Paper Group ANR 572
Towards Generating Explanations for ASP-Based Link Analysis using Declarative Program Transformations. A Study and Analysis of a Feature Subset Selection Technique using Penguin Search Optimization Algorithm (FS-PeSOA). Dependency and Span, Cross-Style Semantic Role Labeling on PropBank and NomBank. Asymptotic Bayes risk for Gaussian mixture in a s …
Towards Generating Explanations for ASP-Based Link Analysis using Declarative Program Transformations
| Title | Towards Generating Explanations for ASP-Based Link Analysis using Declarative Program Transformations |
| Authors | Martin Atzmueller, Cicek Güven, Dietmar Seipel |
| Abstract | The explication and the generation of explanations are prominent topics in artificial intelligence and data science, in order to make methods and systems more transparent and understandable for humans. This paper investigates the problem of link analysis, specifically link prediction and anomalous link discovery in social networks using the declarative method of Answer set programming (ASP). Applying ASP for link prediction provides a powerful declarative approach, e.g., for incorporating domain knowledge for explicative prediction. In this context, we propose a novel method for generating explanations - as offline justifications - using declarative program transformations. The method itself is purely based on syntactic transformations of declarative programs, e.g., in an ASP formalism, using rule instrumentation. We demonstrate the efficacy of the proposed approach, exemplifying it in an application on link analysis in social networks, also including domain knowledge. |
| Tasks | Link Prediction |
| Published | 2019-09-08 |
| URL | https://arxiv.org/abs/1909.03404v1 |
| https://arxiv.org/pdf/1909.03404v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-generating-explanations-for-asp-based |
| Repo | |
| Framework | |
A Study and Analysis of a Feature Subset Selection Technique using Penguin Search Optimization Algorithm (FS-PeSOA)
| Title | A Study and Analysis of a Feature Subset Selection Technique using Penguin Search Optimization Algorithm (FS-PeSOA) |
| Authors | Agnip Dasgupta, Ardhendu Banerjee, Aniket Ghosh Dastidar, Antara Barman, Sanjay Chakraborty |
| Abstract | In today world of enormous amounts of data, it is very important to extract useful knowledge from it. This can be accomplished by feature subset selection. Feature subset selection is a method of selecting a minimum number of features with the help of which our machine can learn and predict which class a particular data belongs to. We will introduce a new adaptive algorithm called Feature selection Penguin Search optimization algorithm which is a metaheuristic approach. It is adapted from the natural hunting strategy of penguins in which a group of penguins take jumps at random depths and come back and share the status of food availability with other penguins and in this way, the global optimum solution is found. In order to explore the feature subset candidates, the bioinspired approach Penguin Search optimization algorithm generates during the process a trial feature subset and estimates its fitness value by using three different classifiers for each case: Random Forest, Nearest Neighbour and Support Vector Machines. However, we are planning to implement our proposed approach Feature selection Penguin Search optimization algorithm on some well known benchmark datasets collected from the UCI repository and also try to evaluate and compare its classification accuracy with some state of art algorithms. |
| Tasks | Feature Selection |
| Published | 2019-07-13 |
| URL | https://arxiv.org/abs/1907.05943v1 |
| https://arxiv.org/pdf/1907.05943v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-study-and-analysis-of-a-feature-subset |
| Repo | |
| Framework | |
Dependency and Span, Cross-Style Semantic Role Labeling on PropBank and NomBank
| Title | Dependency and Span, Cross-Style Semantic Role Labeling on PropBank and NomBank |
| Authors | Zuchao Li, Shexia He, Junru Zhou, Hai Zhao, Kevin Parnow, Rui Wang |
| Abstract | The latest developments in neural semantic role labeling (SRL), including both dependency and span representation formalisms, have shown great performance improvements. Although the two styles share many similarities in linguistic meaning and computation, most previous studies focus on a single style. In this paper, we define a new cross-style semantic role label convention and propose a new cross-style joint optimization model designed according to the linguistic meaning of semantic role, which provides an agreed way to make the results of two styles more comparable and let both types of SRL enjoy their natural connection on both linguistics and computation. Our model learns a general semantic argument structure and is capable of outputting optional style alone. Additionally, we propose a syntax aided method to enhance the learning of both dependency and span representations uniformly. Experiments show that the proposed methods are effective on both span (CoNLL-2005) and dependency (CoNLL-2009) SRL benchmarks. |
| Tasks | Semantic Role Labeling |
| Published | 2019-11-07 |
| URL | https://arxiv.org/abs/1911.02851v1 |
| https://arxiv.org/pdf/1911.02851v1.pdf | |
| PWC | https://paperswithcode.com/paper/dependency-and-span-cross-style-semantic-role |
| Repo | |
| Framework | |
Asymptotic Bayes risk for Gaussian mixture in a semi-supervised setting
| Title | Asymptotic Bayes risk for Gaussian mixture in a semi-supervised setting |
| Authors | Marc Lelarge, Leo Miolane |
| Abstract | Semi-supervised learning (SSL) uses unlabeled data for training and has been shown to greatly improve performance when compared to a supervised approach on the labeled data available. This claim depends both on the amount of labeled data available and on the algorithm used. In this paper, we compute analytically the gap between the best fully-supervised approach using only labeled data and the best semi-supervised approach using both labeled and unlabeled data. We quantify the best possible increase in performance obtained thanks to the unlabeled data, i.e. we compute the accuracy increase due to the information contained in the unlabeled data. Our work deals with a simple high-dimensional Gaussian mixture model for the data in a Bayesian setting. Our rigorous analysis builds on recent theoretical breakthroughs in high-dimensional inference and a large body of mathematical tools from statistical physics initially developed for spin glasses. |
| Tasks | |
| Published | 2019-07-08 |
| URL | https://arxiv.org/abs/1907.03792v2 |
| https://arxiv.org/pdf/1907.03792v2.pdf | |
| PWC | https://paperswithcode.com/paper/asymptotic-bayes-risk-for-gaussian-mixture-in |
| Repo | |
| Framework | |
PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration
| Title | PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration |
| Authors | Sangkug Lym, Esha Choukse, Siavash Zangeneh, Wei Wen, Sujay Sanghavi, Mattan Erez |
| Abstract | State-of-the-art convolutional neural networks (CNNs) used in vision applications have large models with numerous weights. Training these models is very compute- and memory-resource intensive. Much research has been done on pruning or compressing these models to reduce the cost of inference, but little work has addressed the costs of training. We focus precisely on accelerating training. We propose PruneTrain, a cost-efficient mechanism that gradually reduces the training cost during training. PruneTrain uses a structured group-lasso regularization approach that drives the training optimization toward both high accuracy and small weight values. Small weights can then be periodically removed by reconfiguring the network model to a smaller one. By using a structured-pruning approach and additional reconfiguration techniques we introduce, the pruned model can still be efficiently processed on a GPU accelerator. Overall, PruneTrain achieves a reduction of 39% in the end-to-end training time of ResNet50 for ImageNet by reducing computation cost by 40% in FLOPs, memory accesses by 37% for memory bandwidth bound layers, and the inter-accelerator communication by 55%. |
| Tasks | |
| Published | 2019-01-26 |
| URL | https://arxiv.org/abs/1901.09290v5 |
| https://arxiv.org/pdf/1901.09290v5.pdf | |
| PWC | https://paperswithcode.com/paper/prunetrain-gradual-structured-pruning-from |
| Repo | |
| Framework | |
Fast DenseNet: Towards Efficient and Accurate Text Recognition with Fast Dense Networks
| Title | Fast DenseNet: Towards Efficient and Accurate Text Recognition with Fast Dense Networks |
| Authors | Zhao Zhang, Zemin Tang, Yang Wang, Zheng Zhang, Shuicheng Yan, Meng Wang |
| Abstract | Convolutional Recurrent Neural Network (CRNN) is a popular network for recognizing texts in images. Advances like the variants of CRNN, such as Dense Convolutional Network with Connectionist Temporal Classification, has reduced the running time of the networks, but exposing the inner computation cost of the convolutional networks as a bottleneck. Specifically, DenseNet based frameworks use the dense blocks as the core module, but the inner features are combined in the form of concatenation in dense blocks. As a result, the number of channels of combined features delivered as the input of the layers close to the output and the relevant computational cost grows rapidly with the dense blocks getting deeper. This will severely bring heavy computational cost and restrict the depth of dense blocks. In this paper, we propose an efficient convolutional block called Fast Dense Block (FDB). To reduce the computing cost, we redefine and design the way of combining internal features of dense blocks. FDB is a convolutional block similarly as the dense block, but it applies both sum and concatenating operations to connect the inner features in blocks, which can reduce the computation cost to (1/L, 2/L), compared with the original dense block, where L is the number of layers in the dense block. Importantly, since the parameters of standard dense block and our new FDB keep consistent except the way of combining features, and their inputs and outputs have the same size and same number of channels, so FDB can be easily used to replace the original dense block in any DenseNet based framework. Based on the designed FDBs, we further propose a fast network of DenseNet to improve the text recognition performance in images. |
| Tasks | |
| Published | 2019-12-15 |
| URL | https://arxiv.org/abs/1912.07016v1 |
| https://arxiv.org/pdf/1912.07016v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-densenet-towards-efficient-and-accurate |
| Repo | |
| Framework | |
Locality and compositionality in zero-shot learning
| Title | Locality and compositionality in zero-shot learning |
| Authors | Tristan Sylvain, Linda Petrini, Devon Hjelm |
| Abstract | In this work we study locality and compositionality in the context of learning representations for Zero Shot Learning (ZSL). In order to well-isolate the importance of these properties in learned representations, we impose the additional constraint that, differently from most recent work in ZSL, no pre-training on different datasets (e.g. ImageNet) is performed. The results of our experiments show how locality, in terms of small parts of the input, and compositionality, i.e. how well can the learned representations be expressed as a function of a smaller vocabulary, are both deeply related to generalization and motivate the focus on more local-aware models in future research directions for representation learning. |
| Tasks | Representation Learning, Zero-Shot Learning |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.12179v1 |
| https://arxiv.org/pdf/1912.12179v1.pdf | |
| PWC | https://paperswithcode.com/paper/locality-and-compositionality-in-zero-shot-1 |
| Repo | |
| Framework | |
DCIL: Deep Contextual Internal Learning for Image Restoration and Image Retargeting
| Title | DCIL: Deep Contextual Internal Learning for Image Restoration and Image Retargeting |
| Authors | Indra Deep Mastan, Shanmuganathan Raman |
| Abstract | Recently, there is a vast interest in developing methods which are independent of the training samples such as deep image prior, zero-shot learning, and internal learning. The methods above are based on the common goal of maximizing image features learning from a single image despite inherent technical diversity. In this work, we bridge the gap between the various unsupervised approaches above and propose a general framework for image restoration and image retargeting. We use contextual feature learning and internal learning to improvise the structure similarity between the source and the target images. We perform image resize application in the following setups: classical image resize using super-resolution, a challenging image resize where the low-resolution image contains noise, and content-aware image resize using image retargeting. We also provide comparisons to the relevant state-of-the-art methods. |
| Tasks | Image Restoration, Super-Resolution, Zero-Shot Learning |
| Published | 2019-12-09 |
| URL | https://arxiv.org/abs/1912.04229v1 |
| https://arxiv.org/pdf/1912.04229v1.pdf | |
| PWC | https://paperswithcode.com/paper/dcil-deep-contextual-internal-learning-for |
| Repo | |
| Framework | |
Founding The Domain of AI Forensics
| Title | Founding The Domain of AI Forensics |
| Authors | Ibrahim Baggili, Vahid Behzadan |
| Abstract | With the widespread integration of AI in everyday and critical technologies, it seems inevitable to witness increasing instances of failure in AI systems. In such cases, there arises a need for technical investigations that produce legally acceptable and scientifically indisputable findings and conclusions on the causes of such failures. Inspired by the domain of cyber forensics, this paper introduces the need for the establishment of AI Forensics as a new discipline under AI safety. Furthermore, we propose a taxonomy of the subfields under this discipline, and present a discussion on the foundational challenges that lay ahead of this new research area. |
| Tasks | |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.06497v1 |
| https://arxiv.org/pdf/1912.06497v1.pdf | |
| PWC | https://paperswithcode.com/paper/founding-the-domain-of-ai-forensics |
| Repo | |
| Framework | |
Compositionally-Warped Gaussian Processes
| Title | Compositionally-Warped Gaussian Processes |
| Authors | Gonzalo Rios, Felipe Tobar |
| Abstract | The Gaussian process (GP) is a nonparametric prior distribution over functions indexed by time, space, or other high-dimensional index set. The GP is a flexible model yet its limitation is given by its very nature: it can only model Gaussian marginal distributions. To model non-Gaussian data, a GP can be warped by a nonlinear transformation (or warping) as performed by warped GPs (WGPs) and more computationally-demanding alternatives such as Bayesian WGPs and deep GPs. However, the WGP requires a numerical approximation of the inverse warping for prediction, which increases the computational complexity in practice. To sidestep this issue, we construct a novel class of warpings consisting of compositions of multiple elementary functions, for which the inverse is known explicitly. We then propose the compositionally-warped GP (CWGP), a non-Gaussian generative model whose expressiveness follows from its deep compositional architecture, and its computational efficiency is guaranteed by the analytical inverse warping. Experimental validation using synthetic and real-world datasets confirms that the proposed CWGP is robust to the choice of warpings and provides more accurate point predictions, better trained models and shorter computation times than WGP. |
| Tasks | Gaussian Processes |
| Published | 2019-06-23 |
| URL | https://arxiv.org/abs/1906.09665v2 |
| https://arxiv.org/pdf/1906.09665v2.pdf | |
| PWC | https://paperswithcode.com/paper/compositionally-warped-gaussian-processes |
| Repo | |
| Framework | |
A View on Deep Reinforcement Learning in System Optimization
| Title | A View on Deep Reinforcement Learning in System Optimization |
| Authors | Ameer Haj-Ali, Nesreen K. Ahmed, Ted Willke, Joseph Gonzalez, Krste Asanovic, Ion Stoica |
| Abstract | Many real-world systems problems require reasoning about the long term consequences of actions taken to configure and manage the system. These problems with delayed and often sequentially aggregated reward, are often inherently reinforcement learning problems and present the opportunity to leverage the recent substantial advances in deep reinforcement learning. However, in some cases, it is not clear why deep reinforcement learning is a good fit for the problem. Sometimes, it does not perform better than the state-of-the-art solutions. And in other cases, random search or greedy algorithms could outperform deep reinforcement learning. In this paper, we review, discuss, and evaluate the recent trends of using deep reinforcement learning in system optimization. We propose a set of essential metrics to guide future works in evaluating the efficacy of using deep reinforcement learning in system optimization. Our evaluation includes challenges, the types of problems, their formulation in the deep reinforcement learning setting, embedding, the model used, efficiency, and robustness. We conclude with a discussion on open challenges and potential directions for pushing further the integration of reinforcement learning in system optimization. |
| Tasks | |
| Published | 2019-08-04 |
| URL | https://arxiv.org/abs/1908.01275v3 |
| https://arxiv.org/pdf/1908.01275v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-in-system |
| Repo | |
| Framework | |
On Value Functions and the Agent-Environment Boundary
| Title | On Value Functions and the Agent-Environment Boundary |
| Authors | Nan Jiang |
| Abstract | When function approximation is deployed in reinforcement learning (RL), the same problem may be formulated in different ways, often by treating a pre-processing step as a part of the environment or as part of the agent. As a consequence, fundamental concepts in RL, such as (optimal) value functions, are not uniquely defined as they depend on where we draw this agent-environment boundary, causing problems in theoretical analyses that provide optimality guarantees. We address this issue via a simple and novel boundary-invariant analysis of Fitted Q-Iteration, a representative RL algorithm, where the assumptions and the guarantees are invariant to the choice of boundary. We also discuss closely related issues on state resetting and Monte-Carlo Tree Search, deterministic vs stochastic systems, imitation learning, and the verifiability of theoretical assumptions from data. |
| Tasks | Imitation Learning |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.13341v2 |
| https://arxiv.org/pdf/1905.13341v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-value-functions-and-the-agent-environment |
| Repo | |
| Framework | |
Parenting: Safe Reinforcement Learning from Human Input
| Title | Parenting: Safe Reinforcement Learning from Human Input |
| Authors | Christopher Frye, Ilya Feige |
| Abstract | Autonomous agents trained via reinforcement learning present numerous safety concerns: reward hacking, negative side effects, and unsafe exploration, among others. In the context of near-future autonomous agents, operating in environments where humans understand the existing dangers, human involvement in the learning process has proved a promising approach to AI Safety. Here we demonstrate that a precise framework for learning from human input, loosely inspired by the way humans parent children, solves a broad class of safety problems in this context. We show that our Parenting algorithm solves these problems in the relevant AI Safety gridworlds of Leike et al. (2017), that an agent can learn to outperform its parent as it “matures”, and that policies learnt through Parenting are generalisable to new environments. |
| Tasks | |
| Published | 2019-02-18 |
| URL | http://arxiv.org/abs/1902.06766v1 |
| http://arxiv.org/pdf/1902.06766v1.pdf | |
| PWC | https://paperswithcode.com/paper/parenting-safe-reinforcement-learning-from |
| Repo | |
| Framework | |
Centralized and Distributed Machine Learning-Based QoT Estimation for Sliceable Optical Networks
| Title | Centralized and Distributed Machine Learning-Based QoT Estimation for Sliceable Optical Networks |
| Authors | Tania Panayiotou, Giannis Savva, Ioannis Tomkos, Georgios Ellinas |
| Abstract | Dynamic network slicing has emerged as a promising and fundamental framework for meeting 5G’s diverse use cases. As machine learning (ML) is expected to play a pivotal role in the efficient control and management of these networks, in this work we examine the ML-based Quality-of-Transmission (QoT) estimation problem under the dynamic network slicing context, where each slice has to meet a different QoT requirement. We examine ML-based QoT frameworks with the aim of finding QoT model/s that are fine-tuned according to the diverse QoT requirements. Centralized and distributed frameworks are examined and compared according to their accuracy and training time. We show that the distributed QoT models outperform the centralized QoT model, especially as the number of diverse QoT requirements increases. |
| Tasks | |
| Published | 2019-08-22 |
| URL | https://arxiv.org/abs/1908.08338v2 |
| https://arxiv.org/pdf/1908.08338v2.pdf | |
| PWC | https://paperswithcode.com/paper/centralized-and-distributed-machine-learning |
| Repo | |
| Framework | |
Road Segmentation with Image-LiDAR Data Fusion
| Title | Road Segmentation with Image-LiDAR Data Fusion |
| Authors | Huafeng Liu, Yazhou Yao, Zeren Sun, Xiangrui Li, Ke Jia, Zhenmin Tang |
| Abstract | Robust road segmentation is a key challenge in self-driving research. Though many image-based methods have been studied and high performances in dataset evaluations have been reported, developing robust and reliable road segmentation is still a major challenge. Data fusion across different sensors to improve the performance of road segmentation is widely considered an important and irreplaceable solution. In this paper, we propose a novel structure to fuse image and LiDAR point cloud in an end-to-end semantic segmentation network, in which the fusion is performed at decoder stage instead of at, more commonly, encoder stage. During fusion, we improve the multi-scale LiDAR map generation to increase the precision of the multi-scale LiDAR map by introducing pyramid projection method. Additionally, we adapted the multi-path refinement network with our fusion strategy and improve the road prediction compared with transpose convolution with skip layers. Our approach has been tested on KITTI ROAD dataset and has competitive performance. |
| Tasks | Semantic Segmentation |
| Published | 2019-05-26 |
| URL | https://arxiv.org/abs/1905.11559v1 |
| https://arxiv.org/pdf/1905.11559v1.pdf | |
| PWC | https://paperswithcode.com/paper/190511559 |
| Repo | |
| Framework | |
