检索结果-内蒙古大学图书馆

Overview of the TREC 2020 fair ranking track

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Biega, Asia J. Ekstrand, Michael D. Kohlmeier, Sebastian Diaz, Fernando Feldman, Sergey Microsoft Research Montréal Boise State University Allen Institute for Artificial Intelligence Montreal Institute for Learning Algorithms

For 2020, we again adopted an academic search task, where we have a corpus of academic article abstracts and queries submitted to a production academic search engine. The central goal of the Fair Ranking track is to provide fair exposure to different groups of authors (a group fairness framing). We recognize that there may be multiple group definitions (e.g. based on demographics, stature, topic) and hoped for the systems to be robust to these. We expected participants to develop systems that optimize for fairness and relevance for arbitrary group definitions, and did not reveal the exact group deffinitions until after the evaluation runs were submitted. The track contains two tasks, reranking and retrieval, with a shared evaluation. Rerank runs sorted a query-dependent list of documents to simultaneously provide fairness and relevance. Retrieval runs returned 100-item rankings from the corpus in response to a query string. The track organizers provided a sequence of queries, each accompanied by a varying-size set of documents. Both tasks used the same queries;participants were asked not to use the test queries' rerank sets as a component of their retrieval model training. Copyright © 2021, The Authors. All rights reserved.

关键词： Search engines

An Attention-based Collaboration framework for multi-view network representation learning

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Qu, Meng Tang, Jian Shang, Jingbo Ren, Xiang Zhang, Ming Han, Jiawei University of Illinois at Urbana-Champaign IL United States Hec Montreal Montreal Institute of Learning Algorithms Peking University Beijing China

learning distributed node representations in networks has been attracting increasing attention recently due to its effectiveness in a variety of applications. Existing approaches usually study networks with a single type of proximity between nodes, which defines a single view of a network. However, in reality there usually exists multiple types of proximities between nodes, yielding networks with multiple views. This paper studies learning node representations for networks with multiple views, which aims to infer robust node representations across different views. We propose a multi-view representation learning approach, which promotes the collaboration of different views and lets them vote for the robust representations. During the voting process, an attention mechanism is introduced, which enables each node to focus on the most informative views. Experimental results on real-world networks show that the proposed approach outperforms existing state-of-the-art approaches for network representation learning with a single view and other competitive approaches with multiple views. Copyright © 2017, The Authors. All rights reserved.

关键词： Machine learning

Pixelvae: A latent variable model for natural images 5

学校读者我要写书评

暂无评论

Pixelvae: A latent variable model for natural images

5th International Conference on learning Representations, ICLR 2017

作者： Gulrajani, Ishaan Kumar, Kundan Ahmed, Faruk Taiga, Adrien Ali Visin, Francesco Vazquez, David Courville, Aaron Montreal Institute for Learning Algorithms Université de Montréal Canada Department of Computer Science and Engineering IIT Kanpur India CentraleSupélec France Computer Vision Center Universitat Autonoma de Barcelona Spain Politecnico di Milano Italy CIFAR

Natural image modeling is a landmark challenge of unsupervised learning. Variational Autoencoders (VAEs) learn a useful latent representation and model global structure well but have difficulty capturing small details. PixelCNN models details very well, but lacks a latent code and is difficult to scale for capturing large structures. We present PixelVAE, a VAE model with an autoregressive decoder based on PixelCNN. Our model requires very few expensive autoregressive layers compared to PixelCNN and learns latent codes that are more compressed than a standard VAE while still capturing most non-trivial structure. Finally, we extend our model to a hierarchy of latent variables at different scales. Our model achieves state-of-the-art performance on binarized MNIST, competitive performance on 64 × 64 ImageNet, and high-quality samples on the LSUN bedrooms dataset. © ICLR 2019 - Conference Track Proceedings. All rights reserved.

关键词：

Towards an automatic turing test: learning to evaluate dialogue responses

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Lowe, Ryan Noseworthy, Michael Serban, Iulian V. Gontier, Nicolas A. Bengio, Yoshua Pineau, Joelle Reasoning and Learning Lab School of Computer Science McGill University Montreal Institute for Learning Algorithms Université de Montréal Cifar Senior Fellow

Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. Unfortunately, existing automatic evaluation metrics are biased and correlate very poorly with human judgements of response quality. Yet having an accurate automatic evaluation procedure is crucial for dialogue research, as it allows rapid prototyping and testing of new models with fewer expensive human evaluations. In response to this challenge, we formulate automatic dialogue evaluation as a learning problem. We present an evaluation model (ADEM) that learns to predict human-like scores to input responses, using a new dataset of human response scores. We show that the ADEM model's predictions correlate significantly, and at a level much higher than word-overlap metrics such as BLEU, with human judgements at both the utterance and systemlevel. We also show that ADEM can generalize to evaluating dialogue models unseen during training, an important step for automatic dialogue evaluation. Copyright © 2017, The Authors. All rights reserved.

关键词： Quality control

Visualizing the consequences of climate change using cycle-consistent adversarial networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Schmidt, Victor Luccioni, Alexandra Karthik Mukkavilli, S. Sankaran, Kris Bengio, Yoshua Chayes, Jennifer Balasooriya, Narmada Montreal Institute for Learning Algorithms Montreal Canada Microsoft Research New England CambridgeMA United States ConscientAI Labs Colombo Sri Lanka

We present a project that aims to generate images that depict accurate, vivid, and personalized outcomes of climate change using Cycle-Consistent Adversarial Networks (CycleGANs). By training our CycleGAN model on street-view images of houses before and after extreme weather events (e.g. floods, forest fires, etc.), we learn a mapping that can then be applied to images of locations that have not yet experienced these events. This visual transformation is paired with climate model predictions to assess likelihood and type of climate-related events in the long term (50 years) in order to bring the future closer in the viewer's mind. The eventual goal of our project is to enable individuals to make more informed choices about their climate future by creating a more visceral understanding of the effects of climate change, while maintaining scientific credibility by drawing on climate model projections. Copyright © 2019, The Authors. All rights reserved.

关键词： Climate change

DeepInf: Social Influence Prediction with Deep learning

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Qiu, Jiezhong Tang, Jian Ma, Hao Dong, Yuxiao Wang, Kuansan Tang, Jie Department of Computer Science and Technology Tsinghua University Microsoft Research Redmond United States HEC Montreal Canada Montreal Institute for Learning Algorithms Canada

Social and information networking activities such as on Facebook, Twitter, WeChat, and Weibo have become an indispensable part of our everyday life, where we can easily access friends’ behaviors and are in turn influenced by them. Consequently, an effective social influence prediction for each user is critical for a variety of applications such as online recommendation and advertising. Conventional social influence prediction approaches typically design various hand-crafted rules to extract user- and network-specific features. However, their effectiveness heavily relies on the knowledge of domain experts. As a result, it is usually difficult to generalize them into different domains. Inspired by the recent success of deep neural networks in a wide range of computing applications, we design an end-to-end framework, DeepInf1, to learn users’ latent feature representation for predicting social influence. In general, DeepInf takes a user’s local network as the input to a graph neural network for learning her latent social representation. We design strategies to incorporate both network structures and user-specific features into convolutional neural and attention networks. Extensive experiments on Open Academic Graph, Twitter, Weibo, and Digg, representing different types of social and information networks, demonstrate that the proposed end-to-end model, DeepInf, significantly outperforms traditional feature engineering-based approaches, suggesting the effectiveness of representation learning for social applications. Copyright © 2018, The Authors. All rights reserved.

关键词： Convolution

Unsupervised adversarial domain adaptation for acoustic scene classification

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Gharib, Shayan Drossos, Konstantinos Çakir, Emre Serdyuk, Dmitriy Virtanen, Tuomas Audio Research Group Lab. of Signal Processing Tampere University of Technology Tampere Finland Montreal Institute for Learning Algorithms MontrealQC Canada

A general problem in acoustic scene classification task is the mismatched conditions between training and testing data, which significantly reduces the performance of the developed methods on classification accuracy. As a countermeasure, we present the first method of unsupervised adversarial domain adaptation for acoustic scene classification. We employ a model pre-trained on data from one set of conditions and by using data from other set of conditions, we adapt the model in order that its output cannot be used for classifying the set of conditions that input data belong to. We use a freely available dataset from the DCASE 2018 challenge Task 1, subtask B, that contains data from mismatched recording devices. We consider the scenario where the annotations are available for the data recorded from one device, but not for the rest. Our results show that with our model agnostic method we can achieve ∼ 10% increase at the accuracy on an unseen and unlabeled dataset, while keeping almost the same performance on the labeled dataset. Copyright © 2018, The Authors. All rights reserved.

关键词： Machine learning

Dendritic error backpropagation in deep cortical microcircuits

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Sacramento, João Costa, Rui Ponte Bengio, Yoshua Senn, Walter Department of Physiology University of Bern Switzerland Montreal Institute for Learning Algorithms Université de Montréal Quebec Canada

Animal behaviour depends on learning to associate sensory stimuli with the desired motor command. Understanding how the brain orchestrates the necessary synaptic modifications across different brain areas has remained a longstanding puzzle. Here, we introduce a multi-area neuronal network model in which synaptic plasticity continuously adapts the network towards a global desired output. In this model synaptic learning is driven by a local dendritic prediction error that arises from a failure to predict the top-down input given the bottom-up activities. Such errors occur at apical dendrites of pyramidal neurons where both long-range excitatory feedback and local inhibitory predictions are integrated. When local inhibition fails to match excitatory feedback an error occurs which triggers plasticity at bottom-up synapses at basal dendrites of the same pyramidal neurons. We demonstrate the learning capabilities of the model in a number of tasks and show that it approximates the classical error backpropagation algorithm. Finally, complementing this cortical circuit with a disinhibitory mechanism enables attention-like stimulus denoising and generation. Our framework makes several experimental predictions on the function of dendritic integration and cortical microcircuits, is consistent with recent observations of cross-area learning, and suggests a biological implementation of deep learning. Copyright © 2017, The Authors. All rights reserved.

关键词： Forecasting

learning normalized inputs for iterative estimation in medical image segmentation

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Drozdzal, Michal Chartrand, Gabriel Vorontsov, Eugene Jorio, Lisa Di Tang, An Romero, Adriana Bengio, Yoshua Pal, Chris Kadoury, Samuel Ecole Polytechnique de Montréal Montréal Montreal Institute for Learning Algorithms and Imagia Inc. Montréal Université de Montréal Montréal and Imagia Inc. Montréal Imagia Inc. Montréal CHUM Research Center Montréal Ecole Polytechnique de Montréal Montréal Montreal Institute for Learning Algorithms Montreal Institute for Learning Algorithms Ecole Polytechnique de Montréal Montréal

In this paper, we introduce a simple, yet powerful pipeline for medical image segmentation that combines Fully Convolutional Networks (FCNs) with Fully Convolutional Residual Networks (FC-ResNets). We propose and examine a design that takes particular advantage of recent advances in the understanding of both Convolutional Neural Networks as well as ResNets. Our approach focuses upon the importance of a trainable pre-processing when using FC-ResNets and we show that a low-capacity FCN model can serve as a pre-processor to normalize medical input data. In our image segmentation pipeline, we use FCNs to obtain normalized images, which are then iteratively refined by means of a FC-ResNet to generate a segmentation prediction. As in other fully convolutional approaches, our pipeline can be used off-the-shelf on different image modalities. We show that using this pipeline, we exhibit state-of-the-art performance on the challenging Electron Microscopy benchmark, when compared to other 2D methods. We improve segmentation results on CT images of liver lesions, when contrasting with standard FCN methods. Moreover, when applying our 2D pipeline on a challenging 3D MRI prostate segmentation challenge we reach results that are competitive even when compared to 3D methods. The obtained results illustrate the strong potential and versatility of the pipeline by achieving highly accurate results on multi-modality images from different anatomical regions and organs. Copyright © 2017, The Authors. All rights reserved.

关键词： Pipelines