In this paper we present our approach for the Social Event Detection Task 1 of the MediaEval 2013. We address the problem of event detection and clustering by learning a distance measure between two images in a superv...
In this paper we present our approach for the Social Event Detection Task 1 of the MediaEval 2013. We address the problem of event detection and clustering by learning a distance measure between two images in a supervised way. Then, we apply a variant of the Quality Threshold clustering to detect events and assign the images accordingly. We can show that the performance measures do not decrease for an increasing number of documents and report the results achieved for the challenge.
We propose GQFormer, a probabilistic time series forecasting method that models the quantile function of the forecast distribution. Our methodology is rooted in the Implicit Quantile modeling approach, where samples f...
详细信息
Remarkable progress has been achieved in generative modeling for time-series data with the introduction of Generative Adversarial Networks (GANs) [1]. GANs are neural networks that are meant to generate synthetic inst...
详细信息
ISBN:
(纸本)9798350345032
Remarkable progress has been achieved in generative modeling for time-series data with the introduction of Generative Adversarial Networks (GANs) [1]. GANs are neural networks that are meant to generate synthetic instances of data utilizing two neural networks, a generator and a discriminator, that operate against each other at the same time [1]. The generator learns to generate fake data to get the discriminator to classify its generated samples as authentic. The discriminator, on the other hand, attempts to distinguish between authentic and produced data. Finally, the generator could generate realistic data. GANs have demonstrated their ability to generate realistic data and have made remarkable progress in various tasks, such as the generation of time-series [4], images [5], and videos [3]. Particularly, a significant amount of work has utilized GANs based on Recurrent Neural Networks (RNNs) for time-series generation [4]. However, by carefully examining the generated samples from these models, we can observe that RNN-based GANs, such as LSTM GANs and gated recurrent GANs, cannot handle long sequences. Although RNN-based GANs can generate many realistic samples, there is still a difficulty in training due to exploding vanishing gradients and mode collapse that limits their generation capability. In addition, these RNN-based GANs are typically designed for regular time-series data, and thus cannot maintain informative varying intervals properly, which is a major concern for generating time-series *** this paper, we propose SparseGAN, a novel sparse self-attention-based GANs that allows for attention-driven, long-memory modeling for regular and irregular time-series generation through learned embedding space. This way, it can yield a more informative representation and capture long-range dependencies for time-series generation while using original data for supervision. SparseGAN comprises two essential sub-networks: the Supervision Network and the Generation Ne
A key element of the social networks on the internet such as Facebook and Flickr is that they encourage users to create connections between themselves, other users and objects. One important task that has been approac...
详细信息
ISBN:
(纸本)9781450307475
A key element of the social networks on the internet such as Facebook and Flickr is that they encourage users to create connections between themselves, other users and objects. One important task that has been approached in the literature that deals with such data is to use social graphs to predict user behavior (e.g. joining a group of interest). More specifically, we study the cold-start problem, where users only participate in some relations, which we will call social relations, but not in the relation on which the predictions are made, which we will refer to as target relations. We propose a formalization of the problem and a principled approach to it based on multi-relational factorization techniques. Furthermore, we derive a principled feature extraction scheme from the social data to extract predictors for a classifier on the target relation. Experiments conducted on real world datasets show that our approach outperforms current methods. Copyright 2012 ACM.
The integration of OLAP with web-search technologies is a promising research topic. Recommender systems are popular web-search mechanisms, because they can address information overload and provide personalization of r...
详细信息
Time-series classification is an active research topic in machinelearning, as it finds applications in numerous domains. The k-NN classifier, based on the discrete time warping (DTW) distance, had been shown to be co...
详细信息
Current research has introduced new automatic hyperparameter optimization strategies that are able to accelerate this optimization process and outperform manual and grid or random search in terms of time and predictio...
详细信息
Current research has introduced new automatic hyperparameter optimization strategies that are able to accelerate this optimization process and outperform manual and grid or random search in terms of time and prediction accuracy. Currently, meta-learning methods that transfer knowledge from previous experiments to a new experiment arouse particular interest among researchers because it allows to improve the hyperparameter optimization. In this work we further improve the initialization techniques for sequential model-based optimization, the current state of the art hyperparameter optimization framework. Instead of using a static similarity prediction between data sets, we use the few evaluations on the new data sets to create new features. These features allow a better prediction of the data set similarity. Furthermore, we propose a technique that is inspired by active learning. In contrast to the current state of the art, it does not greedily choose the best hyperparameter configuration but considers that a time budget is available. Therefore, the first evaluations on the new data set are used for learning a better prediction function for predicting the similarity between data sets such that we are able to profit from this in future evaluations. We empirically compare the distance function by applying it in the scenario of the initialization of SMBO by meta-learning. Our two proposed approaches are compared against three competitor methods on one meta-data set with respect to the average rank between these methods and show that they are able to outperform them.
Dimensionality reduction is a crucial ingredient of machinelearning and data mining, boosting classification accuracy through the isolation of patterns via omission of noise. Nevertheless, recent studies have shown t...
详细信息
In machinelearning, hyperparameter optimization is a challenging but necessary task that is usually approached in a computationally expensive manner such as grid-search. Out of this reason, surrogate based black-box ...
详细信息
暂无评论