Paper Group ANR 502
Improving Latent User Models in Online Social Media. Stochastic Canonical Correlation Analysis. Rise of the humanbot. Leveraging Node Attributes for Incomplete Relational Data. Evaluation of Classifiers for Image Segmentation: Applications for Eucalypt Forest Inventory. Error Correction for Dense Semantic Image Labeling. Sequence Prediction with Ne …
Improving Latent User Models in Online Social Media
| Title | Improving Latent User Models in Online Social Media |
| Authors | Adit Krishnan, Ashish Sharma, Hari Sundaram |
| Abstract | Modern social platforms are characterized by the presence of rich user-behavior data associated with the publication, sharing and consumption of textual content. Users interact with content and with each other in a complex and dynamic social environment while simultaneously evolving over time. In order to effectively characterize users and predict their future behavior in such a setting, it is necessary to overcome several challenges. Content heterogeneity and temporal inconsistency of behavior data result in severe sparsity at the user level. In this paper, we propose a novel mutual-enhancement framework to simultaneously partition and learn latent activity profiles of users. We propose a flexible user partitioning approach to effectively discover rare behaviors and tackle user-level sparsity. We extensively evaluate the proposed framework on massive datasets from real-world platforms including Q&A networks and interactive online courses (MOOCs). Our results indicate significant gains over state-of-the-art behavior models ( 15% avg ) in a varied range of tasks and our gains are further magnified for users with limited interaction data. The proposed algorithms are amenable to parallelization, scale linearly in the size of datasets, and provide flexibility to model diverse facets of user behavior. |
| Tasks | |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1711.11124v2 |
| http://arxiv.org/pdf/1711.11124v2.pdf | |
| PWC | https://paperswithcode.com/paper/improving-latent-user-models-in-online-social |
| Repo | |
| Framework | |
Stochastic Canonical Correlation Analysis
| Title | Stochastic Canonical Correlation Analysis |
| Authors | Chao Gao, Dan Garber, Nathan Srebro, Jialei Wang, Weiran Wang |
| Abstract | We study the sample complexity of canonical correlation analysis (CCA), \ie, the number of samples needed to estimate the population canonical correlation and directions up to arbitrarily small error. With mild assumptions on the data distribution, we show that in order to achieve $\epsilon$-suboptimality in a properly defined measure of alignment between the estimated canonical directions and the population solution, we can solve the empirical objective exactly with $N(\epsilon, \Delta, \gamma)$ samples, where $\Delta$ is the singular value gap of the whitened cross-covariance matrix and $1/\gamma$ is an upper bound of the condition number of auto-covariance matrices. Moreover, we can achieve the same learning accuracy by drawing the same level of samples and solving the empirical objective approximately with a stochastic optimization algorithm; this algorithm is based on the shift-and-invert power iterations and only needs to process the dataset for $\mathcal{O}\left(\log \frac{1}{\epsilon} \right)$ passes. Finally, we show that, given an estimate of the canonical correlation, the streaming version of the shift-and-invert power iterations achieves the same learning accuracy with the same level of sample complexity, by processing the data only once. |
| Tasks | Stochastic Optimization |
| Published | 2017-02-21 |
| URL | https://arxiv.org/abs/1702.06533v2 |
| https://arxiv.org/pdf/1702.06533v2.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-canonical-correlation-analysis |
| Repo | |
| Framework | |
Rise of the humanbot
| Title | Rise of the humanbot |
| Authors | Ricard Sole |
| Abstract | The accelerated path of technological development, particularly at the interface between hardware and biology has been suggested as evidence for future major technological breakthroughs associated to our potential to overcome biological constraints. This includes the potential of becoming immortal, having expanded cognitive capacities thanks to hardware implants or the creation of intelligent machines. Here I argue that several relevant evolutionary and structural constraints might prevent achieving most (if not all) these innovations. Instead, the coming future will bring novelties that will challenge many other aspects of our life and that can be seen as other feasible singularities. One particularly important one has to do with the evolving interactions between humans and non-intelligent robots capable of learning and communication. Here I argue that a long term interaction can lead to a new class of “agent” (the humanbot). The way shared memories get tangled over time will inevitably have important consequences for both sides of the pair, whose identity as separated entities might become blurred and ultimately vanish. Understanding such hybrid systems requires a second-order neuroscience approach while posing serious conceptual challenges, including the definition of consciousness. |
| Tasks | |
| Published | 2017-05-16 |
| URL | http://arxiv.org/abs/1705.05935v1 |
| http://arxiv.org/pdf/1705.05935v1.pdf | |
| PWC | https://paperswithcode.com/paper/rise-of-the-humanbot |
| Repo | |
| Framework | |
Leveraging Node Attributes for Incomplete Relational Data
| Title | Leveraging Node Attributes for Incomplete Relational Data |
| Authors | He Zhao, Lan Du, Wray Buntine |
| Abstract | Relational data are usually highly incomplete in practice, which inspires us to leverage side information to improve the performance of community detection and link prediction. This paper presents a Bayesian probabilistic approach that incorporates various kinds of node attributes encoded in binary form in relational models with Poisson likelihood. Our method works flexibly with both directed and undirected relational networks. The inference can be done by efficient Gibbs sampling which leverages sparsity of both networks and node attributes. Extensive experiments show that our models achieve the state-of-the-art link prediction results, especially with highly incomplete relational data. |
| Tasks | Community Detection, Link Prediction |
| Published | 2017-06-14 |
| URL | http://arxiv.org/abs/1706.04289v1 |
| http://arxiv.org/pdf/1706.04289v1.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-node-attributes-for-incomplete |
| Repo | |
| Framework | |
Evaluation of Classifiers for Image Segmentation: Applications for Eucalypt Forest Inventory
| Title | Evaluation of Classifiers for Image Segmentation: Applications for Eucalypt Forest Inventory |
| Authors | Rodrigo M. Ferreira, Ricardo M. Marcacini |
| Abstract | The task of counting eucalyptus trees from aerial images collected by unmanned aerial vehicles (UAVs) has been frequently explored by techniques of estimation of the basal area, i.e, by determining the expected number of trees based on sampling techniques. An alternative is the use of machine learning to identify patterns that represent a tree unit, and then search for the occurrence of these patterns throughout the image. This strategy depends on a supervised image segmentation step to define predefined interest regions. Thus, it is possible to automate the counting of eucalyptus trees in these images, thereby increasing the efficiency of the eucalyptus forest inventory management. In this paper, we evaluated 20 different classifiers for the image segmentation task. A real sample was used to analyze the counting trees task considering a practical environment. The results show that it possible to automate this task with 0.7% counting error, in particular, by using strategies based on a combination of classifiers. Moreover, we present some performance considerations about each classifier that can be useful as a basis for decision-making in future tasks. |
| Tasks | Decision Making, Semantic Segmentation |
| Published | 2017-03-28 |
| URL | http://arxiv.org/abs/1703.09436v1 |
| http://arxiv.org/pdf/1703.09436v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluation-of-classifiers-for-image |
| Repo | |
| Framework | |
Error Correction for Dense Semantic Image Labeling
| Title | Error Correction for Dense Semantic Image Labeling |
| Authors | Yu-Hui Huang, Xu Jia, Stamatios Georgoulis, Tinne Tuytelaars, Luc Van Gool |
| Abstract | Pixelwise semantic image labeling is an important, yet challenging, task with many applications. Typical approaches to tackle this problem involve either the training of deep networks on vast amounts of images to directly infer the labels or the use of probabilistic graphical models to jointly model the dependencies of the input (i.e. images) and output (i.e. labels). Yet, the former approaches do not capture the structure of the output labels, which is crucial for the performance of dense labeling, and the latter rely on carefully hand-designed priors that require costly parameter tuning via optimization techniques, which in turn leads to long inference times. To alleviate these restrictions, we explore how to arrive at dense semantic pixel labels given both the input image and an initial estimate of the output labels. We propose a parallel architecture that: 1) exploits the context information through a LabelPropagation network to propagate correct labels from nearby pixels to improve the object boundaries, 2) uses a LabelReplacement network to directly replace possibly erroneous, initial labels with new ones, and 3) combines the different intermediate results via a Fusion network to obtain the final per-pixel label. We experimentally validate our approach on two different datasets for the semantic segmentation and face parsing tasks respectively, where we show improvements over the state-of-the-art. We also provide both a quantitative and qualitative analysis of the generated results. |
| Tasks | Semantic Segmentation |
| Published | 2017-12-11 |
| URL | http://arxiv.org/abs/1712.03812v1 |
| http://arxiv.org/pdf/1712.03812v1.pdf | |
| PWC | https://paperswithcode.com/paper/error-correction-for-dense-semantic-image |
| Repo | |
| Framework | |
Sequence Prediction with Neural Segmental Models
| Title | Sequence Prediction with Neural Segmental Models |
| Authors | Hao Tang |
| Abstract | Segments that span contiguous parts of inputs, such as phonemes in speech, named entities in sentences, actions in videos, occur frequently in sequence prediction problems. Segmental models, a class of models that explicitly hypothesizes segments, have allowed the exploration of rich segment features for sequence prediction. However, segmental models suffer from slow decoding, hampering the use of computationally expensive features. In this thesis, we introduce discriminative segmental cascades, a multi-pass inference framework that allows us to improve accuracy by adding higher-order features and neural segmental features while maintaining efficiency. We also show that instead of including more features to obtain better accuracy, segmental cascades can be used to speed up training and decoding. Segmental models, similarly to conventional speech recognizers, are typically trained in multiple stages. In the first stage, a frame classifier is trained with manual alignments, and then in the second stage, segmental models are trained with manual alignments and the out- puts of the frame classifier. However, obtaining manual alignments are time-consuming and expensive. We explore end-to-end training for segmental models with various loss functions, and show how end-to-end training with marginal log loss can eliminate the need for detailed manual alignments. We draw the connections between the marginal log loss and a popular end-to-end training approach called connectionist temporal classification. We present a unifying framework for various end-to-end graph search-based models, such as hidden Markov models, connectionist temporal classification, and segmental models. Finally, we discuss possible extensions of segmental models to large-vocabulary sequence prediction tasks. |
| Tasks | |
| Published | 2017-09-05 |
| URL | http://arxiv.org/abs/1709.01572v3 |
| http://arxiv.org/pdf/1709.01572v3.pdf | |
| PWC | https://paperswithcode.com/paper/sequence-prediction-with-neural-segmental |
| Repo | |
| Framework | |
Neuron Segmentation Using Deep Complete Bipartite Networks
| Title | Neuron Segmentation Using Deep Complete Bipartite Networks |
| Authors | Jianxu Chen, Sreya Banerjee, Abhinav Grama, Walter J. Scheirer, Danny Z. Chen |
| Abstract | In this paper, we consider the problem of automatically segmenting neuronal cells in dual-color confocal microscopy images. This problem is a key task in various quantitative analysis applications in neuroscience, such as tracing cell genesis in Danio rerio (zebrafish) brains. Deep learning, especially using fully convolutional networks (FCN), has profoundly changed segmentation research in biomedical imaging. We face two major challenges in this problem. First, neuronal cells may form dense clusters, making it difficult to correctly identify all individual cells (even to human experts). Consequently, segmentation results of the known FCN-type models are not accurate enough. Second, pixel-wise ground truth is difficult to obtain. Only a limited amount of approximate instance-wise annotation can be collected, which makes the training of FCN models quite cumbersome. We propose a new FCN-type deep learning model, called deep complete bipartite networks (CB-Net), and a new scheme for leveraging approximate instance-wise annotation to train our pixel-wise prediction model. Evaluated using seven real datasets, our proposed new CB-Net model outperforms the state-of-the-art FCN models and produces neuron segmentation results of remarkable quality |
| Tasks | |
| Published | 2017-05-31 |
| URL | http://arxiv.org/abs/1705.11053v1 |
| http://arxiv.org/pdf/1705.11053v1.pdf | |
| PWC | https://paperswithcode.com/paper/neuron-segmentation-using-deep-complete |
| Repo | |
| Framework | |
Restricted Boltzmann machine to determine the input weights for extreme learning machines
| Title | Restricted Boltzmann machine to determine the input weights for extreme learning machines |
| Authors | Andre Pacheco, Renato Krohling, Carlos da Silva |
| Abstract | The Extreme Learning Machine (ELM) is a single-hidden layer feedforward neural network (SLFN) learning algorithm that can learn effectively and quickly. The ELM training phase assigns the input weights and bias randomly and does not change them in the whole process. Although the network works well, the random weights in the input layer can make the algorithm less effective and impact on its performance. Therefore, we propose a new approach to determine the input weights and bias for the ELM using the restricted Boltzmann machine (RBM), which we call RBM-ELM. We compare our new approach with a well-known approach to improve the ELM and a state of the art algorithm to select the weights for the ELM. The results show that the RBM-ELM outperforms both methodologies and achieve a better performance than the ELM. |
| Tasks | |
| Published | 2017-08-17 |
| URL | http://arxiv.org/abs/1708.05376v1 |
| http://arxiv.org/pdf/1708.05376v1.pdf | |
| PWC | https://paperswithcode.com/paper/restricted-boltzmann-machine-to-determine-the |
| Repo | |
| Framework | |
Horde of Bandits using Gaussian Markov Random Fields
| Title | Horde of Bandits using Gaussian Markov Random Fields |
| Authors | Sharan Vaswani, Mark Schmidt, Laks V. S. Lakshmanan |
| Abstract | The gang of bandits (GOB) model \cite{cesa2013gang} is a recent contextual bandits framework that shares information between a set of bandit problems, related by a known (possibly noisy) graph. This model is useful in problems like recommender systems where the large number of users makes it vital to transfer information between users. Despite its effectiveness, the existing GOB model can only be applied to small problems due to its quadratic time-dependence on the number of nodes. Existing solutions to combat the scalability issue require an often-unrealistic clustering assumption. By exploiting a connection to Gaussian Markov random fields (GMRFs), we show that the GOB model can be made to scale to much larger graphs without additional assumptions. In addition, we propose a Thompson sampling algorithm which uses the recent GMRF sampling-by-perturbation technique, allowing it to scale to even larger problems (leading to a “horde” of bandits). We give regret bounds and experimental results for GOB with Thompson sampling and epoch-greedy algorithms, indicating that these methods are as good as or significantly better than ignoring the graph or adopting a clustering-based approach. Finally, when an existing graph is not available, we propose a heuristic for learning it on the fly and show promising results. |
| Tasks | Multi-Armed Bandits, Recommendation Systems |
| Published | 2017-03-07 |
| URL | http://arxiv.org/abs/1703.02626v1 |
| http://arxiv.org/pdf/1703.02626v1.pdf | |
| PWC | https://paperswithcode.com/paper/horde-of-bandits-using-gaussian-markov-random |
| Repo | |
| Framework | |
Deep Stochastic Configuration Networks with Universal Approximation Property
| Title | Deep Stochastic Configuration Networks with Universal Approximation Property |
| Authors | Dianhui Wang, Ming Li |
| Abstract | This paper develops a randomized approach for incrementally building deep neural networks, where a supervisory mechanism is proposed to constrain the random assignment of the weights and biases, and all the hidden layers have direct links to the output layer. A fundamental result on the universal approximation property is established for such a class of randomized leaner models, namely deep stochastic configuration networks (DeepSCNs). A learning algorithm is presented to implement DeepSCNs with either specific architecture or self-organization. The read-out weights attached with all direct links from each hidden layer to the output layer are evaluated by the least squares method. Given a set of training examples, DeepSCNs can speedily produce a learning representation, that is, a collection of random basis functions with the cascaded inputs together with the read-out weights. An empirical study on a function approximation is carried out to demonstrate some properties of the proposed deep learner model. |
| Tasks | |
| Published | 2017-02-18 |
| URL | http://arxiv.org/abs/1702.05639v4 |
| http://arxiv.org/pdf/1702.05639v4.pdf | |
| PWC | https://paperswithcode.com/paper/deep-stochastic-configuration-networks-with |
| Repo | |
| Framework | |
Histograms of Gaussian normal distribution for feature matching in clutter scenes
| Title | Histograms of Gaussian normal distribution for feature matching in clutter scenes |
| Authors | Wei Zhou, Caiwen Ma, Arjan Kuijper |
| Abstract | 3D feature descriptor provide information between corresponding models and scenes. 3D objection recognition in cluttered scenes, however, remains a largely unsolved problem. Practical applications impose several challenges which are not fully addressed by existing methods. Especially in cluttered scenes there are many feature mismatches between scenes and models. We therefore propose Histograms of Gaussian Normal Distribution (HGND) for extracting salient features on a local reference frame (LRF) that enables us to solve this problem. We propose a LRF on each local surface patches using the scatter matrix’s eigenvectors. Then the HGND information of each salient point is calculated on the LRF, for which we use both the mesh and point data of the depth image. Experiments on 45 cluttered scenes of the Bologna Dataset and 50 cluttered scenes of the UWA Dataset are made to evaluate the robustness and descriptiveness of our HGND. Experiments carried out by us demonstrate that HGND obtains a more reliable matching rate than state-of-the-art approaches in cluttered situations. |
| Tasks | |
| Published | 2017-06-19 |
| URL | http://arxiv.org/abs/1706.05864v1 |
| http://arxiv.org/pdf/1706.05864v1.pdf | |
| PWC | https://paperswithcode.com/paper/histograms-of-gaussian-normal-distribution |
| Repo | |
| Framework | |
Training large margin host-pathogen protein-protein interaction predictors
| Title | Training large margin host-pathogen protein-protein interaction predictors |
| Authors | Abdul Hannan Basit, Wajid Arshad Abbasi, Amina Asif, Fayyaz Ul Amir Afsar Minhas |
| Abstract | Detection of protein-protein interactions (PPIs) plays a vital role in molecular biology. Particularly, infections are caused by the interactions of host and pathogen proteins. It is important to identify host-pathogen interactions (HPIs) to discover new drugs to counter infectious diseases. Conventional wet lab PPI prediction techniques have limitations in terms of large scale application and budget. Hence, computational approaches are developed to predict PPIs. This study aims to develop large margin machine learning models to predict interspecies PPIs with a special interest in host-pathogen protein interactions (HPIs). Especially, we focus on seeking answers to three queries that arise while developing an HPI predictor. 1) How should we select negative samples? 2) What should be the size of negative samples as compared to the positive samples? 3) What type of margin violation penalty should be used to train the predictor? We compare two available methods for negative sampling. Moreover, we propose a new method of assigning weights to each training example in weighted SVM depending on the distance of the negative examples from the positive examples. We have also developed a web server for our HPI predictor called HoPItor (Host Pathogen Interaction predicTOR) that can predict interactions between human and viral proteins. This webserver can be accessed at the URL: http://faculty.pieas.edu.pk/fayyaz/software.html#HoPItor. |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.07886v1 |
| http://arxiv.org/pdf/1711.07886v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-large-margin-host-pathogen-protein |
| Repo | |
| Framework | |
Sparse Depth Sensing for Resource-Constrained Robots
| Title | Sparse Depth Sensing for Resource-Constrained Robots |
| Authors | Fangchang Ma, Luca Carlone, Ulas Ayaz, Sertac Karaman |
| Abstract | We consider the case in which a robot has to navigate in an unknown environment but does not have enough on-board power or payload to carry a traditional depth sensor (e.g., a 3D lidar) and thus can only acquire a few (point-wise) depth measurements. We address the following question: is it possible to reconstruct the geometry of an unknown environment using sparse and incomplete depth measurements? Reconstruction from incomplete data is not possible in general, but when the robot operates in man-made environments, the depth exhibits some regularity (e.g., many planar surfaces with only a few edges); we leverage this regularity to infer depth from a small number of measurements. Our first contribution is a formulation of the depth reconstruction problem that bridges robot perception with the compressive sensing literature in signal processing. The second contribution includes a set of formal results that ascertain the exactness and stability of the depth reconstruction in 2D and 3D problems, and completely characterize the geometry of the profiles that we can reconstruct. Our third contribution is a set of practical algorithms for depth reconstruction: our formulation directly translates into algorithms for depth estimation based on convex programming. In real-world problems, these convex programs are very large and general-purpose solvers are relatively slow. For this reason, we discuss ad-hoc solvers that enable fast depth reconstruction in real problems. The last contribution is an extensive experimental evaluation in 2D and 3D problems, including Monte Carlo runs on simulated instances and testing on multiple real datasets. Empirical results confirm that the proposed approach ensures accurate depth reconstruction, outperforms interpolation-based strategies, and performs well even when the assumption of structured environment is violated. |
| Tasks | Compressive Sensing, Depth Estimation |
| Published | 2017-03-04 |
| URL | http://arxiv.org/abs/1703.01398v3 |
| http://arxiv.org/pdf/1703.01398v3.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-depth-sensing-for-resource-constrained |
| Repo | |
| Framework | |
On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisation
| Title | On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisation |
| Authors | Tommaso Cavallari, Stuart Golodetz, Nicholas A. Lord, Julien Valentin, Luigi Di Stefano, Philip H. S. Torr |
| Abstract | Camera relocalisation is an important problem in computer vision, with applications in simultaneous localisation and mapping, virtual/augmented reality and navigation. Common techniques either match the current image against keyframes with known poses coming from a tracker, or establish 2D-to-3D correspondences between keypoints in the current image and points in the scene in order to estimate the camera pose. Recently, regression forests have become a popular alternative to establish such correspondences. They achieve accurate results, but must be trained offline on the target scene, preventing relocalisation in new environments. In this paper, we show how to circumvent this limitation by adapting a pre-trained forest to a new scene on the fly. Our adapted forests achieve relocalisation performance that is on par with that of offline forests, and our approach runs in under 150ms, making it desirable for real-time systems that require online relocalisation. |
| Tasks | Camera Relocalization |
| Published | 2017-02-09 |
| URL | http://arxiv.org/abs/1702.02779v2 |
| http://arxiv.org/pdf/1702.02779v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-fly-adaptation-of-regression-forests |
| Repo | |
| Framework | |
