Paper Group ANR 789
Information gain ratio correction: Improving prediction with more balanced decision tree splits. Quantitative Phase Imaging and Artificial Intelligence: A Review. AutoGraph: Imperative-style Coding with Graph-based Performance. Knowledge Graph Embedding with Entity Neighbors and Deep Memory Network. Jointly learning relevant subgraph patterns and n …
Information gain ratio correction: Improving prediction with more balanced decision tree splits
Title | Information gain ratio correction: Improving prediction with more balanced decision tree splits |
Authors | Antonin Leroux, Matthieu Boussard, Remi Dès |
Abstract | Decision trees algorithms use a gain function to select the best split during the tree’s induction. This function is crucial to obtain trees with high predictive accuracy. Some gain functions can suffer from a bias when it compares splits of different arities. Quinlan proposed a gain ratio in C4.5’s information gain function to fix this bias. In this paper, we present an updated version of the gain ratio that performs better as it tries to fix the gain ratio’s bias for unbalanced trees and some splits with low predictive interest. |
Tasks | |
Published | 2018-01-25 |
URL | http://arxiv.org/abs/1801.08310v1 |
http://arxiv.org/pdf/1801.08310v1.pdf | |
PWC | https://paperswithcode.com/paper/information-gain-ratio-correction-improving |
Repo | |
Framework | |
Quantitative Phase Imaging and Artificial Intelligence: A Review
Title | Quantitative Phase Imaging and Artificial Intelligence: A Review |
Authors | YoungJu Jo, Hyungjoo Cho, Sang Yun Lee, Gunho Choi, Geon Kim, Hyun-seok Min, YongKeun Park |
Abstract | Recent advances in quantitative phase imaging (QPI) and artificial intelligence (AI) have opened up the possibility of an exciting frontier. The fast and label-free nature of QPI enables the rapid generation of large-scale and uniform-quality imaging data in two, three, and four dimensions. Subsequently, the AI-assisted interrogation of QPI data using data-driven machine learning techniques results in a variety of biomedical applications. Also, machine learning enhances QPI itself. Herein, we review the synergy between QPI and machine learning with a particular focus on deep learning. Further, we provide practical guidelines and perspectives for further development. |
Tasks | |
Published | 2018-06-06 |
URL | http://arxiv.org/abs/1806.03982v2 |
http://arxiv.org/pdf/1806.03982v2.pdf | |
PWC | https://paperswithcode.com/paper/quantitative-phase-imaging-and-artificial |
Repo | |
Framework | |
AutoGraph: Imperative-style Coding with Graph-based Performance
Title | AutoGraph: Imperative-style Coding with Graph-based Performance |
Authors | Dan Moldovan, James M Decker, Fei Wang, Andrew A Johnson, Brian K Lee, Zachary Nado, D Sculley, Tiark Rompf, Alexander B Wiltschko |
Abstract | There is a perceived trade-off between machine learning code that is easy to write, and machine learning code that is scalable or fast to execute. In machine learning, imperative style libraries like Autograd and PyTorch are easy to write, but suffer from high interpretive overhead and are not easily deployable in production or mobile settings. Graph-based libraries like TensorFlow and Theano benefit from whole-program optimization and can be deployed broadly, but make expressing complex models more cumbersome. We describe how the use of staged programming in Python, via source code transformation, offers a midpoint between these two library design patterns, capturing the benefits of both. A key insight is to delay all type-dependent decisions until runtime, via dynamic dispatch. We instantiate these principles in AutoGraph, a software system that improves the programming experience of the TensorFlow library, and demonstrate usability improvements with no loss in performance compared to native TensorFlow graphs. We also show that our system is backend agnostic, and demonstrate targeting an alternate IR with characteristics not found in TensorFlow graphs. |
Tasks | |
Published | 2018-10-16 |
URL | http://arxiv.org/abs/1810.08061v2 |
http://arxiv.org/pdf/1810.08061v2.pdf | |
PWC | https://paperswithcode.com/paper/autograph-imperative-style-coding-with-graph |
Repo | |
Framework | |
Knowledge Graph Embedding with Entity Neighbors and Deep Memory Network
Title | Knowledge Graph Embedding with Entity Neighbors and Deep Memory Network |
Authors | Kai Wang, Yu Liu, Xiujuan Xu, Dan Lin |
Abstract | Knowledge Graph Embedding (KGE) aims to represent entities and relations of knowledge graph in a low-dimensional continuous vector space. Recent works focus on incorporating structural knowledge with additional information, such as entity descriptions, relation paths and so on. However, common used additional information usually contains plenty of noise, which makes it hard to learn valuable representation. In this paper, we propose a new kind of additional information, called entity neighbors, which contain both semantic and topological features about given entity. We then develop a deep memory network model to encode information from neighbors. Employing a gating mechanism, representations of structure and neighbors are integrated into a joint representation. The experimental results show that our model outperforms existing KGE methods utilizing entity descriptions and achieves state-of-the-art metrics on 4 datasets. |
Tasks | Graph Embedding, Knowledge Graph Embedding |
Published | 2018-08-11 |
URL | http://arxiv.org/abs/1808.03752v1 |
http://arxiv.org/pdf/1808.03752v1.pdf | |
PWC | https://paperswithcode.com/paper/knowledge-graph-embedding-with-entity |
Repo | |
Framework | |
Jointly learning relevant subgraph patterns and nonlinear models of their indicators
Title | Jointly learning relevant subgraph patterns and nonlinear models of their indicators |
Authors | Ryo Shirakawa, Yusei Yokoyama, Fumiya Okazaki, Ichigaku Takigawa |
Abstract | Classification and regression in which the inputs are graphs of arbitrary size and shape have been paid attention in various fields such as computational chemistry and bioinformatics. Subgraph indicators are often used as the most fundamental features, but the number of possible subgraph patterns are intractably large due to the combinatorial explosion. We propose a novel efficient algorithm to jointly learn relevant subgraph patterns and nonlinear models of their indicators. Previous methods for such joint learning of subgraph features and models are based on search for single best subgraph features with specific pruning and boosting procedures of adding their indicators one by one, which result in linear models of subgraph indicators. In contrast, the proposed approach is based on directly learning regression trees for graph inputs using a newly derived bound of the total sum of squares for data partitions by a given subgraph feature, and thus can learn nonlinear models through standard gradient boosting. An illustrative example we call the Graph-XOR problem to consider nonlinearity, numerical experiments with real datasets, and scalability comparisons to naive approaches using explicit pattern enumeration are also presented. |
Tasks | |
Published | 2018-07-09 |
URL | http://arxiv.org/abs/1807.02963v1 |
http://arxiv.org/pdf/1807.02963v1.pdf | |
PWC | https://paperswithcode.com/paper/jointly-learning-relevant-subgraph-patterns |
Repo | |
Framework | |
Relaxing the Identically Distributed Assumption in Gaussian Co-Clustering for High Dimensional Data
Title | Relaxing the Identically Distributed Assumption in Gaussian Co-Clustering for High Dimensional Data |
Authors | M. P. B. Gallaugher, C. Biernacki, P. D. McNicholas |
Abstract | A co-clustering model for continuous data that relaxes the identically distributed assumption within blocks of traditional co-clustering is presented. The proposed model, although allowing more flexibility, still maintains the very high degree of parsimony achieved by traditional co-clustering. A stochastic EM algorithm along with a Gibbs sampler is used for parameter estimation and an ICL criterion is used for model selection. Simulated and real datasets are used for illustration and comparison with traditional co-clustering. |
Tasks | Model Selection |
Published | 2018-08-25 |
URL | http://arxiv.org/abs/1808.08366v1 |
http://arxiv.org/pdf/1808.08366v1.pdf | |
PWC | https://paperswithcode.com/paper/relaxing-the-identically-distributed |
Repo | |
Framework | |
Anchor Box Optimization for Object Detection
Title | Anchor Box Optimization for Object Detection |
Authors | Yuanyi Zhong, Jianfeng Wang, Jian Peng, Lei Zhang |
Abstract | In this paper, we propose a general approach to optimize anchor boxes for object detection. Nowadays, anchor boxes are widely adopted in state-of-the-art detection frameworks. However, these frameworks usually pre-define anchor box shapes in heuristic ways and fix the sizes during training. To improve the accuracy and reduce the effort of designing anchor boxes, we propose to dynamically learn the anchor shapes, which allows the anchors to automatically adapt to the data distribution and the network learning capability. The learning approach can be easily implemented with stochastic gradient descent and can be plugged into any anchor box-based detection framework. The extra training cost is almost negligible and it has no impact on the inference time or memory cost. Exhaustive experiments demonstrate that the proposed anchor optimization method consistently achieves significant improvement ($\ge 1%$ mAP absolute gain) over the baseline methods on several benchmark datasets including Pascal VOC 07+12, MS COCO and Brainwash. Meanwhile, the robustness is also verified towards different anchor initialization methods and the number of anchor shapes, which greatly simplifies the problem of anchor box design. |
Tasks | Object Detection |
Published | 2018-12-02 |
URL | https://arxiv.org/abs/1812.00469v2 |
https://arxiv.org/pdf/1812.00469v2.pdf | |
PWC | https://paperswithcode.com/paper/anchor-box-optimization-for-object-detection |
Repo | |
Framework | |
Learning from Pseudo-Randomness With an Artificial Neural Network - Does God Play Pseudo-Dice?
Title | Learning from Pseudo-Randomness With an Artificial Neural Network - Does God Play Pseudo-Dice? |
Authors | Fenglei Fan, Ge Wang |
Abstract | Inspired by the fact that the neural network, as the mainstream for machine learning, has brought successes in many application areas, here we propose to use this approach for decoding hidden correlation among pseudo-random data and predicting events accordingly. With a simple neural network structure and a typical training procedure, we demonstrate the learning and prediction power of the neural network in extremely random environment. Finally, we postulate that the high sensitivity and efficiency of the neural network may allow to critically test if there could be any fundamental difference between quantum randomness and pseudo randomness, which is equivalent to the question: Does God play dice? |
Tasks | |
Published | 2018-01-05 |
URL | http://arxiv.org/abs/1801.01117v1 |
http://arxiv.org/pdf/1801.01117v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-from-pseudo-randomness-with-an |
Repo | |
Framework | |
Data-specific Adaptive Threshold for Face Recognition and Authentication
Title | Data-specific Adaptive Threshold for Face Recognition and Authentication |
Authors | Hsin-Rung Chou, Jia-Hong Lee, Yi-Ming Chan, Chu-Song Chen |
Abstract | Many face recognition systems boost the performance using deep learning models, but only a few researches go into the mechanisms for dealing with online registration. Although we can obtain discriminative facial features through the state-of-the-art deep model training, how to decide the best threshold for practical use remains a challenge. We develop a technique of adaptive threshold mechanism to improve the recognition accuracy. We also design a face recognition system along with the registering procedure to handle online registration. Furthermore, we introduce a new evaluation protocol to better evaluate the performance of an algorithm for real-world scenarios. Under our proposed protocol, our method can achieve a 22% accuracy improvement on the LFW dataset. |
Tasks | Face Recognition |
Published | 2018-10-26 |
URL | http://arxiv.org/abs/1810.11160v1 |
http://arxiv.org/pdf/1810.11160v1.pdf | |
PWC | https://paperswithcode.com/paper/data-specific-adaptive-threshold-for-face |
Repo | |
Framework | |
Optimal Testing in the Experiment-rich Regime
Title | Optimal Testing in the Experiment-rich Regime |
Authors | Sven Schmit, Virag Shah, Ramesh Johari |
Abstract | Motivated by the widespread adoption of large-scale A/B testing in industry, we propose a new experimentation framework for the setting where potential experiments are abundant (i.e., many hypotheses are available to test), and observations are costly; we refer to this as the experiment-rich regime. Such scenarios require the experimenter to internalize the opportunity cost of assigning a sample to a particular experiment. We fully characterize the optimal policy and give an algorithm to compute it. Furthermore, we develop a simple heuristic that also provides intuition for the optimal policy. We use simulations based on real data to compare both the optimal algorithm and the heuristic to other natural alternative experimental design frameworks. In particular, we discuss the paradox of power: high-powered classical tests can lead to highly inefficient sampling in the experiment-rich regime. |
Tasks | |
Published | 2018-05-30 |
URL | http://arxiv.org/abs/1805.11754v1 |
http://arxiv.org/pdf/1805.11754v1.pdf | |
PWC | https://paperswithcode.com/paper/optimal-testing-in-the-experiment-rich-regime |
Repo | |
Framework | |
A probabilistic atlas of the human thalamic nuclei combining ex vivo MRI and histology
Title | A probabilistic atlas of the human thalamic nuclei combining ex vivo MRI and histology |
Authors | Juan Eugenio Iglesias, Ricardo Insausti, Garikoitz Lerma-Usabiaga, Martina Bocchetta, Koen Van Leemput, Douglas N Greve, Andre van der Kouwe, Bruce Fischl, Cesar Caballero-Gaudes, Pedro M Paz-Alonso |
Abstract | The human thalamus is a brain structure that comprises numerous, highly specific nuclei. Since these nuclei are known to have different functions and to be connected to different areas of the cerebral cortex, it is of great interest for the neuroimaging community to study their volume, shape and connectivity in vivo with MRI. In this study, we present a probabilistic atlas of the thalamic nuclei built using ex vivo brain MRI scans and histological data, as well as the application of the atlas to in vivo MRI segmentation. The atlas was built using manual delineation of 26 thalamic nuclei on the serial histology of 12 whole thalami from six autopsy samples, combined with manual segmentations of the whole thalamus and surrounding structures (caudate, putamen, hippocampus, etc.) made on in vivo brain MR data from 39 subjects. The 3D structure of the histological data and corresponding manual segmentations was recovered using the ex vivo MRI as reference frame, and stacks of blockface photographs acquired during the sectioning as intermediate target. The atlas, which was encoded as an adaptive tetrahedral mesh, shows a good agreement with with previous histological studies of the thalamus in terms of volumes of representative nuclei. When applied to segmentation of in vivo scans using Bayesian inference, the atlas shows excellent test-retest reliability, robustness to changes in input MRI contrast, and ability to detect differential thalamic effects in subjects with Alzheimer’s disease. The probabilistic atlas and companion segmentation tool are publicly available as part of the neuroimaging package FreeSurfer. |
Tasks | Bayesian Inference |
Published | 2018-06-22 |
URL | http://arxiv.org/abs/1806.08634v1 |
http://arxiv.org/pdf/1806.08634v1.pdf | |
PWC | https://paperswithcode.com/paper/a-probabilistic-atlas-of-the-human-thalamic |
Repo | |
Framework | |
A Deep Reinforcement Learning Framework for Rebalancing Dockless Bike Sharing Systems
Title | A Deep Reinforcement Learning Framework for Rebalancing Dockless Bike Sharing Systems |
Authors | Ling Pan, Qingpeng Cai, Zhixuan Fang, Pingzhong Tang, Longbo Huang |
Abstract | Bike sharing provides an environment-friendly way for traveling and is booming all over the world. Yet, due to the high similarity of user travel patterns, the bike imbalance problem constantly occurs, especially for dockless bike sharing systems, causing significant impact on service quality and company revenue. Thus, it has become a critical task for bike sharing systems to resolve such imbalance efficiently. In this paper, we propose a novel deep reinforcement learning framework for incentivizing users to rebalance such systems. We model the problem as a Markov decision process and take both spatial and temporal features into consideration. We develop a novel deep reinforcement learning algorithm called Hierarchical Reinforcement Pricing (HRP), which builds upon the Deep Deterministic Policy Gradient algorithm. Different from existing methods that often ignore spatial information and rely heavily on accurate prediction, HRP captures both spatial and temporal dependencies using a divide-and-conquer structure with an embedded localized module. We conduct extensive experiments to evaluate HRP, based on a dataset from Mobike, a major Chinese dockless bike sharing company. Results show that HRP performs close to the 24-timeslot look-ahead optimization, and outperforms state-of-the-art methods in both service level and bike distribution. It also transfers well when applied to unseen areas. |
Tasks | |
Published | 2018-02-13 |
URL | http://arxiv.org/abs/1802.04592v4 |
http://arxiv.org/pdf/1802.04592v4.pdf | |
PWC | https://paperswithcode.com/paper/a-deep-reinforcement-learning-framework-for-1 |
Repo | |
Framework | |
Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association
Title | Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association |
Authors | Dapeng Chen, Hongsheng Li, Xihui Liu, Yantao Shen, Zejian Yuan, Xiaogang Wang |
Abstract | Person re-identification is an important task that requires learning discriminative visual features for distinguishing different person identities. Diverse auxiliary information has been utilized to improve the visual feature learning. In this paper, we propose to exploit natural language description as additional training supervisions for effective visual features. Compared with other auxiliary information, language can describe a specific person from more compact and semantic visual aspects, thus is complementary to the pixel-level image data. Our method not only learns better global visual feature with the supervision of the overall description but also enforces semantic consistencies between local visual and linguistic features, which is achieved by building global and local image-language associations. The global image-language association is established according to the identity labels, while the local association is based upon the implicit correspondences between image regions and noun phrases. Extensive experiments demonstrate the effectiveness of employing language as training supervisions with the two association schemes. Our method achieves state-of-the-art performance without utilizing any auxiliary information during testing and shows better performance than other joint embedding methods for the image-language association. |
Tasks | Person Re-Identification |
Published | 2018-08-05 |
URL | http://arxiv.org/abs/1808.01571v1 |
http://arxiv.org/pdf/1808.01571v1.pdf | |
PWC | https://paperswithcode.com/paper/improving-deep-visual-representation-for |
Repo | |
Framework | |
Sentence Simplification with Memory-Augmented Neural Networks
Title | Sentence Simplification with Memory-Augmented Neural Networks |
Authors | Tu Vu, Baotian Hu, Tsendsuren Munkhdalai, Hong Yu |
Abstract | Sentence simplification aims to simplify the content and structure of complex sentences, and thus make them easier to interpret for human readers, and easier to process for downstream NLP applications. Recent advances in neural machine translation have paved the way for novel approaches to the task. In this paper, we adapt an architecture with augmented memory capacities called Neural Semantic Encoders (Munkhdalai and Yu, 2017) for sentence simplification. Our experiments demonstrate the effectiveness of our approach on different simplification datasets, both in terms of automatic evaluation measures and human judgments. |
Tasks | Machine Translation |
Published | 2018-04-20 |
URL | http://arxiv.org/abs/1804.07445v1 |
http://arxiv.org/pdf/1804.07445v1.pdf | |
PWC | https://paperswithcode.com/paper/sentence-simplification-with-memory-augmented |
Repo | |
Framework | |
Design-based Analysis in Difference-In-Differences Settings with Staggered Adoption
Title | Design-based Analysis in Difference-In-Differences Settings with Staggered Adoption |
Authors | Susan Athey, Guido Imbens |
Abstract | In this paper we study estimation of and inference for average treatment effects in a setting with panel data. We focus on the setting where units, e.g., individuals, firms, or states, adopt the policy or treatment of interest at a particular point in time, and then remain exposed to this treatment at all times afterwards. We take a design perspective where we investigate the properties of estimators and procedures given assumptions on the assignment process. We show that under random assignment of the adoption date the standard Difference-In-Differences estimator is is an unbiased estimator of a particular weighted average causal effect. We characterize the proeperties of this estimand, and show that the standard variance estimator is conservative. |
Tasks | |
Published | 2018-08-15 |
URL | http://arxiv.org/abs/1808.05293v3 |
http://arxiv.org/pdf/1808.05293v3.pdf | |
PWC | https://paperswithcode.com/paper/design-based-analysis-in-difference-in |
Repo | |
Framework | |