Paper Group ANR 846
Adversarial Learning with Local Coordinate Coding. Mobile Machine Learning Hardware at ARM: A Systems-on-Chip (SoC) Perspective. Sequential change-point detection in high-dimensional Gaussian graphical models. SCORES: Shape Composition with Recursive Substructure Priors. Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance. …
Adversarial Learning with Local Coordinate Coding
| Title | Adversarial Learning with Local Coordinate Coding |
| Authors | Jiezhang Cao, Yong Guo, Qingyao Wu, Chunhua Shen, Junzhou Huang, Mingkui Tan |
| Abstract | Generative adversarial networks (GANs) aim to generate realistic data from some prior distribution (e.g., Gaussian noises). However, such prior distribution is often independent of real data and thus may lose semantic information (e.g., geometric structure or content in images) of data. In practice, the semantic information might be represented by some latent distribution learned from data, which, however, is hard to be used for sampling in GANs. In this paper, rather than sampling from the pre-defined prior distribution, we propose a Local Coordinate Coding (LCC) based sampling method to improve GANs. We derive a generalization bound for LCC based GANs and prove that a small dimensional input is sufficient to achieve good generalization. Extensive experiments on various real-world datasets demonstrate the effectiveness of the proposed method. |
| Tasks | |
| Published | 2018-06-13 |
| URL | http://arxiv.org/abs/1806.04895v2 |
| http://arxiv.org/pdf/1806.04895v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-learning-with-local-coordinate |
| Repo | |
| Framework | |
Mobile Machine Learning Hardware at ARM: A Systems-on-Chip (SoC) Perspective
| Title | Mobile Machine Learning Hardware at ARM: A Systems-on-Chip (SoC) Perspective |
| Authors | Yuhao Zhu, Matthew Mattina, Paul Whatmough |
| Abstract | Machine learning is playing an increasingly significant role in emerging mobile application domains such as AR/VR, ADAS, etc. Accordingly, hardware architects have designed customized hardware for machine learning algorithms, especially neural networks, to improve compute efficiency. However, machine learning is typically just one processing stage in complex end-to-end applications, involving multiple components in a mobile Systems-on-a-chip (SoC). Focusing only on ML accelerators loses bigger optimization opportunity at the system (SoC) level. This paper argues that hardware architects should expand the optimization scope to the entire SoC. We demonstrate one particular case-study in the domain of continuous computer vision where camera sensor, image signal processor (ISP), memory, and NN accelerator are synergistically co-designed to achieve optimal system-level efficiency. |
| Tasks | |
| Published | 2018-01-19 |
| URL | http://arxiv.org/abs/1801.06274v2 |
| http://arxiv.org/pdf/1801.06274v2.pdf | |
| PWC | https://paperswithcode.com/paper/mobile-machine-learning-hardware-at-arm-a |
| Repo | |
| Framework | |
Sequential change-point detection in high-dimensional Gaussian graphical models
| Title | Sequential change-point detection in high-dimensional Gaussian graphical models |
| Authors | Hossein Keshavarz, George Michailidis, Yves Atchade |
| Abstract | High dimensional piecewise stationary graphical models represent a versatile class for modelling time varying networks arising in diverse application areas, including biology, economics, and social sciences. There has been recent work in offline detection and estimation of regime changes in the topology of sparse graphical models. However, the online setting remains largely unexplored, despite its high relevance to applications in sensor networks and other engineering monitoring systems, as well as financial markets. To that end, this work introduces a novel scalable online algorithm for detecting an unknown number of abrupt changes in the inverse covariance matrix of sparse Gaussian graphical models with small delay. The proposed algorithm is based upon monitoring the conditional log-likelihood of all nodes in the network and can be extended to a large class of continuous and discrete graphical models. We also investigate asymptotic properties of our procedure under certain mild regularity conditions on the graph size, sparsity level, number of samples, and pre- and post-changes in the topology of the network. Numerical works on both synthetic and real data illustrate the good performance of the proposed methodology both in terms of computational and statistical efficiency across numerous experimental settings. |
| Tasks | Change Point Detection |
| Published | 2018-06-20 |
| URL | http://arxiv.org/abs/1806.07870v1 |
| http://arxiv.org/pdf/1806.07870v1.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-change-point-detection-in-high |
| Repo | |
| Framework | |
SCORES: Shape Composition with Recursive Substructure Priors
| Title | SCORES: Shape Composition with Recursive Substructure Priors |
| Authors | Chenyang Zhu, Kai Xu, Siddhartha Chaudhuri, Renjiao Yi, Hao Zhang |
| Abstract | We introduce SCORES, a recursive neural network for shape composition. Our network takes as input sets of parts from two or more source 3D shapes and a rough initial placement of the parts. It outputs an optimized part structure for the composed shape, leading to high-quality geometry construction. A unique feature of our composition network is that it is not merely learning how to connect parts. Our goal is to produce a coherent and plausible 3D shape, despite large incompatibilities among the input parts. The network may significantly alter the geometry and structure of the input parts and synthesize a novel shape structure based on the inputs, while adding or removing parts to minimize a structure plausibility loss. We design SCORES as a recursive autoencoder network. During encoding, the input parts are recursively grouped to generate a root code. During synthesis, the root code is decoded, recursively, to produce a new, coherent part assembly. Assembled shape structures may be novel, with little global resemblance to training exemplars, yet have plausible substructures. SCORES therefore learns a hierarchical substructure shape prior based on per-node losses. It is trained on structured shapes from ShapeNet, and is applied iteratively to reduce the plausibility loss.We showresults of shape composition from multiple sources over different categories of man-made shapes and compare with state-of-the-art alternatives, demonstrating that our network can significantly expand the range of composable shapes for assembly-based modeling. |
| Tasks | |
| Published | 2018-09-14 |
| URL | http://arxiv.org/abs/1809.05398v1 |
| http://arxiv.org/pdf/1809.05398v1.pdf | |
| PWC | https://paperswithcode.com/paper/scores-shape-composition-with-recursive |
| Repo | |
| Framework | |
Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance
| Title | Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance |
| Authors | Ramprasaath R. Selvaraju, Prithvijit Chattopadhyay, Mohamed Elhoseiny, Tilak Sharma, Dhruv Batra, Devi Parikh, Stefan Lee |
| Abstract | Individual neurons in convolutional neural networks supervised for image-level classification tasks have been shown to implicitly learn semantically meaningful concepts ranging from simple textures and shapes to whole or partial objects - forming a “dictionary” of concepts acquired through the learning process. In this work we introduce a simple, efficient zero-shot learning approach based on this observation. Our approach, which we call Neuron Importance-AwareWeight Transfer (NIWT), learns to map domain knowledge about novel “unseen” classes onto this dictionary of learned concepts and then optimizes for network parameters that can effectively combine these concepts - essentially learning classifiers by discovering and composing learned semantic concepts in deep networks. Our approach shows improvements over previous approaches on the CUBirds and AWA2 generalized zero-shot learning benchmarks. We demonstrate our approach on a diverse set of semantic inputs as external domain knowledge including attributes and natural language captions. Moreover by learning inverse mappings, NIWT can provide visual and textual explanations for the predictions made by the newly learned classifiers and provide neuron names. Our code is available at https://github.com/ramprs/neuron-importance-zsl. |
| Tasks | Zero-Shot Learning |
| Published | 2018-08-08 |
| URL | http://arxiv.org/abs/1808.02861v1 |
| http://arxiv.org/pdf/1808.02861v1.pdf | |
| PWC | https://paperswithcode.com/paper/choose-your-neuron-incorporating-domain |
| Repo | |
| Framework | |
Dual Convolutional Neural Network for Graph of Graphs Link Prediction
| Title | Dual Convolutional Neural Network for Graph of Graphs Link Prediction |
| Authors | Shonosuke Harada, Hirotaka Akita, Masashi Tsubaki, Yukino Baba, Ichigaku Takigawa, Yoshihiro Yamanishi, Hisashi Kashima |
| Abstract | Graphs are general and powerful data representations which can model complex real-world phenomena, ranging from chemical compounds to social networks; however, effective feature extraction from graphs is not a trivial task, and much work has been done in the field of machine learning and data mining. The recent advances in graph neural networks have made automatic and flexible feature extraction from graphs possible and have improved the predictive performance significantly. In this paper, we go further with this line of research and address a more general problem of learning with a graph of graphs (GoG) consisting of an external graph and internal graphs, where each node in the external graph has an internal graph structure. We propose a dual convolutional neural network that extracts node representations by combining the external and internal graph structures in an end-to-end manner. Experiments on link prediction tasks using several chemical network datasets demonstrate the effectiveness of the proposed method. |
| Tasks | Link Prediction |
| Published | 2018-10-04 |
| URL | http://arxiv.org/abs/1810.02080v1 |
| http://arxiv.org/pdf/1810.02080v1.pdf | |
| PWC | https://paperswithcode.com/paper/dual-convolutional-neural-network-for-graph |
| Repo | |
| Framework | |
A Concept Specification and Abstraction-based Semantic Representation: Addressing the Barriers to Rule-based Machine Translation
| Title | A Concept Specification and Abstraction-based Semantic Representation: Addressing the Barriers to Rule-based Machine Translation |
| Authors | Patrick Connor |
| Abstract | Rule-based machine translation is more data efficient than the big data-based machine translation approaches, making it appropriate for languages with low bilingual corpus resources – i.e., minority languages. However, the rule-based approach has declined in popularity relative to its big data cousins primarily because of the extensive training and labour required to define the language rules. To address this, we present a semantic representation that 1) treats all bits of meaning as individual concepts that 2) modify or further specify one another to build a network that relates entities in space and time. Also, the representation can 3) encapsulate propositions and thereby define concepts in terms of other concepts, supporting the abstraction of underlying linguistic and ontological details. These features afford an exact, yet intuitive semantic representation aimed at handling the great variety in language and reducing labour and training time. The proposed natural language generation, parsing, and translation strategies are also amenable to probabilistic modeling and thus to learning the necessary rules from example data. |
| Tasks | Machine Translation, Text Generation |
| Published | 2018-07-06 |
| URL | http://arxiv.org/abs/1807.02226v3 |
| http://arxiv.org/pdf/1807.02226v3.pdf | |
| PWC | https://paperswithcode.com/paper/addressing-the-barriers-to-interlingual-rule |
| Repo | |
| Framework | |
Introducing user-prescribed constraints in Markov chains for nonlinear dimensionality reduction
| Title | Introducing user-prescribed constraints in Markov chains for nonlinear dimensionality reduction |
| Authors | Purushottam D. Dixit |
| Abstract | Stochastic kernel based dimensionality reduction approaches have become popular in the last decade. The central component of many of these methods is a symmetric kernel that quantifies the vicinity between pairs of data points and a kernel-induced Markov chain on the data. Typically, the Markov chain is fully specified by the kernel through row normalization. However, in many cases, it is desirable to impose user-specified stationary-state and dynamical constraints on the Markov chain. Unfortunately, no systematic framework exists to impose such user-defined constraints. Here, we introduce a path entropy maximization based approach to derive the transition probabilities of Markov chains using a kernel and additional user-specified constraints. We illustrate the usefulness of these Markov chains with examples. |
| Tasks | Dimensionality Reduction |
| Published | 2018-06-13 |
| URL | http://arxiv.org/abs/1806.05096v2 |
| http://arxiv.org/pdf/1806.05096v2.pdf | |
| PWC | https://paperswithcode.com/paper/introducing-user-prescribed-constraints-in |
| Repo | |
| Framework | |
Discriminating between Indo-Aryan Languages Using SVM Ensembles
| Title | Discriminating between Indo-Aryan Languages Using SVM Ensembles |
| Authors | Alina Maria Ciobanu, Marcos Zampieri, Shervin Malmasi, Santanu Pal, Liviu P. Dinu |
| Abstract | In this paper we present a system based on SVM ensembles trained on characters and words to discriminate between five similar languages of the Indo-Aryan family: Hindi, Braj Bhasha, Awadhi, Bhojpuri, and Magahi. We investigate the performance of individual features and combine the output of single classifiers to maximize performance. The system competed in the Indo-Aryan Language Identification (ILI) shared task organized within the VarDial Evaluation Campaign 2018. Our best entry in the competition, named ILIdentification, scored 88:95% F1 score and it was ranked 3rd out of 8 teams. |
| Tasks | Language Identification |
| Published | 2018-07-09 |
| URL | http://arxiv.org/abs/1807.03108v1 |
| http://arxiv.org/pdf/1807.03108v1.pdf | |
| PWC | https://paperswithcode.com/paper/discriminating-between-indo-aryan-languages |
| Repo | |
| Framework | |
Building Efficient Deep Neural Networks with Unitary Group Convolutions
| Title | Building Efficient Deep Neural Networks with Unitary Group Convolutions |
| Authors | Ritchie Zhao, Yuwei Hu, Jordan Dotzel, Christopher De Sa, Zhiru Zhang |
| Abstract | We propose unitary group convolutions (UGConvs), a building block for CNNs which compose a group convolution with unitary transforms in feature space to learn a richer set of representations than group convolution alone. UGConvs generalize two disparate ideas in CNN architecture, channel shuffling (i.e. ShuffleNet) and block-circulant networks (i.e. CirCNN), and provide unifying insights that lead to a deeper understanding of each technique. We experimentally demonstrate that dense unitary transforms can outperform channel shuffling in DNN accuracy. On the other hand, different dense transforms exhibit comparable accuracy performance. Based on these observations we propose HadaNet, a UGConv network using Hadamard transforms. HadaNets achieve similar accuracy to circulant networks with lower computation complexity, and better accuracy than ShuffleNets with the same number of parameters and floating-point multiplies. |
| Tasks | |
| Published | 2018-11-19 |
| URL | http://arxiv.org/abs/1811.07755v2 |
| http://arxiv.org/pdf/1811.07755v2.pdf | |
| PWC | https://paperswithcode.com/paper/building-efficient-deep-neural-networks-with |
| Repo | |
| Framework | |
CNN Based Posture-Free Hand Detection
| Title | CNN Based Posture-Free Hand Detection |
| Authors | Richard Adiguna, Yustinus Eko Soelistio |
| Abstract | Although many studies suggest high performance hand detection methods, those methods are likely to be overfitting. Fortunately, the Convolution Neural Network (CNN) based approach provides a better way that is less sensitive to translation and hand poses. However the CNN approach is complex and can increase computational time, which at the end reduce its effectiveness on a system where the speed is essential.In this study we propose a shallow CNN network which is fast, and insensitive to translation and hand poses. It is tested on two different domains of hand datasets, and performs in relatively comparable performance and faster than the other state-of-the-art hand CNN-based hand detection method. Our evaluation shows that the proposed shallow CNN network performs at 93.9% accuracy and reaches much faster speed than its competitors. |
| Tasks | |
| Published | 2018-09-27 |
| URL | http://arxiv.org/abs/1809.10432v1 |
| http://arxiv.org/pdf/1809.10432v1.pdf | |
| PWC | https://paperswithcode.com/paper/cnn-based-posture-free-hand-detection |
| Repo | |
| Framework | |
Leveraging Medical Sentiment to Understand Patients Health on Social Media
| Title | Leveraging Medical Sentiment to Understand Patients Health on Social Media |
| Authors | Shweta Yadav, Joy Sain, Amit Sheth, Asif Ekbal, Sriparna Saha, Pushpak Bhattacharyya |
| Abstract | The unprecedented growth of Internet users in recent years has resulted in an abundance of unstructured information in the form of social media text. A large percentage of this population is actively engaged in health social networks to share health-related information. In this paper, we address an important and timely topic by analyzing the users’ sentiments and emotions w.r.t their medical conditions. Towards this, we examine users on popular medical forums (Patient.info,dailystrength.org), where they post on important topics such as asthma, allergy, depression, and anxiety. First, we provide a benchmark setup for the task by crawling the data, and further define the sentiment specific fine-grained medical conditions (Recovered, Exist, Deteriorate, and Other). We propose an effective architecture that uses a Convolutional Neural Network (CNN) as a data-driven feature extractor and a Support Vector Machine (SVM) as a classifier. We further develop a sentiment feature which is sensitive to the medical context. Here, we show that the use of medical sentiment feature along with extracted features from CNN improves the model performance. In addition to our dataset, we also evaluate our approach on the benchmark “CLEF eHealth 2014” corpora and show that our model outperforms the state-of-the-art techniques. |
| Tasks | |
| Published | 2018-07-30 |
| URL | http://arxiv.org/abs/1807.11172v1 |
| http://arxiv.org/pdf/1807.11172v1.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-medical-sentiment-to-understand |
| Repo | |
| Framework | |
“Press Space to Fire”: Automatic Video Game Tutorial Generation
| Title | “Press Space to Fire”: Automatic Video Game Tutorial Generation |
| Authors | Michael Cerny Green, Ahmed Khalifa, Gabriella A. B. Barros, Julian Togelius |
| Abstract | We propose the problem of tutorial generation for games, i.e. to generate tutorials which can teach players to play games, as an AI problem. This problem can be approached in several ways, including generating natural language descriptions of game rules, generating instructive game levels, and generating demonstrations of how to play a game using agents that play in a human-like manner. We further argue that the General Video Game AI framework provides a useful testbed for addressing this problem. |
| Tasks | |
| Published | 2018-05-30 |
| URL | http://arxiv.org/abs/1805.11768v1 |
| http://arxiv.org/pdf/1805.11768v1.pdf | |
| PWC | https://paperswithcode.com/paper/press-space-to-fire-automatic-video-game |
| Repo | |
| Framework | |
Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification
| Title | Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification |
| Authors | Max Simchowitz, Horia Mania, Stephen Tu, Michael I. Jordan, Benjamin Recht |
| Abstract | We prove that the ordinary least-squares (OLS) estimator attains nearly minimax optimal performance for the identification of linear dynamical systems from a single observed trajectory. Our upper bound relies on a generalization of Mendelson’s small-ball method to dependent data, eschewing the use of standard mixing-time arguments. Our lower bounds reveal that these upper bounds match up to logarithmic factors. In particular, we capture the correct signal-to-noise behavior of the problem, showing that more unstable linear systems are easier to estimate. This behavior is qualitatively different from arguments which rely on mixing-time calculations that suggest that unstable systems are more difficult to estimate. We generalize our technique to provide bounds for a more general class of linear response time-series. |
| Tasks | Time Series |
| Published | 2018-02-22 |
| URL | http://arxiv.org/abs/1802.08334v4 |
| http://arxiv.org/pdf/1802.08334v4.pdf | |
| PWC | https://paperswithcode.com/paper/learning-without-mixing-towards-a-sharp |
| Repo | |
| Framework | |
Semi-supervised clustering for de-duplication
| Title | Semi-supervised clustering for de-duplication |
| Authors | Shrinu Kushagra, Shai Ben-David, Ihab Ilyas |
| Abstract | Data de-duplication is the task of detecting multiple records that correspond to the same real-world entity in a database. In this work, we view de-duplication as a clustering problem where the goal is to put records corresponding to the same physical entity in the same cluster and putting records corresponding to different physical entities into different clusters. We introduce a framework which we call promise correlation clustering. Given a complete graph $G$ with the edges labelled $0$ and $1$, the goal is to find a clustering that minimizes the number of $0$ edges within a cluster plus the number of $1$ edges across different clusters (or correlation loss). The optimal clustering can also be viewed as a complete graph $G^$ with edges corresponding to points in the same cluster being labelled $0$ and other edges being labelled $1$. Under the promise that the edge difference between $G$ and $G^$ is “small”, we prove that finding the optimal clustering (or $G^*$) is still NP-Hard. [Ashtiani et. al, 2016] introduced the framework of semi-supervised clustering, where the learning algorithm has access to an oracle, which answers whether two points belong to the same or different clusters. We further prove that even with access to a same-cluster oracle, the promise version is NP-Hard as long as the number queries to the oracle is not too large ($o(n)$ where $n$ is the number of vertices). Given these negative results, we consider a restricted version of correlation clustering. As before, the goal is to find a clustering that minimizes the correlation loss. However, we restrict ourselves to a given class $\mathcal F$ of clusterings. We offer a semi-supervised algorithmic approach to solve the restricted variant with success guarantees. |
| Tasks | |
| Published | 2018-10-10 |
| URL | http://arxiv.org/abs/1810.04361v1 |
| http://arxiv.org/pdf/1810.04361v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-clustering-for-de-duplication |
| Repo | |
| Framework | |
