Paper Group AWR 58
CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning. NTUA-SLP at SemEval-2018 Task 3: Tracking Ironic Tweets using Ensembles of Word and Character Level Attentive RNNs. Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat. Engaging Image Chat: Modeling Personality in Grounded Dialogue. Breast Canc …
CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning
| Title | CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning |
| Authors | Jiachen Yang, Alireza Nakhaei, David Isele, Kikuo Fujimura, Hongyuan Zha |
| Abstract | A variety of cooperative multi-agent control problems require agents to achieve individual goals while contributing to collective success. This multi-goal multi-agent setting poses difficulties for recent algorithms, which primarily target settings with a single global reward, due to two new challenges: efficient exploration for learning both individual goal attainment and cooperation for others’ success, and credit-assignment for interactions between actions and goals of different agents. To address both challenges, we restructure the problem into a novel two-stage curriculum, in which single-agent goal attainment is learned prior to learning multi-agent cooperation, and we derive a new multi-goal multi-agent policy gradient with a credit function for localized credit assignment. We use a function augmentation scheme to bridge value and policy functions across the curriculum. The complete architecture, called CM3, learns significantly faster than direct adaptations of existing algorithms on three challenging multi-goal multi-agent problems: cooperative navigation in difficult formations, negotiating multi-vehicle lane changes in the SUMO traffic simulator, and strategic cooperation in a Checkers environment. |
| Tasks | Autonomous Vehicles, Efficient Exploration, Multi-agent Reinforcement Learning |
| Published | 2018-09-13 |
| URL | https://arxiv.org/abs/1809.05188v3 |
| https://arxiv.org/pdf/1809.05188v3.pdf | |
| PWC | https://paperswithcode.com/paper/cm3-cooperative-multi-goal-multi-stage-multi |
| Repo | https://github.com/011235813/cm3 |
| Framework | tf |
NTUA-SLP at SemEval-2018 Task 3: Tracking Ironic Tweets using Ensembles of Word and Character Level Attentive RNNs
| Title | NTUA-SLP at SemEval-2018 Task 3: Tracking Ironic Tweets using Ensembles of Word and Character Level Attentive RNNs |
| Authors | Christos Baziotis, Nikos Athanasiou, Pinelopi Papalampidi, Athanasia Kolovou, Georgios Paraskevopoulos, Nikolaos Ellinas, Alexandros Potamianos |
| Abstract | In this paper we present two deep-learning systems that competed at SemEval-2018 Task 3 “Irony detection in English tweets”. We design and ensemble two independent models, based on recurrent neural networks (Bi-LSTM), which operate at the word and character level, in order to capture both the semantic and syntactic information in tweets. Our models are augmented with a self-attention mechanism, in order to identify the most informative words. The embedding layer of our word-level model is initialized with word2vec word embeddings, pretrained on a collection of 550 million English tweets. We did not utilize any handcrafted features, lexicons or external datasets as prior information and our models are trained end-to-end using back propagation on constrained data. Furthermore, we provide visualizations of tweets with annotations for the salient tokens of the attention layer that can help to interpret the inner workings of the proposed models. We ranked 2nd out of 42 teams in Subtask A and 2nd out of 31 teams in Subtask B. However, post-task-completion enhancements of our models achieve state-of-the-art results ranking 1st for both subtasks. |
| Tasks | Word Embeddings |
| Published | 2018-04-18 |
| URL | http://arxiv.org/abs/1804.06659v1 |
| http://arxiv.org/pdf/1804.06659v1.pdf | |
| PWC | https://paperswithcode.com/paper/ntua-slp-at-semeval-2018-task-3-tracking |
| Repo | https://github.com/cbaziotis/ntua-slp-semeval2018 |
| Framework | pytorch |
Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat
| Title | Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat |
| Authors | Ravi Shekhar, Aashish Venkatesh, Tim Baumgärtner, Elia Bruni, Barbara Plank, Raffaella Bernardi, Raquel Fernández |
| Abstract | We propose a grounded dialogue state encoder which addresses a foundational issue on how to integrate visual grounding with dialogue system components. As a test-bed, we focus on the GuessWhat?! game, a two-player game where the goal is to identify an object in a complex visual scene by asking a sequence of yes/no questions. Our visually-grounded encoder leverages synergies between guessing and asking questions, as it is trained jointly using multi-task learning. We further enrich our model via a cooperative learning regime. We show that the introduction of both the joint architecture and cooperative learning lead to accuracy improvements over the baseline system. We compare our approach to an alternative system which extends the baseline with reinforcement learning. Our in-depth analysis shows that the linguistic skills of the two models differ dramatically, despite approaching comparable performance levels. This points at the importance of analyzing the linguistic output of competing systems beyond numeric comparison solely based on task success. |
| Tasks | Multi-Task Learning |
| Published | 2018-09-10 |
| URL | http://arxiv.org/abs/1809.03408v2 |
| http://arxiv.org/pdf/1809.03408v2.pdf | |
| PWC | https://paperswithcode.com/paper/jointly-learning-to-see-ask-and-guesswhat |
| Repo | https://github.com/shekharRavi/Beyond-Task-Success-NAACL2019 |
| Framework | pytorch |
Engaging Image Chat: Modeling Personality in Grounded Dialogue
| Title | Engaging Image Chat: Modeling Personality in Grounded Dialogue |
| Authors | Kurt Shuster, Samuel Humeau, Antoine Bordes, Jason Weston |
| Abstract | To achieve the long-term goal of machines being able to engage humans in conversation, our models should be engaging. We focus on communication grounded in images, whereby a dialogue is conducted based on a given photo, a setup that is naturally engaging to humans (Hu et al., 2014). We collect a large dataset of grounded human-human conversations, where humans are asked to play the role of a given personality, as the use of personality in conversation has also been shown to be engaging (Shuster et al., 2018). Our dataset, Image-Chat, consists of 202k dialogues and 401k utterances over 202k images using 215 possible personality traits. We then design a set of natural architectures using state-of-the-art image and text representations, considering various ways to fuse the components. Automatic metrics and human evaluations show the efficacy of approach, in particular where our best performing model is preferred over human conversationalists 47.7% of the time |
| Tasks | |
| Published | 2018-11-02 |
| URL | http://arxiv.org/abs/1811.00945v1 |
| http://arxiv.org/pdf/1811.00945v1.pdf | |
| PWC | https://paperswithcode.com/paper/engaging-image-chat-modeling-personality-in |
| Repo | https://github.com/facebookresearch/ParlAI |
| Framework | pytorch |
Breast Cancer Classification from Histopathological Images with Inception Recurrent Residual Convolutional Neural Network
| Title | Breast Cancer Classification from Histopathological Images with Inception Recurrent Residual Convolutional Neural Network |
| Authors | Md Zahangir Alom, Chris Yakopcic, Tarek M. Taha, Vijayan K. Asari |
| Abstract | The Deep Convolutional Neural Network (DCNN) is one of the most powerful and successful deep learning approaches. DCNNs have already provided superior performance in different modalities of medical imaging including breast cancer classification, segmentation, and detection. Breast cancer is one of the most common and dangerous cancers impacting women worldwide. In this paper, we have proposed a method for breast cancer classification with the Inception Recurrent Residual Convolutional Neural Network (IRRCNN) model. The IRRCNN is a powerful DCNN model that combines the strength of the Inception Network (Inception-v4), the Residual Network (ResNet), and the Recurrent Convolutional Neural Network (RCNN). The IRRCNN shows superior performance against equivalent Inception Networks, Residual Networks, and RCNNs for object recognition tasks. In this paper, the IRRCNN approach is applied for breast cancer classification on two publicly available datasets including BreakHis and Breast Cancer Classification Challenge 2015. The experimental results are compared against the existing machine learning and deep learning-based approaches with respect to image-based, patch-based, image-level, and patient-level classification. The IRRCNN model provides superior classification performance in terms of sensitivity, Area Under the Curve (AUC), the ROC curve, and global accuracy compared to existing approaches for both datasets. |
| Tasks | Object Recognition |
| Published | 2018-11-10 |
| URL | http://arxiv.org/abs/1811.04241v1 |
| http://arxiv.org/pdf/1811.04241v1.pdf | |
| PWC | https://paperswithcode.com/paper/breast-cancer-classification-from |
| Repo | https://github.com/abhinavsagar/Breast-cancer-classification |
| Framework | none |
GINN: Geometric Illustration of Neural Networks
| Title | GINN: Geometric Illustration of Neural Networks |
| Authors | Luke N. Darlow, Amos J. Storkey |
| Abstract | This informal technical report details the geometric illustration of decision boundaries for ReLU units in a three layer fully connected neural network. The network is designed and trained to predict pixel intensity from an (x, y) input location. The Geometric Illustration of Neural Networks (GINN) tool was built to visualise and track the points at which ReLU units switch from being active to off (or vice versa) as the network undergoes training. Several phenomenon were observed and are discussed herein. This technical report is a supporting document to the blog post with online demos and is available at http://www.bayeswatch.com/2018/09/17/GINN/. |
| Tasks | |
| Published | 2018-10-02 |
| URL | http://arxiv.org/abs/1810.01860v1 |
| http://arxiv.org/pdf/1810.01860v1.pdf | |
| PWC | https://paperswithcode.com/paper/ginn-geometric-illustration-of-neural |
| Repo | https://github.com/learning-luke/ginn |
| Framework | pytorch |
Localized Multiple Kernel Learning for Anomaly Detection: One-class Classification
| Title | Localized Multiple Kernel Learning for Anomaly Detection: One-class Classification |
| Authors | Chandan Gautam, Ramesh Balaji, K Sudharsan, Aruna Tiwari, Kapil Ahuja |
| Abstract | Multi-kernel learning has been well explored in the recent past and has exhibited promising outcomes for multi-class classification and regression tasks. In this paper, we present a multiple kernel learning approach for the One-class Classification (OCC) task and employ it for anomaly detection. Recently, the basic multi-kernel approach has been proposed to solve the OCC problem, which is simply a convex combination of different kernels with equal weights. This paper proposes a Localized Multiple Kernel learning approach for Anomaly Detection (LMKAD) using OCC, where the weight for each kernel is assigned locally. Proposed LMKAD approach adapts the weight for each kernel using a gating function. The parameters of the gating function and one-class classifier are optimized simultaneously through a two-step optimization process. We present the empirical results of the performance of LMKAD on 25 benchmark datasets from various disciplines. This performance is evaluated against existing Multi Kernel Anomaly Detection (MKAD) algorithm, and four other existing kernel-based one-class classifiers to showcase the credibility of our approach. Our algorithm achieves significantly better Gmean scores while using a lesser number of support vectors compared to MKAD. Friedman test is also performed to verify the statistical significance of the results claimed in this paper. |
| Tasks | Anomaly Detection, One-class classifier |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.07892v4 |
| http://arxiv.org/pdf/1805.07892v4.pdf | |
| PWC | https://paperswithcode.com/paper/localized-multiple-kernel-learning-for |
| Repo | https://github.com/Chandan-IITI/LMKAD |
| Framework | none |
Iroko: A Framework to Prototype Reinforcement Learning for Data Center Traffic Control
| Title | Iroko: A Framework to Prototype Reinforcement Learning for Data Center Traffic Control |
| Authors | Fabian Ruffy, Michael Przystupa, Ivan Beschastnikh |
| Abstract | Recent networking research has identified that data-driven congestion control (CC) can be more efficient than traditional CC in TCP. Deep reinforcement learning (RL), in particular, has the potential to learn optimal network policies. However, RL suffers from instability and over-fitting, deficiencies which so far render it unacceptable for use in datacenter networks. In this paper, we analyze the requirements for RL to succeed in the datacenter context. We present a new emulator, Iroko, which we developed to support different network topologies, congestion control algorithms, and deployment scenarios. Iroko interfaces with the OpenAI gym toolkit, which allows for fast and fair evaluation of different RL and traditional CC algorithms under the same conditions. We present initial benchmarks on three deep RL algorithms compared to TCP New Vegas and DCTCP. Our results show that these algorithms are able to learn a CC policy which exceeds the performance of TCP New Vegas on a dumbbell and fat-tree topology. We make our emulator open-source and publicly available: https://github.com/dcgym/iroko |
| Tasks | |
| Published | 2018-12-24 |
| URL | http://arxiv.org/abs/1812.09975v1 |
| http://arxiv.org/pdf/1812.09975v1.pdf | |
| PWC | https://paperswithcode.com/paper/iroko-a-framework-to-prototype-reinforcement |
| Repo | https://github.com/dcgym/iroko |
| Framework | tf |
Toward Convolutional Blind Denoising of Real Photographs
| Title | Toward Convolutional Blind Denoising of Real Photographs |
| Authors | Shi Guo, Zifei Yan, Kai Zhang, Wangmeng Zuo, Lei Zhang |
| Abstract | While deep convolutional neural networks (CNNs) have achieved impressive success in image denoising with additive white Gaussian noise (AWGN), their performance remains limited on real-world noisy photographs. The main reason is that their learned models are easy to overfit on the simplified AWGN model which deviates severely from the complicated real-world noise model. In order to improve the generalization ability of deep CNN denoisers, we suggest training a convolutional blind denoising network (CBDNet) with more realistic noise model and real-world noisy-clean image pairs. On the one hand, both signal-dependent noise and in-camera signal processing pipeline is considered to synthesize realistic noisy images. On the other hand, real-world noisy photographs and their nearly noise-free counterparts are also included to train our CBDNet. To further provide an interactive strategy to rectify denoising result conveniently, a noise estimation subnetwork with asymmetric learning to suppress under-estimation of noise level is embedded into CBDNet. Extensive experimental results on three datasets of real-world noisy photographs clearly demonstrate the superior performance of CBDNet over state-of-the-arts in terms of quantitative metrics and visual quality. The code has been made available at https://github.com/GuoShi28/CBDNet. |
| Tasks | Denoising, Image Denoising |
| Published | 2018-07-12 |
| URL | http://arxiv.org/abs/1807.04686v2 |
| http://arxiv.org/pdf/1807.04686v2.pdf | |
| PWC | https://paperswithcode.com/paper/toward-convolutional-blind-denoising-of-real |
| Repo | https://github.com/IDKiro/CBDNet-tensorflow |
| Framework | tf |
Data-driven Discovery of Closure Models
| Title | Data-driven Discovery of Closure Models |
| Authors | Shaowu Pan, Karthik Duraisamy |
| Abstract | Derivation of reduced order representations of dynamical systems requires the modeling of the truncated dynamics on the retained dynamics. In its most general form, this so-called closure model has to account for memory effects. In this work, we present a framework of operator inference to extract the governing dynamics of closure from data in a compact, non-Markovian form. We employ sparse polynomial regression and artificial neural networks to extract the underlying operator. For a special class of non-linear systems, observability of the closure in terms of the resolved dynamics is analyzed and theoretical results are presented on the compactness of the memory. The proposed framework is evaluated on examples consisting of linear to nonlinear systems with and without chaotic dynamics, with an emphasis on predictive performance on unseen data. |
| Tasks | |
| Published | 2018-03-25 |
| URL | http://arxiv.org/abs/1803.09318v3 |
| http://arxiv.org/pdf/1803.09318v3.pdf | |
| PWC | https://paperswithcode.com/paper/data-driven-discovery-of-closure-models |
| Repo | https://github.com/pswpswpsw/siads_data_driven_closure |
| Framework | tf |
Representation Learning for Image-based Music Recommendation
| Title | Representation Learning for Image-based Music Recommendation |
| Authors | Chih-Chun Hsia, Kwei-Herng Lai, Yian Chen, Chuan-Ju Wang, Ming-Feng Tsai |
| Abstract | Image perception is one of the most direct ways to provide contextual information about a user concerning his/her surrounding environment; hence images are a suitable proxy for contextual recommendation. We propose a novel representation learning framework for image-based music recommendation that bridges the heterogeneity gap between music and image data; the proposed method is a key component for various contextual recommendation tasks. Preliminary experiments show that for an image-to-song retrieval task, the proposed method retrieves relevant or conceptually similar songs for input images. |
| Tasks | Representation Learning |
| Published | 2018-08-28 |
| URL | https://arxiv.org/abs/1808.09198v2 |
| https://arxiv.org/pdf/1808.09198v2.pdf | |
| PWC | https://paperswithcode.com/paper/representation-learning-for-image-based-music |
| Repo | https://github.com/sankalpdayal5/60daysofudacity |
| Framework | none |
Stress Field Prediction in Cantilevered Structures Using Convolutional Neural Networks
| Title | Stress Field Prediction in Cantilevered Structures Using Convolutional Neural Networks |
| Authors | Zhenguo Nie, Haoliang Jiang, Levent Burak Kara |
| Abstract | The demand for fast and accurate structural analysis is becoming increasingly more prevalent with the advance of generative design and topology optimization technologies. As one step toward accelerating structural analysis, this work explores a deep learning based approach for predicting the stress fields in 2D linear elastic cantilevered structures subjected to external static loads at its free end using convolutional neural networks (CNN). Two different architectures are implemented that take as input the structure geometry, external loads, and displacement boundary conditions, and output the predicted von Mises stress field. The first is a single input channel network called SCSNet as the baseline architecture, and the second is the multi-channel input network called StressNet. Accuracy analysis shows that StressNet results in significantly lower prediction errors than SCSNet on three loss functions, with a mean relative error of 2.04% for testing. These results suggest that deep learning models may offer a promising alternative to classical methods in structural design and topology optimization. Code and dataset are available at https://github.com/zhenguonie/stress_net |
| Tasks | |
| Published | 2018-08-27 |
| URL | https://arxiv.org/abs/1808.08914v3 |
| https://arxiv.org/pdf/1808.08914v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-stress-field-prediction |
| Repo | https://github.com/zhenguonie/stress_net |
| Framework | tf |
Unifying and Merging Well-trained Deep Neural Networks for Inference Stage
| Title | Unifying and Merging Well-trained Deep Neural Networks for Inference Stage |
| Authors | Yi-Min Chou, Yi-Ming Chan, Jia-Hong Lee, Chih-Yi Chiu, Chu-Song Chen |
| Abstract | We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks and merges them into a unified model by sharing the representative codes of weights. The shared weights are further re-trained to fine-tune the performance of the merged model. The proposed method effectively produces a compact model that may run original tasks simultaneously on resource-limited devices. As it preserves the general architectures and leverages the co-used weights of well-trained networks, a substantial training overhead can be reduced to shorten the system development time. Experimental results demonstrate a satisfactory performance and validate the effectiveness of the method. |
| Tasks | |
| Published | 2018-05-14 |
| URL | http://arxiv.org/abs/1805.04980v1 |
| http://arxiv.org/pdf/1805.04980v1.pdf | |
| PWC | https://paperswithcode.com/paper/unifying-and-merging-well-trained-deep-neural |
| Repo | https://github.com/ivclab/NeuralMerger |
| Framework | tf |
What you can cram into a single vector: Probing sentence embeddings for linguistic properties
| Title | What you can cram into a single vector: Probing sentence embeddings for linguistic properties |
| Authors | Alexis Conneau, German Kruszewski, Guillaume Lample, Loïc Barrault, Marco Baroni |
| Abstract | Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing. “Downstream” tasks, often based on sentence classification, are commonly used to evaluate the quality of sentence representations. The complexity of the tasks makes it however difficult to infer what kind of information is present in the representations. We introduce here 10 probing tasks designed to capture simple linguistic features of sentences, and we use them to study embeddings generated by three different encoders trained in eight distinct ways, uncovering intriguing properties of both encoders and training methods. |
| Tasks | Sentence Classification, Sentence Embeddings |
| Published | 2018-05-03 |
| URL | http://arxiv.org/abs/1805.01070v2 |
| http://arxiv.org/pdf/1805.01070v2.pdf | |
| PWC | https://paperswithcode.com/paper/what-you-can-cram-into-a-single-vector |
| Repo | https://github.com/facebookresearch/InferSent |
| Framework | pytorch |
A DIRT-T Approach to Unsupervised Domain Adaptation
| Title | A DIRT-T Approach to Unsupervised Domain Adaptation |
| Authors | Rui Shu, Hung H. Bui, Hirokazu Narui, Stefano Ermon |
| Abstract | Domain adaptation refers to the problem of leveraging labeled data in a source domain to learn an accurate model in a target domain where labels are scarce or unavailable. A recent approach for finding a common representation of the two domains is via domain adversarial training (Ganin & Lempitsky, 2015), which attempts to induce a feature extractor that matches the source and target feature distributions in some feature space. However, domain adversarial training faces two critical limitations: 1) if the feature extraction function has high-capacity, then feature distribution matching is a weak constraint, 2) in non-conservative domain adaptation (where no single classifier can perform well in both the source and target domains), training the model to do well on the source domain hurts performance on the target domain. In this paper, we address these issues through the lens of the cluster assumption, i.e., decision boundaries should not cross high-density data regions. We propose two novel and related models: 1) the Virtual Adversarial Domain Adaptation (VADA) model, which combines domain adversarial training with a penalty term that punishes the violation the cluster assumption; 2) the Decision-boundary Iterative Refinement Training with a Teacher (DIRT-T) model, which takes the VADA model as initialization and employs natural gradient steps to further minimize the cluster assumption violation. Extensive empirical results demonstrate that the combination of these two models significantly improve the state-of-the-art performance on the digit, traffic sign, and Wi-Fi recognition domain adaptation benchmarks. |
| Tasks | Domain Adaptation, Unsupervised Domain Adaptation |
| Published | 2018-02-23 |
| URL | http://arxiv.org/abs/1802.08735v2 |
| http://arxiv.org/pdf/1802.08735v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-dirt-t-approach-to-unsupervised-domain |
| Repo | https://github.com/RuiShu/dirt-t |
| Framework | tf |
