Search Results for author:
Found 48 papers, 20 papers with code
Sequentially Generated Instance-Dependent Image Representations for Classification
In this paper, we investigate a new framework for image classification that adaptively generates spatial representations.
Learning Information Spread in Content Networks
We introduce a model for predicting the diffusion of content information on social media.
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.
Deep Sequential Neural Network
Instead of considering global transformations, like in classical multilayer networks, this model allows us for learning a set of local transformations.
Representation Learning for cold-start recommendation
Representations for both users and items are computed from the observed ratings and used for prediction.
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.
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.
Multi-view Generative Adversarial Networks
Most related studies focus on the classification point of view and assume that all the views are available at any time.
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.
Learning Time/Memory-Efficient Deep Architectures with Budgeted Super Networks
We propose to focus on the problem of discovering neural network architectures efficient in terms of both prediction quality and cost.
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.
A Meta-Learning Approach to One-Step Active Learning
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.
Word Translation Without Parallel Data
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.
Ranked #2 on
Word Alignment
on en-es
Unsupervised Machine Translation Using Monolingual Corpora Only
By learning to reconstruct in both languages from this shared feature space, the model effectively learns to translate without using any labeled data.
Ranked #7 on
Machine Translation
on WMT2016 German-English
Multi-View Data Generation Without View Supervision
We assume that the distribution of the data is driven by two independent latent factors: the content, which represents the intrinsic features of an object, and the view, which stands for the settings of a particular observation of that object.
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.
Phrase-Based & Neural Unsupervised Machine Translation
Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of language pairs.
Ranked #2 on
Machine Translation
on WMT2016 English-Russian
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.
A Reinforcement Learning-driven Translation Model for Search-Oriented Conversational Systems
Search-oriented conversational systems rely on information needs expressed in natural language (NL).
Phrase-Based \& Neural Unsupervised Machine Translation
Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of language pairs.
Multiple-Attribute Text Style Transfer
The dominant approach to unsupervised "style transfer" in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its "style".
Stochastic Adaptive Neural Architecture Search for Keyword Spotting
The problem of keyword spotting i. e. identifying keywords in a real-time audio stream is mainly solved by applying a neural network over successive sliding windows.
Multiple-Attribute Text Rewriting
The dominant approach to unsupervised "style transfer" in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its "style".
Unsupervised Object Segmentation by Redrawing
Object segmentation is a crucial problem that is usually solved by using supervised learning approaches over very large datasets composed of both images and corresponding object masks.
EDUCE: Explaining model Decisions through Unsupervised Concepts Extraction
Therefore, we propose a new self-interpretable model that performs output prediction and simultaneously provides an explanation in terms of the presence of particular concepts in the input.
Unsupervised Question Answering by Cloze Translation
We approach this problem by first learning to generate context, question and answer triples in an unsupervised manner, which we then use to synthesize Extractive QA training data automatically.
Binary Stochastic Representations for Large Multi-class Classification
Different models based on the notion of binary codes have been proposed to overcome this limitation, achieving in a sublinear inference complexity.
Large Memory Layers with Product Keys
In our experiments we consider a dataset with up to 30 billion words, and we plug our memory layer in a state-of-the-art transformer-based architecture.
Learning Dynamic Author Representations with Temporal Language Models
By conditioning language models with author and temporal vector states, we are able to leverage the latent dependencies between the text contexts.
Soft Token Matching for Interpretable Low-Resource Classification
We propose a model to tackle classification tasks in the presence of very little training data.
EDUCE: Explaining model Decision through Unsupervised Concepts Extraction
Therefore, we propose a new self-interpretable model that performs output prediction and simultaneously provides an explanation in terms of the presence of particular concepts in the input.
Learning Adaptive Exploration Strategies in Dynamic Environments Through Informed Policy Regularization
We test the performance of our algorithm in a variety of environments where tasks may vary within each episode.
Concept Matching for Low-Resource Classification
We propose a model to tackle classification tasks in the presence of very little training data.
Efficient Continual Learning with Modular Networks and Task-Driven Priors
Finally, we introduce a new modular architecture, whose modules represent atomic skills that can be composed to perform a certain task.
Meta-Reinforcement Learning With Informed Policy Regularization
Meta-reinforcement learning aims at finding a policy able to generalize to new environments.
Exploration-Driven Representation Learning in Reinforcement Learning
In this work, we introduce a method that explicitly couples representation learning with exploration when the agent is not provided with a uniform prior over the state space.
On Anytime Learning at Macroscale
Practitioners have then to decide how to allocate their computational budget in order to obtain the best performance at any point in time.
Learning a subspace of policies for online adaptation in Reinforcement Learning
There is a need to develop RL methods that generalize well to variations of the training conditions.
SaLinA: Sequential Learning of Agents
SaLinA is a simple library that makes implementing complex sequential learning models easy, including reinforcement learning algorithms.
Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching
Learning meaningful behaviors in the absence of reward is a difficult problem in reinforcement learning.
State of the Art of User Simulation approaches for conversational information retrieval
Conversational Information Retrieval (CIR) is an emerging field of Information Retrieval (IR) at the intersection of interactive IR and dialogue systems for open domain information needs.
Can I see an Example? Active Learning the Long Tail of Attributes and Relations
Using this framing, we introduce an active sampling method that asks for examples from the tail of the data distribution and show that it outperforms classical active learning methods on Visual Genome.
Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL
In reinforcement learning, the graph Laplacian has proved to be a valuable tool in the task-agnostic setting, with applications ranging from skill discovery to reward shaping.
Interactive Query Clarification and Refinement via User Simulation
When users initiate search sessions, their queries are often unclear or might lack of context; this resulting in inefficient document ranking.
Regularized Soft Actor-Critic for Behavior Transfer Learning
Existing imitation learning methods mainly focus on making an agent effectively mimic a demonstrated behavior, but do not address the potential contradiction between the behavior style and the objective of a task.
Building a Subspace of Policies for Scalable Continual Learning
We introduce Continual Subspace of Policies (CSP), a new approach that incrementally builds a subspace of policies for training a reinforcement learning agent on a sequence of tasks.
Learning Computational Efficient Bots with Costly Features
Deep reinforcement learning (DRL) techniques have become increasingly used in various fields for decision-making processes.
Policy Diversity for Cooperative Agents
In this work, we propose a method called Moment-Matching Policy Diversity to alleviate this problem.
