Paper Group ANR 1522
Hybrid MemNet for Extractive Summarization. Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems. Towards Deployment of Robust AI Agents for Human-Machine Partnerships. Learning from Label Proportions with Generative Adversarial Networks. Human-centric Transfer Learning Explanation via Knowledge Graph [Extended Ab …
Hybrid MemNet for Extractive Summarization
| Title | Hybrid MemNet for Extractive Summarization |
| Authors | Abhishek Kumar Singh, Manish Gupta, Vasudeva Varma |
| Abstract | Extractive text summarization has been an extensive research problem in the field of natural language understanding. While the conventional approaches rely mostly on manually compiled features to generate the summary, few attempts have been made in developing data-driven systems for extractive summarization. To this end, we present a fully data-driven end-to-end deep network which we call as Hybrid MemNet for single document summarization task. The network learns the continuous unified representation of a document before generating its summary. It jointly captures local and global sentential information along with the notion of summary worthy sentences. Experimental results on two different corpora confirm that our model shows significant performance gains compared with the state-of-the-art baselines. |
| Tasks | Document Summarization, Text Summarization |
| Published | 2019-12-25 |
| URL | https://arxiv.org/abs/1912.11701v1 |
| https://arxiv.org/pdf/1912.11701v1.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-memnet-for-extractive-summarization |
| Repo | |
| Framework | |
Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems
| Title | Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems |
| Authors | Guannan Qu, Adam Wierman, Na Li |
| Abstract | We study reinforcement learning (RL) in a setting with a network of agents whose states and actions interact in a local manner where the objective is to find localized policies such that the (discounted) global reward is maximized. A fundamental challenge in this setting is that the state-action space size scales exponentially in the number of agents, rendering the problem intractable for large networks. In this paper, we propose a Scalable Actor-Critic (SAC) framework that exploits the network structure and finds a localized policy that is a $O(\rho^\kappa)$-approximation of a stationary point of the objective for some $\rho\in(0,1)$, with complexity that scales with the local state-action space size of the largest $\kappa$-hop neighborhood of the network. |
| Tasks | |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02906v2 |
| https://arxiv.org/pdf/1912.02906v2.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-reinforcement-learning-of-localized |
| Repo | |
| Framework | |
Towards Deployment of Robust AI Agents for Human-Machine Partnerships
| Title | Towards Deployment of Robust AI Agents for Human-Machine Partnerships |
| Authors | Ahana Ghosh, Sebastian Tschiatschek, Hamed Mahdavi, Adish Singla |
| Abstract | We study the problem of designing AI agents that can robustly cooperate with people in human-machine partnerships. Our work is inspired by real-life scenarios in which an AI agent, e.g., a virtual assistant, has to cooperate with new users after its deployment. We model this problem via a parametric MDP framework where the parameters correspond to a user’s type and characterize her behavior. In the test phase, the AI agent has to interact with a user of unknown type. Our approach to designing a robust AI agent relies on observing the user’s actions to make inferences about the user’s type and adapting its policy to facilitate efficient cooperation. We show that without being adaptive, an AI agent can end up performing arbitrarily bad in the test phase. We develop two algorithms for computing policies that automatically adapt to the user in the test phase. We demonstrate the effectiveness of our approach in solving a two-agent collaborative task. |
| Tasks | |
| Published | 2019-10-05 |
| URL | https://arxiv.org/abs/1910.02330v1 |
| https://arxiv.org/pdf/1910.02330v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-deployment-of-robust-ai-agents-for |
| Repo | |
| Framework | |
Learning from Label Proportions with Generative Adversarial Networks
| Title | Learning from Label Proportions with Generative Adversarial Networks |
| Authors | Jiabin Liu, Bo Wang, Zhiquan Qi, Yingjie Tian, Yong Shi |
| Abstract | In this paper, we leverage generative adversarial networks (GANs) to derive an effective algorithm LLP-GAN for learning from label proportions (LLP), where only the bag-level proportional information in labels is available. Endowed with end-to-end structure, LLP-GAN performs approximation in the light of an adversarial learning mechanism, without imposing restricted assumptions on distribution. Accordingly, we can directly induce the final instance-level classifier upon the discriminator. Under mild assumptions, we give the explicit generative representation and prove the global optimality for LLP-GAN. Additionally, compared with existing methods, our work empowers LLP solver with capable scalability inheriting from deep models. Several experiments on benchmark datasets demonstrate vivid advantages of the proposed approach. |
| Tasks | |
| Published | 2019-09-05 |
| URL | https://arxiv.org/abs/1909.02180v4 |
| https://arxiv.org/pdf/1909.02180v4.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-label-proportions-with |
| Repo | |
| Framework | |
Human-centric Transfer Learning Explanation via Knowledge Graph [Extended Abstract]
| Title | Human-centric Transfer Learning Explanation via Knowledge Graph [Extended Abstract] |
| Authors | Yuxia Geng, Jiaoyan Chen, Ernesto Jimenez-Ruiz, Huajun Chen |
| Abstract | Transfer learning which aims at utilizing knowledge learned from one problem (source domain) to solve another different but related problem (target domain) has attracted wide research attentions. However, the current transfer learning methods are mostly uninterpretable, especially to people without ML expertise. In this extended abstract, we brief introduce two knowledge graph (KG) based frameworks towards human understandable transfer learning explanation. The first one explains the transferability of features learned by Convolutional Neural Network (CNN) from one domain to another through pre-training and fine-tuning, while the second justifies the model of a target domain predicted by models from multiple source domains in zero-shot learning (ZSL). Both methods utilize KG and its reasoning capability to provide rich and human understandable explanations to the transfer procedure. |
| Tasks | Transfer Learning, Zero-Shot Learning |
| Published | 2019-01-20 |
| URL | http://arxiv.org/abs/1901.08547v1 |
| http://arxiv.org/pdf/1901.08547v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-centric-transfer-learning-explanation |
| Repo | |
| Framework | |
Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection
| Title | Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection |
| Authors | Bingzhe Wu, Shiwan Zhao, ChaoChao Chen, Haoyang Xu, Li Wang, Xiaolu Zhang, Guangyu Sun, Jun Zhou |
| Abstract | In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a differentially private learning algorithm used for training the GAN does not overfit to a certain degree, i.e., the generalization gap can be bounded. Moreover, some recent works, such as the Bayesian GAN, can be re-interpreted based on our theoretical insight from privacy protection. Quantitatively, to evaluate the information leakage of well-trained GAN models, we perform various membership attacks on these models. The results show that previous Lipschitz regularization techniques are effective in not only reducing the generalization gap but also alleviating the information leakage of the training dataset. |
| Tasks | |
| Published | 2019-08-21 |
| URL | https://arxiv.org/abs/1908.07882v3 |
| https://arxiv.org/pdf/1908.07882v3.pdf | |
| PWC | https://paperswithcode.com/paper/190807882 |
| Repo | |
| Framework | |
Dynamic Input for Deep Reinforcement Learning in Autonomous Driving
| Title | Dynamic Input for Deep Reinforcement Learning in Autonomous Driving |
| Authors | Maria Huegle, Gabriel Kalweit, Branka Mirchevska, Moritz Werling, Joschka Boedecker |
| Abstract | In many real-world decision making problems, reaching an optimal decision requires taking into account a variable number of objects around the agent. Autonomous driving is a domain in which this is especially relevant, since the number of cars surrounding the agent varies considerably over time and affects the optimal action to be taken. Classical methods that process object lists can deal with this requirement. However, to take advantage of recent high-performing methods based on deep reinforcement learning in modular pipelines, special architectures are necessary. For these, a number of options exist, but a thorough comparison of the different possibilities is missing. In this paper, we elaborate limitations of fully-connected neural networks and other established approaches like convolutional and recurrent neural networks in the context of reinforcement learning problems that have to deal with variable sized inputs. We employ the structure of Deep Sets in off-policy reinforcement learning for high-level decision making, highlight their capabilities to alleviate these limitations, and show that Deep Sets not only yield the best overall performance but also offer better generalization to unseen situations than the other approaches. |
| Tasks | Autonomous Driving, Decision Making |
| Published | 2019-07-25 |
| URL | https://arxiv.org/abs/1907.10994v1 |
| https://arxiv.org/pdf/1907.10994v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-input-for-deep-reinforcement-learning |
| Repo | |
| Framework | |
Ruminating Word Representations with Random Noised Masker
| Title | Ruminating Word Representations with Random Noised Masker |
| Authors | Hwiyeol Jo, Byoung-Tak Zhang |
| Abstract | We introduce a training method for both better word representation and performance, which we call GROVER (Gradual Rumination On the Vector with maskERs). The method is to gradually and iteratively add random noises to word embeddings while training a model. GROVER first starts from conventional training process, and then extracts the fine-tuned representations. Next, we gradually add random noises to the word representations and repeat the training process from scratch, but initialize with the noised word representations. Through the re-training process, we can mitigate some noises to be compensated and utilize other noises to learn better representations. As a result, we can get word representations further fine-tuned and specialized on the task. When we experiment with our method on 5 text classification datasets, our method improves model performances on most of the datasets. Moreover, we show that our method can be combined with other regularization techniques, further improving the model performance. |
| Tasks | Text Classification, Word Embeddings |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03459v1 |
| https://arxiv.org/pdf/1911.03459v1.pdf | |
| PWC | https://paperswithcode.com/paper/ruminating-word-representations-with-random |
| Repo | |
| Framework | |
CS-R-FCN: Cross-supervised Learning for Large-Scale Object Detection
| Title | CS-R-FCN: Cross-supervised Learning for Large-Scale Object Detection |
| Authors | Ye Guo, Yali Li, Shengjin Wang |
| Abstract | Generic object detection is one of the most fundamental problems in computer vision, yet it is difficult to provide all the bounding-box-level annotations aiming at large-scale object detection for thousands of categories. In this paper, we present a novel cross-supervised learning pipeline for large-scale object detection, denoted as CS-R-FCN. First, we propose to utilize the data flow of image-level annotated images in the fully-supervised two-stage object detection framework, leading to cross-supervised learning combining bounding-box-level annotated data and image-level annotated data. Second, we introduce a semantic aggregation strategy utilizing the relationships among the cross-supervised categories to reduce the unreasonable mutual inhibition effects during the feature learning. Experimental results show that the proposed CS-R-FCN improves the mAP by a large margin compared to previous related works. |
| Tasks | Object Detection |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.12863v2 |
| https://arxiv.org/pdf/1905.12863v2.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-structure-and-joint-training-for |
| Repo | |
| Framework | |
Physical-Layer Supervised Learning Assisted by an Entangled Sensor Network
| Title | Physical-Layer Supervised Learning Assisted by an Entangled Sensor Network |
| Authors | Quntao Zhuang, Zheshen Zhang |
| Abstract | Many existing quantum supervised learning (SL) schemes consider data given a priori in a classical description. With only noisy intermediate-scale quantum (NISQ) devices available in the near future, their quantum speedup awaits the development of quantum random access memories (qRAMs) and fault-tolerant quantum computing. There, however, also exist a multitude of SL tasks whose data are acquired by sensors, e.g., pattern classification based on data produced by imaging sensors. Solving such SL tasks naturally requires an integrated approach harnessing tools from both quantum sensing and quantum computing. We introduce supervised learning assisted by an entangled sensor network (SLAEN) as a means to carry out SL tasks at the physical layer. The entanglement shared by the sensors in SLAEN boosts the performance of extracting global features of the object under investigation. We leverage SLAEN to construct an entanglement-assisted support-vector machine for data classification and entanglement-assisted principal component analyzer for data compression. In both schemes, variational circuits are employed to seek the optimum entangled probe states and measurement settings to maximize the entanglement-enabled {enhancement}. We observe that SLAEN enjoys an appreciable entanglement-enabled performance gain, even in the presence of loss, over conventional strategies in which classical data are acquired by separable sensors and subsequently processed by classical SL algorithms. SLAEN is realizable with available technology, opening a viable route toward building NISQ devices that offer unmatched performance beyond what the optimum classical device is able to afford. |
| Tasks | |
| Published | 2019-01-28 |
| URL | https://arxiv.org/abs/1901.09566v2 |
| https://arxiv.org/pdf/1901.09566v2.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-learning-enhanced-by-an-entangled |
| Repo | |
| Framework | |
A Novel Method for the Absolute Pose Problem with Pairwise Constraints
| Title | A Novel Method for the Absolute Pose Problem with Pairwise Constraints |
| Authors | Yinlong Liu, Xuechen Li, Manning Wang, Guang Chen, Zhijian Song, Alois Knoll |
| Abstract | Absolute pose estimation is a fundamental problem in computer vision, and it is a typical parameter estimation problem, meaning that efforts to solve it will always suffer from outlier-contaminated data. Conventionally, for a fixed dimensionality d and the number of measurements N, a robust estimation problem cannot be solved faster than O(N^d). Furthermore, it is almost impossible to remove d from the exponent of the runtime of a globally optimal algorithm. However, absolute pose estimation is a geometric parameter estimation problem, and thus has special constraints. In this paper, we consider pairwise constraints and propose a globally optimal algorithm for solving the absolute pose estimation problem. The proposed algorithm has a linear complexity in the number of correspondences at a given outlier ratio. Concretely, we first decouple the rotation and the translation subproblems by utilizing the pairwise constraints, and then we solve the rotation subproblem using the branch-and-bound algorithm. Lastly, we estimate the translation based on the known rotation by using another branch-and-bound algorithm. The advantages of our method are demonstrated via thorough testing on both synthetic and real-world data |
| Tasks | Pose Estimation |
| Published | 2019-03-25 |
| URL | http://arxiv.org/abs/1903.10175v2 |
| http://arxiv.org/pdf/1903.10175v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-method-for-the-absolute-pose-problem |
| Repo | |
| Framework | |
Content-Based Features to Rank Influential Hidden Services of the Tor Darknet
| Title | Content-Based Features to Rank Influential Hidden Services of the Tor Darknet |
| Authors | Mhd Wesam Al-Nabki, Eduardo Fidalgo, Enrique Alegre, Deisy Chaves |
| Abstract | The unevenness importance of criminal activities in the onion domains of the Tor Darknet and the different levels of their appeal to the end-user make them tangled to measure their influence. To this end, this paper presents a novel content-based ranking framework to detect the most influential onion domains. Our approach comprises a modeling unit that represents an onion domain using forty features extracted from five different resources: user-visible text, HTML markup, Named Entities, network topology, and visual content. And also, a ranking unit that, using the Learning-to-Rank (LtR) approach, automatically learns a ranking function by integrating the previously obtained features. Using a case-study based on drugs-related onion domains, we obtained the following results. (1) Among the explored LtR schemes, the listwise approach outperforms the benchmarked methods with an NDCG of 0.95 for the top-10 ranked domains. (2) We proved quantitatively that our framework surpasses the link-based ranking techniques. Also, (3) with the selected feature, we observed that the textual content, composed by text, NER, and HTML features, is the most balanced approach, in terms of efficiency and score obtained. The proposed framework might support Law Enforcement Agencies in detecting the most influential domains related to possible suspicious activities. |
| Tasks | Learning-To-Rank |
| Published | 2019-10-05 |
| URL | https://arxiv.org/abs/1910.02332v1 |
| https://arxiv.org/pdf/1910.02332v1.pdf | |
| PWC | https://paperswithcode.com/paper/content-based-features-to-rank-influential |
| Repo | |
| Framework | |
J Regularization Improves Imbalanced Multiclass Segmentation
| Title | J Regularization Improves Imbalanced Multiclass Segmentation |
| Authors | Fidel A. Guerrero Peña, Pedro D. Marrero Fernandez, Paul T. Tarr, Tsang Ing Ren, Elliot M. Meyerowitz, Alexandre Cunha |
| Abstract | We propose a new loss formulation to further advance the multiclass segmentation of cluttered cells under weakly supervised conditions. We improve the separation of touching and immediate cells, obtaining sharp segmentation boundaries with high adequacy, when we add Youden’s $J$ statistic regularization term to the cross entropy loss. This regularization intrinsically supports class imbalance thus eliminating the necessity of explicitly using weights to balance training. Simulations demonstrate this capability and show how the regularization leads to better results by helping advancing the optimization when cross entropy stalls. We build upon our previous work on multiclass segmentation by adding yet another training class representing gaps between adjacent cells. This addition helps the classifier identify narrow gaps as background and no longer as touching regions. We present results of our methods for 2D and 3D images, from bright field to confocal stacks containing different types of cells, and we show that they accurately segment individual cells after training with a limited number of annotated images, some of which are poorly annotated. |
| Tasks | |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.09783v1 |
| https://arxiv.org/pdf/1910.09783v1.pdf | |
| PWC | https://paperswithcode.com/paper/j-regularization-improves-imbalanced |
| Repo | |
| Framework | |
Self-supervised Attention Model for Weakly Labeled Audio Event Classification
| Title | Self-supervised Attention Model for Weakly Labeled Audio Event Classification |
| Authors | Bongjun Kim, Shabnam Ghaffarzadegan |
| Abstract | We describe a novel weakly labeled Audio Event Classification approach based on a self-supervised attention model. The weakly labeled framework is used to eliminate the need for expensive data labeling procedure and self-supervised attention is deployed to help a model distinguish between relevant and irrelevant parts of a weakly labeled audio clip in a more effective manner compared to prior attention models. We also propose a highly effective strongly supervised attention model when strong labels are available. This model also serves as an upper bound for the self-supervised model. The performances of the model with self-supervised attention training are comparable to the strongly supervised one which is trained using strong labels. We show that our self-supervised attention method is especially beneficial for short audio events. We achieve 8.8% and 17.6% relative mean average precision improvements over the current state-of-the-art systems for SL-DCASE-17 and balanced AudioSet. |
| Tasks | |
| Published | 2019-08-07 |
| URL | https://arxiv.org/abs/1908.02876v1 |
| https://arxiv.org/pdf/1908.02876v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-attention-model-for-weakly |
| Repo | |
| Framework | |
Generating Adversarial Examples With Conditional Generative Adversarial Net
| Title | Generating Adversarial Examples With Conditional Generative Adversarial Net |
| Authors | Ping Yu, Kaitao Song, Jianfeng Lu |
| Abstract | Recently, deep neural networks have significant progress and successful application in various fields, but they are found vulnerable to attack instances, e.g., adversarial examples. State-of-art attack methods can generate attack images by adding small perturbation to the source image. These attack images can fool the classifier but have little impact to human. Therefore, such attack instances are difficult to generate by searching the feature space. How to design an effective and robust generating method has become a spotlight. Inspired by adversarial examples, we propose two novel generative models to produce adaptive attack instances directly, in which conditional generative adversarial network is adopted and distinctive strategy is designed for training. Compared with the common method, such as Fast Gradient Sign Method, our models can reduce the generating cost and improve robustness and has about one fifth running time for producing attack instance. |
| Tasks | |
| Published | 2019-03-18 |
| URL | http://arxiv.org/abs/1903.07282v1 |
| http://arxiv.org/pdf/1903.07282v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-adversarial-examples-with-2 |
| Repo | |
| Framework | |
