-attribute-extraction |
| Repo | |
| Framework | |
Flatsomatic: A Method for Compression of Somatic Mutation Profiles in Cancer
| Title | Flatsomatic: A Method for Compression of Somatic Mutation Profiles in Cancer |
| Authors | Geoffroy Dubourg-Felonneau, Yasmeen Kussad, Dominic Kirkham, John W Cassidy, Nirmesh Patel, Harry W Clifford |
| Abstract | In this study, we present Flatsomatic - a Variational Auto Encoder (VAE) optimized to compress somatic mutations that allow for unbiased data compression whilst maintaining the signal. We compared two different neural network architectures for the VAE: Multilayer Perceptron (MLP) and bidirectional LSTM. The somatic profiles we used to train our models consisted of 8,062 Pan-Cancer patients from The Cancer Genome Atlas and 989 cell lines from the COSMIC cell line project. The profiles for each patient were represented by the genomic loci where somatic mutations occurred and, to reduce sparsity, the locations with a frequency <5 were removed. We enhanced the VAE performance by changing its evidence lower bound, and devised an F1-score based loss showing that it helps the VAE learn better than with binary cross-entropy. We also employed beta-VAE to weight the variational regularisation term in the loss function and showed the best performance through a preliminary function to increase the weight of the regularisation term with each epoch. We assessed the reconstruction ability of the VAE using the micro F1-score metric and showed that our best performing model was a 2-layer deep MLP VAE. Our analysis also showed that the size of the latent space did not have a significant effect on the VAE learning ability. We compared the Flatsomatic embeddings created to a lower dimension version of the data from principal component analysis, showing superior performance of Flatsomatic, and performed K-means clustering on both datasets to draw comparisons to known cancer types of each profile. Finally, we present results that confirm that the Flatsomatic representations of 64 dimensions maintain the same predictive power as the original 8,298 dimensions vector, through prediction of drug response. |
| Tasks | |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.13259v1 |
| https://arxiv.org/pdf/1911.13259v1.pdf | |
| PWC | https://paperswithcode.com/paper/flatsomatic-a-method-for-compression-of |
| Repo | |
| Framework | |
Fast Exact Matrix Completion: A Unifying Optimization Framework
| Title | Fast Exact Matrix Completion: A Unifying Optimization Framework |
| Authors | Dimitris Bertsimas, Michael Lingzhi Li |
| Abstract | We consider the problem of matrix completion of rank $k$ on an $n\times m$ matrix. We show that both the general case and the case with side information can be formulated as a combinatorical problem of selecting $k$ vectors from $p$ column features. We demonstrate that it is equivalent to a separable optimization problem that is amenable to stochastic gradient descent. We design fastImpute, based on projected stochastic gradient descent, to enable efficient scaling of the algorithm of sizes of $10^5 \times 10^5$. We report experiments on both synthetic and real-world datasets that show fastImpute is competitive in both the accuracy of the matrix recovered and the time needed across all cases. Furthermore, when a high number of entries are missing, fastImpute is over $75%$ lower in MAPE and $10$x faster than current state-of-the-art matrix completion methods in both the case with side information and without. |
| Tasks | Matrix Completion |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09092v1 |
| https://arxiv.org/pdf/1910.09092v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-exact-matrix-completion-a-unifying |
| Repo | |
| Framework | |
Support Relation Analysis for Objects in Multiple View RGB-D Images
| Title | Support Relation Analysis for Objects in Multiple View RGB-D Images |
| Authors | Peng Zhang, Xiaoyu Ge, Jochen Renz |
| Abstract | Understanding physical relations between objects, especially their support relations, is crucial for robotic manipulation. There has been work on reasoning about support relations and structural stability of simple configurations in RGB-D images. In this paper, we propose a method for extracting more detailed physical knowledge from a set of RGB-D images taken from the same scene but from different views using qualitative reasoning and intuitive physical models. Rather than providing a simple contact relation graph and approximating stability over convex shapes, our method is able to provide a detailed supporting relation analysis based on a volumetric representation. Specifically, true supporting relations between objects (e.g., if an object supports another object by touching it on the side or if the object above contributes to the stability of the object below) are identified. We apply our method to real-world structures captured in warehouse scenarios and show our method works as desired. |
| Tasks | |
| Published | 2019-05-10 |
| URL | https://arxiv.org/abs/1905.04084v1 |
| https://arxiv.org/pdf/1905.04084v1.pdf | |
| PWC | https://paperswithcode.com/paper/support-relation-analysis-for-objects-in |
| Repo | |
| Framework | |
Multi-label Classification with Optimal Thresholding for Multi-composition Spectroscopic Analysis
| Title | Multi-label Classification with Optimal Thresholding for Multi-composition Spectroscopic Analysis |
| Authors | Luyun Gan, Brosnan Yuen, Tao Lu |
| Abstract | In this paper, we implement multi-label neural networks with optimal thresholding to identify gas species among a multi gas mixture in a cluttered environment. Using infrared absorption spectroscopy and tested on synthesized spectral datasets, our approach outperforms conventional binary relevance - partial least squares discriminant analysis when signal-to-noise ratio and training sample size are sufficient. |
| Tasks | Multi-Label Classification |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.10242v1 |
| https://arxiv.org/pdf/1906.10242v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-label-classification-with-optimal |
| Repo | |
| Framework | |
Discounted Reinforcement Learning Is Not an Optimization Problem
| Title | Discounted Reinforcement Learning Is Not an Optimization Problem |
| Authors | Abhishek Naik, Roshan Shariff, Niko Yasui, Hengshuai Yao, Richard S. Sutton |
| Abstract | Discounted reinforcement learning is fundamentally incompatible with function approximation for control in continuing tasks. It is not an optimization problem in its usual formulation, so when using function approximation there is no optimal policy. We substantiate these claims, then go on to address some misconceptions about discounting and its connection to the average reward formulation. We encourage researchers to adopt rigorous optimization approaches, such as maximizing average reward, for reinforcement learning in continuing tasks. |
| Tasks | |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.02140v3 |
| https://arxiv.org/pdf/1910.02140v3.pdf | |
| PWC | https://paperswithcode.com/paper/discounted-reinforcement-learning-is-not-an |
| Repo | |
| Framework | |
Learning Neural Activations
| Title | Learning Neural Activations |
| Authors | Fayyaz ul Amir Afsar Minhas, Amina Asif |
| Abstract | An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been explored in the literature. In this short paper, we explore what happens when the activation function of each neuron in an artificial neural network is learned natively from data alone. This is achieved by modelling the activation function of each neuron as a small neural network whose weights are shared by all neurons in the original network. We list our primary findings in the conclusions section. The code for our analysis is available at: https://github.com/amina01/Learning-Neural-Activations. |
| Tasks | |
| Published | 2019-12-27 |
| URL | https://arxiv.org/abs/1912.12187v1 |
| https://arxiv.org/pdf/1912.12187v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-neural-activations |
| Repo | |
| Framework | |
A New Ensemble Method for Concessively Targeted Multi-model Attack
| Title | A New Ensemble Method for Concessively Targeted Multi-model Attack |
| Authors | Ziwen He, Wei Wang, Xinsheng Xuan, Jing Dong, Tieniu Tan |
| Abstract | It is well known that deep learning models are vulnerable to adversarial examples crafted by maliciously adding perturbations to original inputs. There are two types of attacks: targeted attack and non-targeted attack, and most researchers often pay more attention to the targeted adversarial examples. However, targeted attack has a low success rate, especially when aiming at a robust model or under a black-box attack protocol. In this case, non-targeted attack is the last chance to disable AI systems. Thus, in this paper, we propose a new attack mechanism which performs the non-targeted attack when the targeted attack fails. Besides, we aim to generate a single adversarial sample for different deployed models of the same task, e.g. image classification models. Hence, for this practical application, we focus on attacking ensemble models by dividing them into two groups: easy-to-attack and robust models. We alternately attack these two groups of models in the non-targeted or targeted manner. We name it a bagging and stacking ensemble (BAST) attack. The BAST attack can generate an adversarial sample that fails multiple models simultaneously. Some of the models classify the adversarial sample as a target label, and other models which are not attacked successfully may give wrong labels at least. The experimental results show that the proposed BAST attack outperforms the state-of-the-art attack methods on the new defined criterion that considers both targeted and non-targeted attack performance. |
| Tasks | Image Classification |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.10833v1 |
| https://arxiv.org/pdf/1912.10833v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-ensemble-method-for-concessively |
| Repo | |
| Framework | |
Mapping of Local and Global Synapses on Spiking Neuromorphic Hardware
| Title | Mapping of Local and Global Synapses on Spiking Neuromorphic Hardware |
| Authors | Anup Das, Yuefeng Wu, Khanh Huynh, Francesco Dell’Anna, Francky Catthoor, Siebren Schaafsma |
| Abstract | Spiking Neural Networks (SNNs) are widely deployed to solve complex pattern recognition, function approximation and image classification tasks. With the growing size and complexity of these networks, hardware implementation becomes challenging because scaling up the size of a single array (crossbar) of fully connected neurons is no longer feasible due to strict energy budget. Modern neromorphic hardware integrates small-sized crossbars with time-multiplexed interconnects. Partitioning SNNs becomes essential in order to map them on neuromorphic hardware with the major aim to reduce the global communication latency and energy overhead. To achieve this goal, we propose our instantiation of particle swarm optimization, which partitions SNNs into local synapses (mapped on crossbars) and global synapses (mapped on time-multiplexed interconnects), with the objective of reducing spike communication on the interconnect. This improves latency, power consumption as well as application performance by reducing inter-spike interval distortion and spike disorders. Our framework is implemented in Python, interfacing CARLsim, a GPU-accelerated application-level spiking neural network simulator with an extended version of Noxim, for simulating time-multiplexed interconnects. Experiments are conducted with realistic and synthetic SNN-based applications with different computation models, topologies and spike coding schemes. Using power numbers from in-house neuromorphic chips, we demonstrate significant reductions in energy consumption and spike latency over PACMAN, the widely-used partitioning technique for SNNs on SpiNNaker. |
| Tasks | Image Classification |
| Published | 2019-08-13 |
| URL | https://arxiv.org/abs/1908.08024v1 |
| https://arxiv.org/pdf/1908.08024v1.pdf | |
| PWC | https://paperswithcode.com/paper/mapping-of-local-and-global-synapses-on |
| Repo | |
| Framework | |
Neural Legal Judgment Prediction in English
| Title | Neural Legal Judgment Prediction in English |
| Authors | Ilias Chalkidis, Ion Androutsopoulos, Nikolaos Aletras |
| Abstract | Legal judgment prediction is the task of automatically predicting the outcome of a court case, given a text describing the case’s facts. Previous work on using neural models for this task has focused on Chinese; only feature-based models (e.g., using bags of words and topics) have been considered in English. We release a new English legal judgment prediction dataset, containing cases from the European Court of Human Rights. We evaluate a broad variety of neural models on the new dataset, establishing strong baselines that surpass previous feature-based models in three tasks: (1) binary violation classification; (2) multi-label classification; (3) case importance prediction. We also explore if models are biased towards demographic information via data anonymization. As a side-product, we propose a hierarchical version of BERT, which bypasses BERT’s length limitation. |
| Tasks | Multi-Label Classification |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02059v1 |
| https://arxiv.org/pdf/1906.02059v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-legal-judgment-prediction-in-english |
| Repo | |
| Framework | |
