arXiv subjects

Ludovic Denoyer

Publications and source records attributed to Ludovic Denoyer.

54 records · Page 3Linked to original sources

arXiv2018

Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery

We introduce a dynamical spatio-temporal model formalized as a recurrent neural network for forecasting time series of spatial processes, i.e. series of observations sharing temporal and spatial dependencies. The model learns these dependencies through a structured latent dynamical component, while a decoder predicts the observations from the latent representations. We consider several variants of this model, corresponding to different prior hypothesis about the spatial relations between the series. The model is evaluated and compared to state-of-the-art baselines, on a variety of forecasting problems representative of different application areas: epidemiology, geo-spatial statistics and car-traffic prediction. Besides these evaluations, we also describe experiments showing the ability of this approach to extract relevant spatial relations.

cs.LG↗

arXiv2018

Unsupervised Machine Translation Using Monolingual Corpora Only

Machine translation has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale parallel corpora. There have been numerous attempts to extend these successes to low-resource language pairs, yet requiring tens of thousands of parallel sentences. In this work, we take this research direction to the extreme and investigate whether it is possible to learn to translate even without any parallel data. We propose a model that takes sentences from monolingual corpora in two different languages and maps them into the same latent space. By learning to reconstruct in both languages from this shared feature space, the model effectively learns to translate without using any labeled data. We demonstrate our model on two widely used datasets and two language pairs, reporting BLEU scores of 32.8 and 15.1 on the Multi30k and WMT English-French datasets, without using even a single parallel sentence at training time.

cs.CL↗

arXiv2018

Word Translation Without Parallel Data

State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel data supervision can be alleviated with character-level information. While these methods showed encouraging results, they are not on par with their supervised counterparts and are limited to pairs of languages sharing a common alphabet. In this work, we show that we can build a bilingual dictionary between two languages without using any parallel corpora, by aligning monolingual word embedding spaces in an unsupervised way. Without using any character information, our model even outperforms existing supervised methods on cross-lingual tasks for some language pairs. Our experiments demonstrate that our method works very well also for distant language pairs, like English-Russian or English-Chinese. We finally describe experiments on the English-Esperanto low-resource language pair, on which there only exists a limited amount of parallel data, to show the potential impact of our method in fully unsupervised machine translation. Our code, embeddings and dictionaries are publicly available.

cs.CL↗

arXiv2018

Fader Networks: Manipulating Images by Sliding Attributes

This paper introduces a new encoder-decoder architecture that is trained to reconstruct images by disentangling the salient information of the image and the values of attributes directly in the latent space. As a result, after training, our model can generate different realistic versions of an input image by varying the attribute values. By using continuous attribute values, we can choose how much a specific attribute is perceivable in the generated image. This property could allow for applications where users can modify an image using sliding knobs, like faders on a mixing console, to change the facial expression of a portrait, or to update the color of some objects. Compared to the state-of-the-art which mostly relies on training adversarial networks in pixel space by altering attribute values at train time, our approach results in much simpler training schemes and nicely scales to multiple attributes. We present evidence that our model can significantly change the perceived value of the attributes while preserving the naturalness of images.

cs.CV↗

arXiv2017

A Meta-Learning Approach to One-Step Active Learning

We consider the problem of learning when obtaining the training labels is costly, which is usually tackled in the literature using active-learning techniques. These approaches provide strategies to choose the examples to label before or during training. These strategies are usually based on heuristics or even theoretical measures, but are not learned as they are directly used during training. We design a model which aims at \textit{learning active-learning strategies} using a meta-learning setting. More specifically, we consider a pool-based setting, where the system observes all the examples of the dataset of a problem and has to choose the subset of examples to label in a single shot. Experiments show encouraging results.

cs.LG↗

arXiv2017

Options Discovery with Budgeted Reinforcement Learning

We consider the problem of learning hierarchical policies for Reinforcement Learning able to discover options, an option corresponding to a sub-policy over a set of primitive actions. Different models have been proposed during the last decade that usually rely on a predefined set of options. We specifically address the problem of automatically discovering options in decision processes. We describe a new learning model called Budgeted Option Neural Network (BONN) able to discover options based on a budgeted learning objective. The BONN model is evaluated on different classical RL problems, demonstrating both quantitative and qualitative interesting results.

cs.LG↗

arXiv2016

Sequential Cost-Sensitive Feature Acquisition

We propose a reinforcement learning based approach to tackle the cost-sensitive learning problem where each input feature has a specific cost. The acquisition process is handled through a stochastic policy which allows features to be acquired in an adaptive way. The general architecture of our approach relies on representation learning to enable performing prediction on any partially observed sample, whatever the set of its observed features are. The resulting model is an original mix of representation learning and of reinforcement learning ideas. It is learned with policy gradient techniques to minimize a budgeted inference cost. We demonstrate the effectiveness of our proposed method with several experiments on a variety of datasets for the sparse prediction problem where all features have the same cost, but also for some cost-sensitive settings.

cs.LG↗

arXiv2015

Representation Learning for cold-start recommendation

A standard approach to Collaborative Filtering (CF), i.e. prediction of user ratings on items, relies on Matrix Factorization techniques. Representations for both users and items are computed from the observed ratings and used for prediction. Unfortunatly, these transductive approaches cannot handle the case of new users arriving in the system, with no known rating, a problem known as user cold-start. A common approach in this context is to ask these incoming users for a few initialization ratings. This paper presents a model to tackle this twofold problem of (i) finding good questions to ask, (ii) building efficient representations from this small amount of information. The model can also be used in a more standard (warm) context. Our approach is evaluated on the classical CF problem and on the cold-start problem on four different datasets showing its ability to improve baseline performance in both cases.

cs.IR↗

arXiv2015

Reinforced Decision Trees

In order to speed-up classification models when facing a large number of categories, one usual approach consists in organizing the categories in a particular structure, this structure being then used as a way to speed-up the prediction computation. This is for example the case when using error-correcting codes or even hierarchies of categories. But in the majority of approaches, this structure is chosen \textit{by hand}, or during a preliminary step, and not integrated in the learning process. We propose a new model called Reinforced Decision Tree which simultaneously learns how to organize categories in a tree structure and how to classify any input based on this structure. This approach keeps the advantages of existing techniques (low inference complexity) but allows one to build efficient classifiers in one learning step. The learning algorithm is inspired by reinforcement learning and policy-gradient techniques which allows us to integrate the two steps (building the tree, and learning the classifier) in one single algorithm.

cs.LG↗

arXiv2014

Deep Sequential Neural Network

Neural Networks sequentially build high-level features through their successive layers. We propose here a new neural network model where each layer is associated with a set of candidate mappings. When an input is processed, at each layer, one mapping among these candidates is selected according to a sequential decision process. The resulting model is structured according to a DAG like architecture, so that a path from the root to a leaf node defines a sequence of transformations. Instead of considering global transformations, like in classical multilayer networks, this model allows us for learning a set of local transformations. It is thus able to process data with different characteristics through specific sequences of such local transformations, increasing the expression power of this model w.r.t a classical multilayered network. The learning algorithm is inspired from policy gradient techniques coming from the reinforcement learning domain and is used here instead of the classical back-propagation based gradient descent techniques. Experiments on different datasets show the relevance of this approach.

cs.LG↗

arXiv2014

Learning States Representations in POMDP

We propose to deal with sequential processes where only partial observations are available by learning a latent representation space on which policies may be accurately learned.

cs.LG↗

arXiv2014

Sequentially Generated Instance-Dependent Image Representations for Classification

In this paper, we investigate a new framework for image classification that adaptively generates spatial representations. Our strategy is based on a sequential process that learns to explore the different regions of any image in order to infer its category. In particular, the choice of regions is specific to each image, directed by the actual content of previously selected regions.The capacity of the system to handle incomplete image information as well as its adaptive region selection allow the system to perform well in budgeted classification tasks by exploiting a dynamicly generated representation of each image. We demonstrate the system's abilities in a series of image-based exploration and classification tasks that highlight its learned exploration and inference abilities.

cs.CV↗

arXiv2014

Learning Information Spread in Content Networks

We introduce a model for predicting the diffusion of content information on social media. When propagation is usually modeled on discrete graph structures, we introduce here a continuous diffusion model, where nodes in a diffusion cascade are projected onto a latent space with the property that their proximity in this space reflects the temporal diffusion process. We focus on the task of predicting contaminated users for an initial initial information source and provide preliminary results on differents datasets.

cs.LG↗

arXiv2012

Modeling Relational Data via Latent Factor Blockmodel

In this paper we address the problem of modeling relational data, which appear in many applications such as social network analysis, recommender systems and bioinformatics. Previous studies either consider latent feature based models but disregarding local structure in the network, or focus exclusively on capturing local structure of objects based on latent blockmodels without coupling with latent characteristics of objects. To combine the benefits of the previous work, we propose a novel model that can simultaneously incorporate the effect of latent features and covariates if any, as well as the effect of latent structure that may exist in the data. To achieve this, we model the relation graph as a function of both latent feature factors and latent cluster memberships of objects to collectively discover globally predictive intrinsic properties of objects and capture latent block structure in the network to improve prediction performance. We also develop an optimization transfer algorithm based on the generalized EM-style strategy to learn the latent factors. We prove the efficacy of our proposed model through the link prediction task and cluster analysis task, and extensive experiments on the synthetic data and several real world datasets suggest that our proposed LFBM model outperforms the other state of the art approaches in the evaluated tasks.

cs.DS↗

arXiv2012

Probabilistic Latent Tensor Factorization Model for Link Pattern Prediction in Multi-relational Networks

This paper aims at the problem of link pattern prediction in collections of objects connected by multiple relation types, where each type may play a distinct role. While common link analysis models are limited to single-type link prediction, we attempt here to capture the correlations among different relation types and reveal the impact of various relation types on performance quality. For that, we define the overall relations between object pairs as a \textit{link pattern} which consists in interaction pattern and connection structure in the network, and then use tensor formalization to jointly model and predict the link patterns, which we refer to as \textit{Link Pattern Prediction} (LPP) problem. To address the issue, we propose a Probabilistic Latent Tensor Factorization (PLTF) model by introducing another latent factor for multiple relation types and furnish the Hierarchical Bayesian treatment of the proposed probabilistic model to avoid overfitting for solving the LPP problem. To learn the proposed model we develop an efficient Markov Chain Monte Carlo sampling method. Extensive experiments are conducted on several real world datasets and demonstrate significant improvements over several existing state-of-the-art methods.

cs.SI↗

arXiv2012

Fast Reinforcement Learning with Large Action Sets using Error-Correcting Output Codes for MDP Factorization

The use of Reinforcement Learning in real-world scenarios is strongly limited by issues of scale. Most RL learning algorithms are unable to deal with problems composed of hundreds or sometimes even dozens of possible actions, and therefore cannot be applied to many real-world problems. We consider the RL problem in the supervised classification framework where the optimal policy is obtained through a multiclass classifier, the set of classes being the set of actions of the problem. We introduce error-correcting output codes (ECOCs) in this setting and propose two new methods for reducing complexity when using rollouts-based approaches. The first method consists in using an ECOC-based classifier as the multiclass classifier, reducing the learning complexity from O(A2) to O(Alog(A)). We then propose a novel method that profits from the ECOC's coding dictionary to split the initial MDP into O(log(A)) seperate two-action MDPs. This second method reduces learning complexity even further, from O(A2) to O(log(A)), thus rendering problems with large action sets tractable. We finish by experimentally demonstrating the advantages of our approach on a set of benchmark problems, both in speed and performance.

cs.LG↗

arXiv2011

Text Classification: A Sequential Reading Approach

We propose to model the text classification process as a sequential decision process. In this process, an agent learns to classify documents into topics while reading the document sentences sequentially and learns to stop as soon as enough information was read for deciding. The proposed algorithm is based on a modelisation of Text Classification as a Markov Decision Process and learns by using Reinforcement Learning. Experiments on four different classical mono-label corpora show that the proposed approach performs comparably to classical SVM approaches for large training sets, and better for small training sets. In addition, the model automatically adapts its reading process to the quantity of training information provided.

cs.AI↗

arXiv2011

Datum-Wise Classification: A Sequential Approach to Sparsity

We propose a novel classification technique whose aim is to select an appropriate representation for each datapoint, in contrast to the usual approach of selecting a representation encompassing the whole dataset. This datum-wise representation is found by using a sparsity inducing empirical risk, which is a relaxation of the standard L 0 regularized risk. The classification problem is modeled as a sequential decision process that sequentially chooses, for each datapoint, which features to use before classifying. Datum-Wise Classification extends naturally to multi-class tasks, and we describe a specific case where our inference has equivalent complexity to a traditional linear classifier, while still using a variable number of features. We compare our classifier to classical L 1 regularized linear models (L 1-SVM and LARS) on a set of common binary and multi-class datasets and show that for an equal average number of features used we can get improved performance using our method.

cs.AI↗