Paper Group ANR 374
A feasibility study of deep neural networks for the recognition of banknotes regarding central bank requirements. Detecting F-formations & Roles in Crowded Social Scenes with Wearables: Combining Proxemics & Dynamics using LSTMs. Guarantees for Sound Abstractions for Generalized Planning (Extended Paper). A Data Driven Approach to Learning The Hami …
A feasibility study of deep neural networks for the recognition of banknotes regarding central bank requirements
| Title | A feasibility study of deep neural networks for the recognition of banknotes regarding central bank requirements |
| Authors | Julia Schulte, Daniel Staps, Alexander Lampe |
| Abstract | This paper contains a feasibility study of deep neural networks for the classification of Euro banknotes with respect to requirements of central banks on the ATM and high speed sorting industry. Instead of concentrating on the accuracy for a large number of classes as in the famous ImageNet Challenge we focus thus on conditions with few classes and the requirement of rejection of images belonging clearly to neither of the trained classes (i.e. classification in a so-called 0-class). These special requirements are part of frameworks defined by central banks as the European Central Bank and are met by current ATMs and high speed sorting machines. We also consider training and classification time on state of the art GPU hardware. The study concentrates on the banknote recognition whereas banknote class dependent authenticity and fitness checks are a topic of its own which is not considered in this work. |
| Tasks | |
| Published | 2019-07-18 |
| URL | https://arxiv.org/abs/1907.07890v2 |
| https://arxiv.org/pdf/1907.07890v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-feasibility-study-of-deep-neural-networks |
| Repo | |
| Framework | |
Detecting F-formations & Roles in Crowded Social Scenes with Wearables: Combining Proxemics & Dynamics using LSTMs
| Title | Detecting F-formations & Roles in Crowded Social Scenes with Wearables: Combining Proxemics & Dynamics using LSTMs |
| Authors | Alessio Rosatelli, Ekin Gedik, Hayley Hung |
| Abstract | In this paper, we investigate the use of proxemics and dynamics for automatically identifying conversing groups, or so-called F-formations. More formally we aim to automatically identify whether wearable sensor data coming from 2 people is indicative of F-formation membership. We also explore the problem of jointly detecting membership and more descriptive information about the pair relating to the role they take in the conversation (i.e. speaker or listener). We jointly model the concepts of proxemics and dynamics using binary proximity and acceleration obtained through a single wearable sensor per person. We test our approaches on the publicly available MatchNMingle dataset which was collected during real-life mingling events. We find out that fusion of these two modalities performs significantly better than them independently, providing an AUC of 0.975 when data from 30-second windows are used. Furthermore, our investigation into roles detection shows that each role pair requires a different time resolution for accurate detection. |
| Tasks | |
| Published | 2019-11-17 |
| URL | https://arxiv.org/abs/1911.07279v1 |
| https://arxiv.org/pdf/1911.07279v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-f-formations-roles-in-crowded |
| Repo | |
| Framework | |
Guarantees for Sound Abstractions for Generalized Planning (Extended Paper)
| Title | Guarantees for Sound Abstractions for Generalized Planning (Extended Paper) |
| Authors | Blai Bonet, Raquel Fuentetaja, Yolanda E-Martin, Daniel Borrajo |
| Abstract | Generalized planning is about finding plans that solve collections of planning instances, often infinite collections, rather than single instances. Recently it has been shown how to reduce the planning problem for generalized planning to the planning problem for a qualitative numerical problem; the latter being a reformulation that simultaneously captures all the instances in the collection. An important thread of research thus consists in finding such reformulations, or abstractions, automatically. A recent proposal learns the abstractions inductively from a finite and small sample of transitions from instances in the collection. However, as in all inductive processes, the learned abstraction is not guaranteed to be correct for the whole collection. In this work we address this limitation by performing an analysis of the abstraction with respect to the collection, and show how to obtain formal guarantees for generalization. These guarantees, in the form of first-order formulas, may be used to 1) define subcollections of instances on which the abstraction is guaranteed to be sound, 2) obtain necessary conditions for generalization under certain assumptions, and 3) do automated synthesis of complex invariants for planning problems. Our framework is general, it can be extended or combined with other approaches, and it has applications that go beyond generalized planning. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.12071v2 |
| https://arxiv.org/pdf/1905.12071v2.pdf | |
| PWC | https://paperswithcode.com/paper/guarantees-for-sound-abstractions-for |
| Repo | |
| Framework | |
A Data Driven Approach to Learning The Hamiltonian Matrix in Quantum Mechanics
| Title | A Data Driven Approach to Learning The Hamiltonian Matrix in Quantum Mechanics |
| Authors | Jordan Burns, David Maughan, Yih Sung |
| Abstract | We present a new machine learning technique which calculates a real-valued, time independent, finite dimensional Hamiltonian matrix from only experimental data. A novel cost function is given along with a proof that the cost function has the theoretically correct Hamiltonian as a global minimum. We present results based on data simulated on a classical computer and results based on simulations of quantum systems on IBM’s ibmqx2 quantum computer. We conclude with a discussion on the limitations of this data driven framework, as well as several possible extensions of this work. We also note that algorithm presented in this article not only serves as an example of using domain knowledge to design a machine learning framework, but also as an example of using domain knowledge to improve the speed of such algorithm. |
| Tasks | |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12548v1 |
| https://arxiv.org/pdf/1911.12548v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-data-driven-approach-to-learning-the |
| Repo | |
| Framework | |
LTG-Oslo Hierarchical Multi-task Network: The importance of negation for document-level sentiment in Spanish
| Title | LTG-Oslo Hierarchical Multi-task Network: The importance of negation for document-level sentiment in Spanish |
| Authors | Jeremy Barnes |
| Abstract | This paper details LTG-Oslo team’s participation in the sentiment track of the NEGES 2019 evaluation campaign. We participated in the task with a hierarchical multi-task network, which used shared lower-layers in a deep BiLSTM to predict negation, while the higher layers were dedicated to predicting document-level sentiment. The multi-task component shows promise as a way to incorporate information on negation into deep neural sentiment classifiers, despite the fact that the absolute results on the test set were relatively low for a binary classification task. |
| Tasks | |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07599v1 |
| https://arxiv.org/pdf/1906.07599v1.pdf | |
| PWC | https://paperswithcode.com/paper/ltg-oslo-hierarchical-multi-task-network-the |
| Repo | |
| Framework | |
IR2Vec: A Flow Analysis based Scalable Infrastructure for Program Encodings
| Title | IR2Vec: A Flow Analysis based Scalable Infrastructure for Program Encodings |
| Authors | Venkata Keerthy S, Rohit Aggarwal, Shalini Jain, Maunendra Sankar Desarkar, Ramakrishna Upadrasta, Y. N. Srikant |
| Abstract | We propose IR2Vec, a Concise and Scalable encoding infrastructure to represent programs as a distributed embedding in continuous space. This distributed embedding is obtained by combining representation learning methods with data and control flow information to capture the syntax as well as the semantics of the input programs. Our embeddings are obtained from the Intermediate Representation (IR) of the source code, and are both language as well as machine independent. The entities of the IR are modelled as relationships, and their representations are learned to form a seed embedding vocabulary. This vocabulary is used along with the flow analyses information to form a hierarchy of encodings based on various levels of program abstractions. We show the effectiveness of our methodology on a software engineering task (program classification) as well as optimization tasks (Heterogeneous device mapping and Thread coarsening). The embeddings generated by IR2Vec outperform the existing methods in all the three tasks even when using simple machine learning models. As we follow an agglomerative method of forming encodings at various levels using seed embedding vocabulary, our encoding is naturally more scalable and not data-hungry when compared to the other methods. |
| Tasks | Representation Learning |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1909.06228v2 |
| https://arxiv.org/pdf/1909.06228v2.pdf | |
| PWC | https://paperswithcode.com/paper/ir2vec-a-flow-analysis-based-scalable |
| Repo | |
| Framework | |
Long-range Prediction of Vital Signs Using Generative Boosting via LSTM Networks
| Title | Long-range Prediction of Vital Signs Using Generative Boosting via LSTM Networks |
| Authors | Shiyu Liu, Mehul Motani |
| Abstract | Vital signs including heart rate, respiratory rate, body temperature and blood pressure, are critical in the clinical decision making process. Effective early prediction of vital signs help to alert medical practitioner ahead of time and may prevent adverse health outcomes. In this paper, we suggest a new approach called generative boosting, in order to effectively perform early prediction of vital signs. Generative boosting consists of a generative model, to generate synthetic data for next few time steps, and several predictive models, to directly make long-range predictions based on observed and generated data. We explore generative boosting via long short-term memory (LSTM) for both the predictive and generative models, leading to a scheme called generative LSTM (GLSTM). Our experiments indicate that GLSTM outperforms a diverse range of strong benchmark models, with and without generative boosting. Finally, we use a mutual information based clustering algorithm to select a more representative dataset to train the generative model of GLSTM. This significantly improves the long-range predictive performance of high variation vital signs such as heart rate and systolic blood pressure. |
| Tasks | Decision Making |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.06621v1 |
| https://arxiv.org/pdf/1911.06621v1.pdf | |
| PWC | https://paperswithcode.com/paper/long-range-prediction-of-vital-signs-using |
| Repo | |
| Framework | |
ASTRA: High Throughput 3PC over Rings with Application to Secure Prediction
| Title | ASTRA: High Throughput 3PC over Rings with Application to Secure Prediction |
| Authors | Harsh Chaudhari, Ashish Choudhury, Arpita Patra, Ajith Suresh |
| Abstract | The concrete efficiency of secure computation has been the focus of many recent works. In this work, we present concretely-efficient protocols for secure $3$-party computation (3PC) over a ring of integers modulo $2^{\ell}$ tolerating one corruption, both with semi-honest and malicious security. Owing to the fact that computation over ring emulates computation over the real-world system architectures, secure computation over ring has gained momentum of late. Cast in the offline-online paradigm, our constructions present the most efficient online phase in concrete terms. In the semi-honest setting, our protocol requires communication of $2$ ring elements per multiplication gate during the {\it online} phase, attaining a per-party cost of {\em less than one element}. This is achieved for the first time in the regime of 3PC. In the {\it malicious} setting, our protocol requires communication of $4$ elements per multiplication gate during the online phase, beating the state-of-the-art protocol by $5$ elements. Realized with both the security notions of selective abort and fairness, the malicious protocol with fairness involves slightly more communication than its counterpart with abort security for the output gates {\em alone}. We apply our techniques from $3$PC in the regime of secure server-aided machine-learning (ML) inference for a range of prediction functions– linear regression, linear SVM regression, logistic regression, and linear SVM classification. Our setting considers a model-owner with trained model parameters and a client with a query, with the latter willing to learn the prediction of her query based on the model parameters of the former. The inputs and computation are outsourced to a set of three non-colluding servers. Our constructions catering to both semi-honest and the malicious world, invariably perform better than the existing constructions. |
| Tasks | |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02592v1 |
| https://arxiv.org/pdf/1912.02592v1.pdf | |
| PWC | https://paperswithcode.com/paper/astra-high-throughput-3pc-over-rings-with |
| Repo | |
| Framework | |
Extendable NFV-Integrated Control Method Using Reinforcement Learning
| Title | Extendable NFV-Integrated Control Method Using Reinforcement Learning |
| Authors | Akito Suzuki, Ryoichi Kawahara, Masahiro Kobayashi, Shigeaki Harada, Yousuke Takahashi, Keisuke Ishibashi |
| Abstract | Network functions virtualization (NFV) enables telecommunications service providers to realize various network services by flexibly combining multiple virtual network functions (VNFs). To provide such services, an NFV control method should optimally allocate such VNFs into physical networks and servers by taking account of the combination(s) of objective functions and constraints for each metric defined for each VNF type, e.g., VNF placements and routes between the VNFs. The NFV control method should also be extendable for adding new metrics or changing the combination of metrics. One approach for NFV control to optimize allocations is to construct an algorithm that simultaneously solves the combined optimization problem. However, this approach is not extendable because the problem needs to be reformulated every time a new metric is added or a combination of metrics is changed. Another approach involves using an extendable network-control architecture that coordinates multiple control algorithms specified for individual metrics. However, to the best of our knowledge, no method has been developed that can optimize allocations through this kind of coordination. In this paper, we propose an extendable NFV-integrated control method by coordinating multiple control algorithms. We also propose an efficient coordination algorithm based on reinforcement learning. Finally, we evaluate the effectiveness of the proposed method through simulations. |
| Tasks | |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09022v1 |
| https://arxiv.org/pdf/1912.09022v1.pdf | |
| PWC | https://paperswithcode.com/paper/extendable-nfv-integrated-control-method |
| Repo | |
| Framework | |
AI Matrix: A Deep Learning Benchmark for Alibaba Data Centers
| Title | AI Matrix: A Deep Learning Benchmark for Alibaba Data Centers |
| Authors | Wei Zhang, Wei Wei, Lingjie Xu, Lingling Jin, Cheng Li |
| Abstract | Alibaba has China’s largest e-commerce platform. To support its diverse businesses, Alibaba has its own large-scale data centers providing the computing foundation for a wide variety of software applications. Among these applications, deep learning (DL) has been playing an important role in delivering services like image recognition, objection detection, text recognition, recommendation, and language processing. To build more efficient data centers that deliver higher performance for these DL applications, it is important to understand their computational needs and use that information to guide the design of future computing infrastructure. An effective way to achieve this is through benchmarks that can fully represent Alibaba’s DL applications. |
| Tasks | |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.10562v1 |
| https://arxiv.org/pdf/1909.10562v1.pdf | |
| PWC | https://paperswithcode.com/paper/ai-matrix-a-deep-learning-benchmark-for |
| Repo | |
| Framework | |
One-Shot Decision-Making with and without Surrogates
| Title | One-Shot Decision-Making with and without Surrogates |
| Authors | Jakob Bossek, Pascal Kerschke, Aneta Neumann, Frank Neumann, Carola Doerr |
| Abstract | One-shot decision making is required in situations in which we can evaluate a fixed number of solution candidates but do not have any possibility for further, adaptive sampling. Such settings are frequently encountered in neural network design, hyper-parameter optimization, and many simulation-based real-world optimization tasks, in which evaluations are costly and time sparse. It seems intuitive that well-distributed samples should be more meaningful in one-shot decision making settings than uniform or grid-based samples, since they show a better coverage of the decision space. In practice, quasi-random designs such as Latin Hypercube Samples and low-discrepancy point sets form indeed the state of the art, as confirmed by a number of recent studies and competitions. In this work we take a closer look into the correlation between the distribution of the quasi-random designs and their performance in one-shot decision making tasks, with the goal to investigate whether the assumed correlation between uniform distribution and performance can be confirmed. We study three different decision tasks: classic one-shot optimization (only the best sample matters), one-shot optimization with surrogates (allowing to use surrogate models for selecting a design that need not necessarily be one of the evaluated samples), and one-shot regression (i.e., function approximation, with minimization of mean squared error as objective). Our results confirm an advantage of low-discrepancy designs for all three settings. The overall correlation, however, is rather weak. We complement our study by evolving problem-specific samples that show significantly better performance for the regression task than the standard approaches based on low-discrepancy sequences, giving strong indication that significant performance gains over state-of-the-art one-shot sampling techniques are possible. |
| Tasks | Decision Making |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.08956v2 |
| https://arxiv.org/pdf/1912.08956v2.pdf | |
| PWC | https://paperswithcode.com/paper/one-sh-ot-decision-making-with-and-without |
| Repo | |
| Framework | |
Scheduled Differentiable Architecture Search for Visual Recognition
| Title | Scheduled Differentiable Architecture Search for Visual Recognition |
| Authors | Zhaofan Qiu, Ting Yao, Yiheng Zhang, Yongdong Zhang, Tao Mei |
| Abstract | Convolutional Neural Networks (CNN) have been regarded as a capable class of models for visual recognition problems. Nevertheless, it is not trivial to develop generic and powerful network architectures, which requires significant efforts of human experts. In this paper, we introduce a new idea for automatically exploring architectures on a remould of Differentiable Architecture Search (DAS), which possesses the efficient search via gradient descent. Specifically, we present Scheduled Differentiable Architecture Search (SDAS) for both image and video recognition that nicely integrates the selection of operations during training with a schedule. Technically, an architecture or a cell is represented as a directed graph. Our SDAS gradually fixes the operations on the edges in the graph in a progressive and scheduled manner, as opposed to a one-step decision of operations for all the edges once the training completes in existing DAS, which may make the architecture brittle. Moreover, we enlarge the search space of SDAS particularly for video recognition by devising several unique operations to encode spatio-temporal dynamics and demonstrate the impact in affecting the architecture search of SDAS. Extensive experiments of architecture learning are conducted on CIFAR10, Kinetics10, UCF101 and HMDB51 datasets, and superior results are reported when comparing to DAS method. More remarkably, the search by our SDAS is around 2-fold faster than DAS. When transferring the learnt cells on CIFAR10 and Kinetics10 respectively to large-scale ImageNet and Kinetics400 datasets, the constructed network also outperforms several state-of-the-art hand-crafted structures. |
| Tasks | Video Recognition |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.10236v1 |
| https://arxiv.org/pdf/1909.10236v1.pdf | |
| PWC | https://paperswithcode.com/paper/190910236 |
| Repo | |
| Framework | |
Self-Attention Based Molecule Representation for Predicting Drug-Target Interaction
| Title | Self-Attention Based Molecule Representation for Predicting Drug-Target Interaction |
| Authors | Bonggun Shin, Sungsoo Park, Keunsoo Kang, Joyce C. Ho |
| Abstract | Predicting drug-target interactions (DTI) is an essential part of the drug discovery process, which is an expensive process in terms of time and cost. Therefore, reducing DTI cost could lead to reduced healthcare costs for a patient. In addition, a precisely learned molecule representation in a DTI model could contribute to developing personalized medicine, which will help many patient cohorts. In this paper, we propose a new molecule representation based on the self-attention mechanism, and a new DTI model using our molecule representation. The experiments show that our DTI model outperforms the state of the art by up to 4.9% points in terms of area under the precision-recall curve. Moreover, a study using the DrugBank database proves that our model effectively lists all known drugs targeting a specific cancer biomarker in the top-30 candidate list. |
| Tasks | Drug Discovery |
| Published | 2019-08-15 |
| URL | https://arxiv.org/abs/1908.06760v1 |
| https://arxiv.org/pdf/1908.06760v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-attention-based-molecule-representation |
| Repo | |
| Framework | |
Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering
| Title | Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering |
| Authors | Binghui Chen, Weihong Deng |
| Abstract | Deep metric learning has been widely applied in many computer vision tasks, and recently, it is more attractive in \emph{zero-shot image retrieval and clustering}(ZSRC) where a good embedding is requested such that the unseen classes can be distinguished well. Most existing works deem this ‘good’ embedding just to be the discriminative one and thus race to devise powerful metric objectives or hard-sample mining strategies for leaning discriminative embedding. However, in this paper, we first emphasize that the generalization ability is a core ingredient of this ‘good’ embedding as well and largely affects the metric performance in zero-shot settings as a matter of fact. Then, we propose the Energy Confused Adversarial Metric Learning(ECAML) framework to explicitly optimize a robust metric. It is mainly achieved by introducing an interesting Energy Confusion regularization term, which daringly breaks away from the traditional metric learning idea of discriminative objective devising, and seeks to ‘confuse’ the learned model so as to encourage its generalization ability by reducing overfitting on the seen classes. We train this confusion term together with the conventional metric objective in an adversarial manner. Although it seems weird to ‘confuse’ the network, we show that our ECAML indeed serves as an efficient regularization technique for metric learning and is applicable to various conventional metric methods. This paper empirically and experimentally demonstrates the importance of learning embedding with good generalization, achieving state-of-the-art performances on the popular CUB, CARS, Stanford Online Products and In-Shop datasets for ZSRC tasks. \textcolor[rgb]{1, 0, 0}{Code available at http://www.bhchen.cn/}. |
| Tasks | Image Retrieval, Metric Learning |
| Published | 2019-01-22 |
| URL | http://arxiv.org/abs/1901.07169v1 |
| http://arxiv.org/pdf/1901.07169v1.pdf | |
| PWC | https://paperswithcode.com/paper/energy-confused-adversarial-metric-learning |
| Repo | |
| Framework | |
What sets Verified Users apart? Insights, Analysis and Prediction of Verified Users on Twitter
| Title | What sets Verified Users apart? Insights, Analysis and Prediction of Verified Users on Twitter |
| Authors | Indraneil Paul, Abhinav Khattar, Shaan Chopra, Ponnurangam Kumaraguru, Manish Gupta |
| Abstract | Social network and publishing platforms, such as Twitter, support the concept of a secret proprietary verification process, for handles they deem worthy of platform-wide public interest. In line with significant prior work which suggests that possessing such a status symbolizes enhanced credibility in the eyes of the platform audience, a verified badge is clearly coveted among public figures and brands. What are less obvious are the inner workings of the verification process and what being verified represents. This lack of clarity, coupled with the flak that Twitter received by extending aforementioned status to political extremists in 2017, backed Twitter into publicly admitting that the process and what the status represented needed to be rethought. With this in mind, we seek to unravel the aspects of a user’s profile which likely engender or preclude verification. The aim of the paper is two-fold: First, we test if discerning the verification status of a handle from profile metadata and content features is feasible. Second, we unravel the features which have the greatest bearing on a handle’s verification status. We collected a dataset consisting of profile metadata of all 231,235 verified English-speaking users (as of July 2018), a control sample of 175,930 non-verified English-speaking users and all their 494 million tweets over a one year collection period. Our proposed models are able to reliably identify verification status (Area under curve AUC > 99%). We show that number of public list memberships, presence of neutral sentiment in tweets and an authoritative language style are the most pertinent predictors of verification status. To the best of our knowledge, this work represents the first attempt at discerning and classifying verification worthy users on Twitter. |
| Tasks | |
| Published | 2019-03-12 |
| URL | http://arxiv.org/abs/1903.04879v1 |
| http://arxiv.org/pdf/1903.04879v1.pdf | |
| PWC | https://paperswithcode.com/paper/what-sets-verified-users-apart-insights |
| Repo | |
| Framework | |
