Paper Group ANR 624
Graph Kernels based on High Order Graphlet Parsing and Hashing. Repeatability Corner Cases in Document Ranking: The Impact of Score Ties. Semi-dual Regularized Optimal Transport. Engaging Image Captioning Via Personality. Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification. Multi-Layer Ensembling Techniques …
Graph Kernels based on High Order Graphlet Parsing and Hashing
| Title | Graph Kernels based on High Order Graphlet Parsing and Hashing |
| Authors | Anjan Dutta, Hichem Sahbi |
| Abstract | Graph-based methods are known to be successful in many machine learning and pattern classification tasks. These methods consider semi-structured data as graphs where nodes correspond to primitives (parts, interest points, segments, etc.) and edges characterize the relationships between these primitives. However, these non-vectorial graph data cannot be straightforwardly plugged into off-the-shelf machine learning algorithms without a preliminary step of – explicit/implicit – graph vectorization and embedding. This embedding process should be resilient to intra-class graph variations while being highly discriminant. In this paper, we propose a novel high-order stochastic graphlet embedding (SGE) that maps graphs into vector spaces. Our main contribution includes a new stochastic search procedure that efficiently parses a given graph and extracts/samples unlimitedly high-order graphlets. We consider these graphlets, with increasing orders, to model local primitives as well as their increasingly complex interactions. In order to build our graph representation, we measure the distribution of these graphlets into a given graph, using particular hash functions that efficiently assign sampled graphlets into isomorphic sets with a very low probability of collision. When combined with maximum margin classifiers, these graphlet-based representations have positive impact on the performance of pattern comparison and recognition as corroborated through extensive experiments using standard benchmark databases. |
| Tasks | |
| Published | 2018-02-28 |
| URL | http://arxiv.org/abs/1803.00425v1 |
| http://arxiv.org/pdf/1803.00425v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-kernels-based-on-high-order-graphlet |
| Repo | |
| Framework | |
Repeatability Corner Cases in Document Ranking: The Impact of Score Ties
| Title | Repeatability Corner Cases in Document Ranking: The Impact of Score Ties |
| Authors | Jimmy Lin, Peilin Yang |
| Abstract | Document ranking experiments should be repeatable. However, the interaction between multi-threaded indexing and score ties during retrieval may yield non-deterministic rankings, making repeatability not as trivial as one might imagine. In the context of the open-source Lucene search engine, score ties are broken by internal document ids, which are assigned at index time. Due to multi-threaded indexing, which makes experimentation with large modern document collections practical, internal document ids are not assigned consistently between different index instances of the same collection, and thus score ties are broken unpredictably. This short paper examines the effectiveness impact of such score ties, quantifying the variability that can be attributed to this phenomenon. The obvious solution to this non-determinism and to ensure repeatable document ranking is to break score ties using external collection document ids. This approach, however, comes with measurable efficiency costs due to the necessity of consulting external identifiers during query evaluation. |
| Tasks | Document Ranking |
| Published | 2018-07-16 |
| URL | https://arxiv.org/abs/1807.05798v2 |
| https://arxiv.org/pdf/1807.05798v2.pdf | |
| PWC | https://paperswithcode.com/paper/repeatability-corner-cases-in-document |
| Repo | |
| Framework | |
Semi-dual Regularized Optimal Transport
| Title | Semi-dual Regularized Optimal Transport |
| Authors | Marco Cuturi, Gabriel Peyré |
| Abstract | Variational problems that involve Wasserstein distances and more generally optimal transport (OT) theory are playing an increasingly important role in data sciences. Such problems can be used to form an examplar measure out of various probability measures, as in the Wasserstein barycenter problem, or to carry out parametric inference and density fitting, where the loss is measured in terms of an optimal transport cost to the measure of observations. Despite being conceptually simple, such problems are computationally challenging because they involve minimizing over quantities (Wasserstein distances) that are themselves hard to compute. Entropic regularization has recently emerged as an efficient tool to approximate the solution of such variational Wasserstein problems. In this paper, we give a thorough duality tour of these regularization techniques. In particular, we show how important concepts from classical OT such as c-transforms and semi-discrete approaches translate into similar ideas in a regularized setting. These dual formulations lead to smooth variational problems, which can be solved using smooth, differentiable and convex optimization problems that are simpler to implement and numerically more stable that their un-regularized counterparts. We illustrate the versatility of this approach by applying it to the computation of Wasserstein barycenters and gradient flows of spatial regularization functionals. |
| Tasks | |
| Published | 2018-11-13 |
| URL | http://arxiv.org/abs/1811.05527v1 |
| http://arxiv.org/pdf/1811.05527v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-dual-regularized-optimal-transport |
| Repo | |
| Framework | |
Engaging Image Captioning Via Personality
| Title | Engaging Image Captioning Via Personality |
| Authors | Kurt Shuster, Samuel Humeau, Hexiang Hu, Antoine Bordes, Jason Weston |
| Abstract | Standard image captioning tasks such as COCO and Flickr30k are factual, neutral in tone and (to a human) state the obvious (e.g., “a man playing a guitar”). While such tasks are useful to verify that a machine understands the content of an image, they are not engaging to humans as captions. With this in mind we define a new task, Personality-Captions, where the goal is to be as engaging to humans as possible by incorporating controllable style and personality traits. We collect and release a large dataset of 201,858 of such captions conditioned over 215 possible traits. We build models that combine existing work from (i) sentence representations (Mazare et al., 2018) with Transformers trained on 1.7 billion dialogue examples; and (ii) image representations (Mahajan et al., 2018) with ResNets trained on 3.5 billion social media images. We obtain state-of-the-art performance on Flickr30k and COCO, and strong performance on our new task. Finally, online evaluations validate that our task and models are engaging to humans, with our best model close to human performance. |
| Tasks | Image Captioning |
| Published | 2018-10-25 |
| URL | http://arxiv.org/abs/1810.10665v2 |
| http://arxiv.org/pdf/1810.10665v2.pdf | |
| PWC | https://paperswithcode.com/paper/engaging-image-captioning-via-personality |
| Repo | |
| Framework | |
Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification
| Title | Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification |
| Authors | Jingya Wang, Xiatian Zhu, Shaogang Gong, Wei Li |
| Abstract | Most existing person re-identification (re-id) methods require supervised model learning from a separate large set of pairwise labelled training data for every single camera pair. This significantly limits their scalability and usability in real-world large scale deployments with the need for performing re-id across many camera views. To address this scalability problem, we develop a novel deep learning method for transferring the labelled information of an existing dataset to a new unseen (unlabelled) target domain for person re-id without any supervised learning in the target domain. Specifically, we introduce an Transferable Joint Attribute-Identity Deep Learning (TJ-AIDL) for simultaneously learning an attribute-semantic and identitydiscriminative feature representation space transferrable to any new (unseen) target domain for re-id tasks without the need for collecting new labelled training data from the target domain (i.e. unsupervised learning in the target domain). Extensive comparative evaluations validate the superiority of this new TJ-AIDL model for unsupervised person re-id over a wide range of state-of-the-art methods on four challenging benchmarks including VIPeR, PRID, Market-1501, and DukeMTMC-ReID. |
| Tasks | Person Re-Identification, Unsupervised Person Re-Identification |
| Published | 2018-03-26 |
| URL | http://arxiv.org/abs/1803.09786v1 |
| http://arxiv.org/pdf/1803.09786v1.pdf | |
| PWC | https://paperswithcode.com/paper/transferable-joint-attribute-identity-deep |
| Repo | |
| Framework | |
Multi-Layer Ensembling Techniques for Multilingual Intent Classification
| Title | Multi-Layer Ensembling Techniques for Multilingual Intent Classification |
| Authors | Charles Costello, Ruixi Lin, Vishwas Mruthyunjaya, Bettina Bolla, Charles Jankowski |
| Abstract | In this paper we determine how multi-layer ensembling improves performance on multilingual intent classification. We develop a novel multi-layer ensembling approach that ensembles both different model initializations and different model architectures. We also introduce a new banking domain dataset and compare results against the standard ATIS dataset and the Chinese SMP2017 dataset to determine ensembling performance in multilingual and multi-domain contexts. We run ensemble experiments across all three datasets, and conclude that ensembling provides significant performance increases, and that multi-layer ensembling is a no-risk way to improve performance on intent classification. We also find that a diverse ensemble of simple models can reach perform comparable to much more sophisticated state-of-the-art models. Our best F 1 scores on ATIS, Banking, and SMP are 97.54%, 91.79%, and 93.55% respectively, which compare well with the state-of-the-art on ATIS and best submission to the SMP2017 competition. The total ensembling performance increases we achieve are 0.23%, 1.96%, and 4.04% F 1 respectively. |
| Tasks | Intent Classification |
| Published | 2018-06-20 |
| URL | http://arxiv.org/abs/1806.07914v1 |
| http://arxiv.org/pdf/1806.07914v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-layer-ensembling-techniques-for |
| Repo | |
| Framework | |
Database of iris images acquired in the presence of ocular pathologies and assessment of iris recognition reliability for disease-affected eyes
| Title | Database of iris images acquired in the presence of ocular pathologies and assessment of iris recognition reliability for disease-affected eyes |
| Authors | Mateusz Trokielewicz, Adam Czajka, Piotr Maciejewicz |
| Abstract | This paper presents a database of iris images collected from disease affected eyes and an analysis related to the influence of ocular diseases on iris recognition reliability. For that purpose we have collected a database of iris images acquired for 91 different eyes during routine ophthalmology visits. This collection gathers samples for healthy eyes as well as those with various eye pathologies, including cataract, acute glaucoma, posterior and anterior synechiae, retinal detachment, rubeosis iridis, corneal vascularization, corneal grafting, iris damage and atrophy and corneal ulcers, haze or opacities. To our best knowledge this is the first database of such kind that will be made publicly available. In the analysis the data were divided into five groups of samples presenting similar anticipated impact on iris recognition: 1) healthy (no impact), 2) unaffected, clear iris (although the illness was detected), 3) geometrically distorted irides, 4) distorted iris tissue and 5) obstructed iris tissue. Three different iris recognition methods (MIRLIN, VeriEye and OSIRIS) were then used to find differences in average genuine and impostor comparison scores calculated for healthy eyes and those impacted by a disease. Specifically, we obtained significantly worse genuine comparison scores for all iris matchers and all disease-affected eyes when compared to a group of healthy eyes, what have a high potential of impacting false non-match rate. |
| Tasks | Iris Recognition |
| Published | 2018-09-01 |
| URL | http://arxiv.org/abs/1809.00212v1 |
| http://arxiv.org/pdf/1809.00212v1.pdf | |
| PWC | https://paperswithcode.com/paper/database-of-iris-images-acquired-in-the |
| Repo | |
| Framework | |
Generalizing Across Multi-Objective Reward Functions in Deep Reinforcement Learning
| Title | Generalizing Across Multi-Objective Reward Functions in Deep Reinforcement Learning |
| Authors | Eli Friedman, Fred Fontaine |
| Abstract | Many reinforcement-learning researchers treat the reward function as a part of the environment, meaning that the agent can only know the reward of a state if it encounters that state in a trial run. However, we argue that this is an unnecessary limitation and instead, the reward function should be provided to the learning algorithm. The advantage is that the algorithm can then use the reward function to check the reward for states that the agent hasn’t even encountered yet. In addition, the algorithm can simultaneously learn policies for multiple reward functions. For each state, the algorithm would calculate the reward using each of the reward functions and add the rewards to its experience replay dataset. The Hindsight Experience Replay algorithm developed by Andrychowicz et al. (2017) does just this, and learns to generalize across a distribution of sparse, goal-based rewards. We extend this algorithm to linearly-weighted, multi-objective rewards and learn a single policy that can generalize across all linear combinations of the multi-objective reward. Whereas other multi-objective algorithms teach the Q-function to generalize across the reward weights, our algorithm enables the policy to generalize, and can thus be used with continuous actions. |
| Tasks | |
| Published | 2018-09-17 |
| URL | http://arxiv.org/abs/1809.06364v1 |
| http://arxiv.org/pdf/1809.06364v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalizing-across-multi-objective-reward |
| Repo | |
| Framework | |
Self-Adaptive Systems in Organic Computing: Strategies for Self-Improvement
| Title | Self-Adaptive Systems in Organic Computing: Strategies for Self-Improvement |
| Authors | Andreas Niederquell |
| Abstract | With the intensified use of intelligent things, the demands on the technological systems are increasing permanently. A possible approach to meet the continuously changing challenges is to shift the system integration from design to run-time by using adaptive systems. Diverse adaptivity properties, so-called self-* properties, form the basis of these systems and one of the properties is self-improvement. It describes the ability of a system not only to adapt to a changing environment according to a predefined model, but also the capability to adapt the adaptation logic of the whole system. In this paper, a closer look is taken at the structure of self-adaptive systems. Additionally, the systems’ ability to improve themselves during run-time is described from the perspective of Organic Computing. Furthermore, four different strategies for self-improvement are presented, following the taxonomy of self-adaptation suggested by Christian Krupitzer et al. |
| Tasks | |
| Published | 2018-08-08 |
| URL | http://arxiv.org/abs/1808.03519v1 |
| http://arxiv.org/pdf/1808.03519v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-adaptive-systems-in-organic-computing |
| Repo | |
| Framework | |
Reservoir computing with simple oscillators: Virtual and real networks
| Title | Reservoir computing with simple oscillators: Virtual and real networks |
| Authors | André Röhm, Kathy Lüdge |
| Abstract | The reservoir computing scheme is a machine learning mechanism which utilizes the naturally occuring computational capabilities of dynamical systems. One important subset of systems that has proven powerful both in experiments and theory are delay-systems. In this work, we investigate the reservoir computing performance of hybrid network-delay systems systematically by evaluating the NARMA10 and the Sante Fe task.. We construct ‘multiplexed networks’ that can be seen as intermediate steps on the scale from classical networks to the ‘virtual networks’ of delay systems. We find that the delay approach can be extended to the network case without loss of computational power, enabling the construction of faster reservoir computing substrates. |
| Tasks | |
| Published | 2018-02-23 |
| URL | http://arxiv.org/abs/1802.08590v1 |
| http://arxiv.org/pdf/1802.08590v1.pdf | |
| PWC | https://paperswithcode.com/paper/reservoir-computing-with-simple-oscillators |
| Repo | |
| Framework | |
Machine Learning-based Link Fault Identification and Localization in Complex Networks
| Title | Machine Learning-based Link Fault Identification and Localization in Complex Networks |
| Authors | Srinikethan Madapuzi Srinivasan, Tram Truong-Huu, Mohan Gurusamy |
| Abstract | With the proliferation of network devices and rapid development in information technology, networks such as Internet of Things are increasing in size and becoming more complex with heterogeneous wired and wireless links. In such networks, link faults may result in a link disconnection without immediate replacement or a link reconnection, e.g., a wireless node changes its access point. Identifying whether a link disconnection or a link reconnection has occurred and localizing the failed link become a challenging problem. An active probing approach requires a long time to probe the network by sending signaling messages on different paths, thus incurring significant communication delay and overhead. In this paper, we adopt a passive approach and develop a three-stage machine learning-based technique, namely ML-LFIL that identifies and localizes link faults by analyzing the measurements captured from the normal traffic flows, including aggregate flow rate, end-to-end delay and packet loss. ML-LFIL learns the traffic behavior in normal working conditions and different link fault scenarios. We train the learning model using support vector machine, multi-layer perceptron and random forest. We implement ML-LFIL and carry out extensive experiments using Mininet platform. Performance studies show that ML-LFIL achieves high accuracy while requiring much lower fault localization time compared to the active probing approach. |
| Tasks | |
| Published | 2018-12-10 |
| URL | http://arxiv.org/abs/1812.03650v2 |
| http://arxiv.org/pdf/1812.03650v2.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-based-link-fault |
| Repo | |
| Framework | |
Equation Embeddings
| Title | Equation Embeddings |
| Authors | Kriste Krstovski, David M. Blei |
| Abstract | We present an unsupervised approach for discovering semantic representations of mathematical equations. Equations are challenging to analyze because each is unique, or nearly unique. Our method, which we call equation embeddings, finds good representations of equations by using the representations of their surrounding words. We used equation embeddings to analyze four collections of scientific articles from the arXiv, covering four computer science domains (NLP, IR, AI, and ML) and $\sim$98.5k equations. Quantitatively, we found that equation embeddings provide better models when compared to existing word embedding approaches. Qualitatively, we found that equation embeddings provide coherent semantic representations of equations and can capture semantic similarity to other equations and to words. |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2018-03-24 |
| URL | http://arxiv.org/abs/1803.09123v1 |
| http://arxiv.org/pdf/1803.09123v1.pdf | |
| PWC | https://paperswithcode.com/paper/equation-embeddings |
| Repo | |
| Framework | |
Local Optimality and Generalization Guarantees for the Langevin Algorithm via Empirical Metastability
| Title | Local Optimality and Generalization Guarantees for the Langevin Algorithm via Empirical Metastability |
| Authors | Belinda Tzen, Tengyuan Liang, Maxim Raginsky |
| Abstract | We study the detailed path-wise behavior of the discrete-time Langevin algorithm for non-convex Empirical Risk Minimization (ERM) through the lens of metastability, adopting some techniques from Berglund and Gentz (2003. For a particular local optimum of the empirical risk, with an arbitrary initialization, we show that, with high probability, at least one of the following two events will occur: (1) the Langevin trajectory ends up somewhere outside the $\varepsilon$-neighborhood of this particular optimum within a short recurrence time; (2) it enters this $\varepsilon$-neighborhood by the recurrence time and stays there until a potentially exponentially long escape time. We call this phenomenon empirical metastability. This two-timescale characterization aligns nicely with the existing literature in the following two senses. First, the effective recurrence time (i.e., number of iterations multiplied by stepsize) is dimension-independent, and resembles the convergence time of continuous-time deterministic Gradient Descent (GD). However unlike GD, the Langevin algorithm does not require strong conditions on local initialization, and has the possibility of eventually visiting all optima. Second, the scaling of the escape time is consistent with the Eyring-Kramers law, which states that the Langevin scheme will eventually visit all local minima, but it will take an exponentially long time to transit among them. We apply this path-wise concentration result in the context of statistical learning to examine local notions of generalization and optimality. |
| Tasks | |
| Published | 2018-02-18 |
| URL | http://arxiv.org/abs/1802.06439v2 |
| http://arxiv.org/pdf/1802.06439v2.pdf | |
| PWC | https://paperswithcode.com/paper/local-optimality-and-generalization |
| Repo | |
| Framework | |
A Regression Model of Recurrent Deep Neural Networks for Noise Robust Estimation of the Fundamental Frequency Contour of Speech
| Title | A Regression Model of Recurrent Deep Neural Networks for Noise Robust Estimation of the Fundamental Frequency Contour of Speech |
| Authors | Akihiro Kato, Tomi Kinnunen |
| Abstract | The fundamental frequency (F0) contour of speech is a key aspect to represent speech prosody that finds use in speech and spoken language analysis such as voice conversion and speech synthesis as well as speaker and language identification. This work proposes new methods to estimate the F0 contour of speech using deep neural networks (DNNs) and recurrent neural networks (RNNs). They are trained using supervised learning with the ground truth of F0 contours. The latest prior research addresses this problem first as a frame-by-frame-classification problem followed by sequence tracking using deep neural network hidden Markov model (DNN-HMM) hybrid architecture. This study, however, tackles the problem as a regression problem instead, in order to obtain F0 contours with higher frequency resolution from clean and noisy speech. Experiments using PTDB-TUG corpus contaminated with additive noise (NOISEX-92) show the proposed method improves gross pitch error (GPE) by more than 25 % at signal-to-noise ratios (SNRs) between -10 dB and +10 dB as compared with one of the most noise-robust F0 trackers, PEFAC. Furthermore, the performance on fine pitch error (FPE) is improved by approximately 20 % against a state-of-the-art DNN-HMM-based approach. |
| Tasks | Language Identification, Speech Synthesis, Voice Conversion |
| Published | 2018-05-08 |
| URL | http://arxiv.org/abs/1805.02958v1 |
| http://arxiv.org/pdf/1805.02958v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-regression-model-of-recurrent-deep-neural |
| Repo | |
| Framework | |
On the Equivalence of Convolutional and Hadamard Networks using DFT
| Title | On the Equivalence of Convolutional and Hadamard Networks using DFT |
| Authors | Marcel Crasmaru |
| Abstract | In this paper we introduce activation functions that move the entire computation of Convolutional Networks into the frequency domain, where they are actually Hadamard Networks. To achieve this result we employ the properties of Discrete Fourier Transform. We present some implementation details and experimental results, as well as some insights into why convolutional networks perform well in learning use cases. |
| Tasks | |
| Published | 2018-10-27 |
| URL | http://arxiv.org/abs/1810.11650v1 |
| http://arxiv.org/pdf/1810.11650v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-equivalence-of-convolutional-and |
| Repo | |
| Framework | |
