Paper Group AWR 298
Text Segmentation as a Supervised Learning Task. Improving the Transformer Translation Model with Document-Level Context. Reviving and Improving Recurrent Back-Propagation. Detecting Social Influence in Event Cascades by Comparing Discriminative Rankers. Learning Type-Aware Embeddings for Fashion Compatibility. QMIX: Monotonic Value Function Factor …
Text Segmentation as a Supervised Learning Task
| Title | Text Segmentation as a Supervised Learning Task |
| Authors | Omri Koshorek, Adir Cohen, Noam Mor, Michael Rotman, Jonathan Berant |
| Abstract | Text segmentation, the task of dividing a document into contiguous segments based on its semantic structure, is a longstanding challenge in language understanding. Previous work on text segmentation focused on unsupervised methods such as clustering or graph search, due to the paucity in labeled data. In this work, we formulate text segmentation as a supervised learning problem, and present a large new dataset for text segmentation that is automatically extracted and labeled from Wikipedia. Moreover, we develop a segmentation model based on this dataset and show that it generalizes well to unseen natural text. |
| Tasks | |
| Published | 2018-03-25 |
| URL | http://arxiv.org/abs/1803.09337v1 |
| http://arxiv.org/pdf/1803.09337v1.pdf | |
| PWC | https://paperswithcode.com/paper/text-segmentation-as-a-supervised-learning |
| Repo | https://github.com/koomri/text-segmentation |
| Framework | pytorch |
Improving the Transformer Translation Model with Document-Level Context
| Title | Improving the Transformer Translation Model with Document-Level Context |
| Authors | Jiacheng Zhang, Huanbo Luan, Maosong Sun, FeiFei Zhai, Jingfang Xu, Min Zhang, Yang Liu |
| Abstract | Although the Transformer translation model (Vaswani et al., 2017) has achieved state-of-the-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer still remains a challenge. In this work, we extend the Transformer model with a new context encoder to represent document-level context, which is then incorporated into the original encoder and decoder. As large-scale document-level parallel corpora are usually not available, we introduce a two-step training method to take full advantage of abundant sentence-level parallel corpora and limited document-level parallel corpora. Experiments on the NIST Chinese-English datasets and the IWSLT French-English datasets show that our approach improves over Transformer significantly. |
| Tasks | |
| Published | 2018-10-08 |
| URL | http://arxiv.org/abs/1810.03581v1 |
| http://arxiv.org/pdf/1810.03581v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-the-transformer-translation-model |
| Repo | https://github.com/thumt/THUMT |
| Framework | tf |
Reviving and Improving Recurrent Back-Propagation
| Title | Reviving and Improving Recurrent Back-Propagation |
| Authors | Renjie Liao, Yuwen Xiong, Ethan Fetaya, Lisa Zhang, KiJung Yoon, Xaq Pitkow, Raquel Urtasun, Richard Zemel |
| Abstract | In this paper, we revisit the recurrent back-propagation (RBP) algorithm, discuss the conditions under which it applies as well as how to satisfy them in deep neural networks. We show that RBP can be unstable and propose two variants based on conjugate gradient on the normal equations (CG-RBP) and Neumann series (Neumann-RBP). We further investigate the relationship between Neumann-RBP and back propagation through time (BPTT) and its truncated version (TBPTT). Our Neumann-RBP has the same time complexity as TBPTT but only requires constant memory, whereas TBPTT’s memory cost scales linearly with the number of truncation steps. We examine all RBP variants along with BPTT and TBPTT in three different application domains: associative memory with continuous Hopfield networks, document classification in citation networks using graph neural networks and hyperparameter optimization for fully connected networks. All experiments demonstrate that RBPs, especially the Neumann-RBP variant, are efficient and effective for optimizing convergent recurrent neural networks. Code is released at: \url{https://github.com/lrjconan/RBP}. |
| Tasks | Document Classification, Hyperparameter Optimization |
| Published | 2018-03-16 |
| URL | https://arxiv.org/abs/1803.06396v4 |
| https://arxiv.org/pdf/1803.06396v4.pdf | |
| PWC | https://paperswithcode.com/paper/reviving-and-improving-recurrent-back |
| Repo | https://github.com/lrjconan/RBP |
| Framework | pytorch |
Detecting Social Influence in Event Cascades by Comparing Discriminative Rankers
| Title | Detecting Social Influence in Event Cascades by Comparing Discriminative Rankers |
| Authors | Sandeep Soni, Shawn Ling Ramirez, Jacob Eisenstein |
| Abstract | The global dynamics of event cascades are often governed by the local dynamics of peer influence. However, detecting social influence from observational data is challenging due to confounds like homophily and practical issues like missing data. We propose a simple discriminative method to detect influence from observational data. The core of the approach is to train a ranking algorithm to predict the source of the next event in a cascade, and compare its out-of-sample accuracy against a competitive baseline which lacks access to features corresponding to social influence. We analyze synthetically generated data to show that this method correctly identifies influence in the presence of confounds, and is robust to both missing data and misspecification — unlike well-known alternatives. We apply the method to two real-world datasets: (1) the co-sponsorship of legislation in the U.S. House of Representatives on a social network of shared campaign donors; (2) rumors about the Higgs boson discovery on a follower network of $10^5$ Twitter accounts. Our model identifies the role of social influence in these scenarios and uses it to make more accurate predictions about the future trajectory of cascades. |
| Tasks | |
| Published | 2018-02-16 |
| URL | https://arxiv.org/abs/1802.06138v2 |
| https://arxiv.org/pdf/1802.06138v2.pdf | |
| PWC | https://paperswithcode.com/paper/discriminative-modeling-of-social-influence |
| Repo | https://github.com/sandeepsoni/MHP |
| Framework | none |
Learning Type-Aware Embeddings for Fashion Compatibility
| Title | Learning Type-Aware Embeddings for Fashion Compatibility |
| Authors | Mariya I. Vasileva, Bryan A. Plummer, Krishna Dusad, Shreya Rajpal, Ranjitha Kumar, David Forsyth |
| Abstract | Outfits in online fashion data are composed of items of many different types (e.g. top, bottom, shoes) that share some stylistic relationship with one another. A representation for building outfits requires a method that can learn both notions of similarity (for example, when two tops are interchangeable) and compatibility (items of possibly different type that can go together in an outfit). This paper presents an approach to learning an image embedding that respects item type, and jointly learns notions of item similarity and compatibility in an end-to-end model. To evaluate the learned representation, we crawled 68,306 outfits created by users on the Polyvore website. Our approach obtains 3-5% improvement over the state-of-the-art on outfit compatibility prediction and fill-in-the-blank tasks using our dataset, as well as an established smaller dataset, while supporting a variety of useful queries. |
| Tasks | |
| Published | 2018-03-25 |
| URL | http://arxiv.org/abs/1803.09196v2 |
| http://arxiv.org/pdf/1803.09196v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-type-aware-embeddings-for-fashion |
| Repo | https://github.com/mvasil/fashion-compatibility |
| Framework | pytorch |
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
| Title | QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning |
| Authors | Tabish Rashid, Mikayel Samvelyan, Christian Schroeder de Witt, Gregory Farquhar, Jakob Foerster, Shimon Whiteson |
| Abstract | In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, where global state information is available and communication constraints are lifted. Learning joint action-values conditioned on extra state information is an attractive way to exploit centralised learning, but the best strategy for then extracting decentralised policies is unclear. Our solution is QMIX, a novel value-based method that can train decentralised policies in a centralised end-to-end fashion. QMIX employs a network that estimates joint action-values as a complex non-linear combination of per-agent values that condition only on local observations. We structurally enforce that the joint-action value is monotonic in the per-agent values, which allows tractable maximisation of the joint action-value in off-policy learning, and guarantees consistency between the centralised and decentralised policies. We evaluate QMIX on a challenging set of StarCraft II micromanagement tasks, and show that QMIX significantly outperforms existing value-based multi-agent reinforcement learning methods. |
| Tasks | Multi-agent Reinforcement Learning, Starcraft, Starcraft II |
| Published | 2018-03-30 |
| URL | http://arxiv.org/abs/1803.11485v2 |
| http://arxiv.org/pdf/1803.11485v2.pdf | |
| PWC | https://paperswithcode.com/paper/qmix-monotonic-value-function-factorisation |
| Repo | https://github.com/oxwhirl/smac |
| Framework | pytorch |
Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality
| Title | Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality |
| Authors | Jun-Ho Choi, Jun-Hyuk Kim, Manri Cheon, Jong-Seok Lee |
| Abstract | Recently, it has been shown that in super-resolution, there exists a tradeoff relationship between the quantitative and perceptual quality of super-resolved images, which correspond to the similarity to the ground-truth images and the naturalness, respectively. In this paper, we propose a novel super-resolution method that can improve the perceptual quality of the upscaled images while preserving the conventional quantitative performance. The proposed method employs a deep network for multi-pass upscaling in company with a discriminator network and two quantitative score predictor networks. Experimental results demonstrate that the proposed method achieves a good balance of the quantitative and perceptual quality, showing more satisfactory results than existing methods. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2018-09-13 |
| URL | http://arxiv.org/abs/1809.04789v2 |
| http://arxiv.org/pdf/1809.04789v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-image-super-resolution |
| Repo | https://github.com/idearibosome/tf-perceptual-eusr |
| Framework | tf |
Representation Learning on Graphs with Jumping Knowledge Networks
| Title | Representation Learning on Graphs with Jumping Knowledge Networks |
| Authors | Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, Stefanie Jegelka |
| Abstract | Recent deep learning approaches for representation learning on graphs follow a neighborhood aggregation procedure. We analyze some important properties of these models, and propose a strategy to overcome those. In particular, the range of “neighboring” nodes that a node’s representation draws from strongly depends on the graph structure, analogous to the spread of a random walk. To adapt to local neighborhood properties and tasks, we explore an architecture – jumping knowledge (JK) networks – that flexibly leverages, for each node, different neighborhood ranges to enable better structure-aware representation. In a number of experiments on social, bioinformatics and citation networks, we demonstrate that our model achieves state-of-the-art performance. Furthermore, combining the JK framework with models like Graph Convolutional Networks, GraphSAGE and Graph Attention Networks consistently improves those models’ performance. |
| Tasks | Node Classification, Representation Learning |
| Published | 2018-06-09 |
| URL | http://arxiv.org/abs/1806.03536v2 |
| http://arxiv.org/pdf/1806.03536v2.pdf | |
| PWC | https://paperswithcode.com/paper/representation-learning-on-graphs-with |
| Repo | https://github.com/mori97/JKNet-dgl |
| Framework | pytorch |
EARL: Joint Entity and Relation Linking for Question Answering over Knowledge Graphs
| Title | EARL: Joint Entity and Relation Linking for Question Answering over Knowledge Graphs |
| Authors | Mohnish Dubey, Debayan Banerjee, Debanjan Chaudhuri, Jens Lehmann |
| Abstract | Many question answering systems over knowledge graphs rely on entity and relation linking components in order to connect the natural language input to the underlying knowledge graph. Traditionally, entity linking and relation linking have been performed either as dependent sequential tasks or as independent parallel tasks. In this paper, we propose a framework called EARL, which performs entity linking and relation linking as a joint task. EARL implements two different solution strategies for which we provide a comparative analysis in this paper: The first strategy is a formalisation of the joint entity and relation linking tasks as an instance of the Generalised Travelling Salesman Problem (GTSP). In order to be computationally feasible, we employ approximate GTSP solvers. The second strategy uses machine learning in order to exploit the connection density between nodes in the knowledge graph. It relies on three base features and re-ranking steps in order to predict entities and relations. We compare the strategies and evaluate them on a dataset with 5000 questions. Both strategies significantly outperform the current state-of-the-art approaches for entity and relation linking. |
| Tasks | Entity Linking, Knowledge Graphs, Question Answering |
| Published | 2018-01-11 |
| URL | http://arxiv.org/abs/1801.03825v4 |
| http://arxiv.org/pdf/1801.03825v4.pdf | |
| PWC | https://paperswithcode.com/paper/earl-joint-entity-and-relation-linking-for |
| Repo | https://github.com/AskNowQA/EARL |
| Framework | none |
3D Pose Estimation for Fine-Grained Object Categories
| Title | 3D Pose Estimation for Fine-Grained Object Categories |
| Authors | Yaming Wang, Xiao Tan, Yi Yang, Xiao Liu, Errui Ding, Feng Zhou, Larry S. Davis |
| Abstract | Existing object pose estimation datasets are related to generic object types and there is so far no dataset for fine-grained object categories. In this work, we introduce a new large dataset to benchmark pose estimation for fine-grained objects, thanks to the availability of both 2D and 3D fine-grained data recently. Specifically, we augment two popular fine-grained recognition datasets (StanfordCars and CompCars) by finding a fine-grained 3D CAD model for each sub-category and manually annotating each object in images with 3D pose. We show that, with enough training data, a full perspective model with continuous parameters can be estimated using 2D appearance information alone. We achieve this via a framework based on Faster/Mask R-CNN. This goes beyond previous works on category-level pose estimation, which only estimate discrete/continuous viewpoint angles or recover rotation matrices often with the help of key points. Furthermore, with fine-grained 3D models available, we incorporate a dense 3D representation named as location field into the CNN-based pose estimation framework to further improve the performance. The new dataset is available at www.umiacs.umd.edu/~wym/3dpose.html |
| Tasks | 3D Pose Estimation, Pose Estimation |
| Published | 2018-06-12 |
| URL | http://arxiv.org/abs/1806.04314v3 |
| http://arxiv.org/pdf/1806.04314v3.pdf | |
| PWC | https://paperswithcode.com/paper/3d-pose-estimation-for-fine-grained-object |
| Repo | https://github.com/yangyi02/3d_pose_fine_grained |
| Framework | none |
Realizing Learned Quadruped Locomotion Behaviors through Kinematic Motion Primitives
| Title | Realizing Learned Quadruped Locomotion Behaviors through Kinematic Motion Primitives |
| Authors | Abhik Singla, Shounak Bhattacharya, Dhaivat Dholakiya, Shalabh Bhatnagar, Ashitava Ghosal, Bharadwaj Amrutur, Shishir Kolathaya |
| Abstract | Humans and animals are believed to use a very minimal set of trajectories to perform a wide variety of tasks including walking. Our main objective in this paper is two fold 1) Obtain an effective tool to realize these basic motion patterns for quadrupedal walking, called the kinematic motion primitives (kMPs), via trajectories learned from deep reinforcement learning (D-RL) and 2) Realize a set of behaviors, namely trot, walk, gallop and bound from these kinematic motion primitives in our custom four legged robot, called the `Stoch’. D-RL is a data driven approach, which has been shown to be very effective for realizing all kinds of robust locomotion behaviors, both in simulation and in experiment. On the other hand, kMPs are known to capture the underlying structure of walking and yield a set of derived behaviors. We first generate walking gaits from D-RL, which uses policy gradient based approaches. We then analyze the resulting walking by using principal component analysis. We observe that the kMPs extracted from PCA followed a similar pattern irrespective of the type of gaits generated. Leveraging on this underlying structure, we then realize walking in Stoch by a straightforward reconstruction of joint trajectories from kMPs. This type of methodology improves the transferability of these gaits to real hardware, lowers the computational overhead on-board, and also avoids multiple training iterations by generating a set of derived behaviors from a single learned gait. | |
| Tasks | |
| Published | 2018-10-09 |
| URL | http://arxiv.org/abs/1810.03842v2 |
| http://arxiv.org/pdf/1810.03842v2.pdf | |
| PWC | https://paperswithcode.com/paper/realizing-learned-quadruped-locomotion |
| Repo | https://github.com/FlorianWilk/SpotMicroAI |
| Framework | none |
A test case for application of convolutional neural networks to spatio-temporal climate data: Re-identifying clustered weather patterns
| Title | A test case for application of convolutional neural networks to spatio-temporal climate data: Re-identifying clustered weather patterns |
| Authors | Ashesh Chattopadhyay, Pedram Hassanzadeh, Saba Pasha |
| Abstract | Convolutional neural networks (CNNs) can potentially provide powerful tools for classifying and identifying patterns in climate and environmental data. However, because of the inherent complexities of such data, which are often spatio-temporal, chaotic, and non-stationary, the CNN algorithms must be designed/evaluated for each specific dataset and application. Yet to start, CNN, a supervised technique, requires a large labeled dataset. Labeling demands (human) expert time, which combined with the limited number of relevant examples in this area, can discourage using CNNs for new problems. To address these challenges, here we (1) Propose an effective auto-labeling strategy based on using an unsupervised clustering algorithm and evaluating the performance of CNNs in re-identifying these clusters; (2) Use this approach to label thousands of daily large-scale weather patterns over North America in the outputs of a fully-coupled climate model and show the capabilities of CNNs in re-identifying the 4 clustered regimes. The deep CNN trained with $1000$ samples or more per cluster has an accuracy of $90%$ or better. Accuracy scales monotonically but nonlinearly with the size of the training set, e.g. reaching $94%$ with $3000$ training samples per cluster. Effects of architecture and hyperparameters on the performance of CNNs are examined and discussed. |
| Tasks | |
| Published | 2018-11-12 |
| URL | http://arxiv.org/abs/1811.04817v1 |
| http://arxiv.org/pdf/1811.04817v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-test-case-for-application-of-convolutional |
| Repo | https://github.com/ashesh6810/DLC-toolbox |
| Framework | none |
A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Images
| Title | A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Images |
| Authors | Yide Zhang, Yinhao Zhu, Evan Nichols, Qingfei Wang, Siyuan Zhang, Cody Smith, Scott Howard |
| Abstract | Fluorescence microscopy has enabled a dramatic development in modern biology. Due to its inherently weak signal, fluorescence microscopy is not only much noisier than photography, but also presented with Poisson-Gaussian noise where Poisson noise, or shot noise, is the dominating noise source. To get clean fluorescence microscopy images, it is highly desirable to have effective denoising algorithms and datasets that are specifically designed to denoise fluorescence microscopy images. While such algorithms exist, no such datasets are available. In this paper, we fill this gap by constructing a dataset - the Fluorescence Microscopy Denoising (FMD) dataset - that is dedicated to Poisson-Gaussian denoising. The dataset consists of 12,000 real fluorescence microscopy images obtained with commercial confocal, two-photon, and wide-field microscopes and representative biological samples such as cells, zebrafish, and mouse brain tissues. We use image averaging to effectively obtain ground truth images and 60,000 noisy images with different noise levels. We use this dataset to benchmark 10 representative denoising algorithms and find that deep learning methods have the best performance. To our knowledge, this is the first real microscopy image dataset for Poisson-Gaussian denoising purposes and it could be an important tool for high-quality, real-time denoising applications in biomedical research. |
| Tasks | Denoising |
| Published | 2018-12-26 |
| URL | http://arxiv.org/abs/1812.10366v2 |
| http://arxiv.org/pdf/1812.10366v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-poisson-gaussian-denoising-dataset-with |
| Repo | https://github.com/bmmi/denoising-fluorescence |
| Framework | pytorch |
Large-Scale Learnable Graph Convolutional Networks
| Title | Large-Scale Learnable Graph Convolutional Networks |
| Authors | Hongyang Gao, Zhengyang Wang, Shuiwang Ji |
| Abstract | Convolutional neural networks (CNNs) have achieved great success on grid-like data such as images, but face tremendous challenges in learning from more generic data such as graphs. In CNNs, the trainable local filters enable the automatic extraction of high-level features. The computation with filters requires a fixed number of ordered units in the receptive fields. However, the number of neighboring units is neither fixed nor are they ordered in generic graphs, thereby hindering the applications of convolutional operations. Here, we address these challenges by proposing the learnable graph convolutional layer (LGCL). LGCL automatically selects a fixed number of neighboring nodes for each feature based on value ranking in order to transform graph data into grid-like structures in 1-D format, thereby enabling the use of regular convolutional operations on generic graphs. To enable model training on large-scale graphs, we propose a sub-graph training method to reduce the excessive memory and computational resource requirements suffered by prior methods on graph convolutions. Our experimental results on node classification tasks in both transductive and inductive learning settings demonstrate that our methods can achieve consistently better performance on the Cora, Citeseer, Pubmed citation network, and protein-protein interaction network datasets. Our results also indicate that the proposed methods using sub-graph training strategy are more efficient as compared to prior approaches. |
| Tasks | Document Classification, Node Classification |
| Published | 2018-08-12 |
| URL | http://arxiv.org/abs/1808.03965v1 |
| http://arxiv.org/pdf/1808.03965v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-learnable-graph-convolutional |
| Repo | https://github.com/divelab/lgcn |
| Framework | tf |
Shallow decision-making analysis in General Video Game Playing
| Title | Shallow decision-making analysis in General Video Game Playing |
| Authors | Ivan Bravi, Jialin Liu, Diego Perez-Liebana, Simon Lucas |
| Abstract | The General Video Game AI competitions have been the testing ground for several techniques for game playing, such as evolutionary computation techniques, tree search algorithms, hyper heuristic based or knowledge based algorithms. So far the metrics used to evaluate the performance of agents have been win ratio, game score and length of games. In this paper we provide a wider set of metrics and a comparison method for evaluating and comparing agents. The metrics and the comparison method give shallow introspection into the agent’s decision making process and they can be applied to any agent regardless of its algorithmic nature. In this work, the metrics and the comparison method are used to measure the impact of the terms that compose a tree policy of an MCTS based agent, comparing with several baseline agents. The results clearly show how promising such general approach is and how it can be useful to understand the behaviour of an AI agent, in particular, how the comparison with baseline agents can help understanding the shape of the agent decision landscape. The presented metrics and comparison method represent a step toward to more descriptive ways of logging and analysing agent’s behaviours. |
| Tasks | Decision Making |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.01151v1 |
| http://arxiv.org/pdf/1806.01151v1.pdf | |
| PWC | https://paperswithcode.com/paper/shallow-decision-making-analysis-in-general |
| Repo | https://github.com/ivanbravi/ShadowingAgentForGVGAI |
| Framework | none |
