无监督元学习表示学习

2019 年 1 月 4 日 CreateAMind
无监督元学习表示学习


Learning Unsupervised Learning Rules 


https://github.com/tensorflow/models/tree/master/research/learning_unsupervised_learning



Abstract

A major goal of unsupervised learning is to discover data representations that are useful for subsequent tasks, without access to supervised labels during training. Typically, this goal is approached by minimizing a surrogate objective, such as the negative log likelihood of a generative model, with the hope that representations useful for subsequent tasks will arise incidentally. In this work, we propose instead to directly target a later desired task by meta-learning an unsupervised learning rule, which leads to representations useful for that task. Here, our desired task (meta-objective) is the performance of the representation on semi-supervised classification, and we meta-learn an algorithm – an unsupervised weight update rule – that produces representations that perform well under this meta-objective. Additionally, we constrain our unsupervised update rule to a be a biologically- motivated, neuron-local function, which enables it to generalize to novel neural network architectures. We show that the meta-learned update rule produces useful features and sometimes outperforms existing unsupervised learning techniques. We further show that the meta-learned unsupervised update rule generalizes to train networks with different widths, depths, and nonlinearities. It also generalizes to train on data with randomly permuted input dimensions and even generalizes from image datasets to a text task.


1

 One explanation for this failure is that unsupervised representation learning algorithms are typically mismatched to the target task. Ideally, learned representations should linearly expose high level attributes of data (e.g. object identity) and perform well in semi-supervised settings. Many current unsupervised objectives, however, optimize for objectives such as log-likelihood of a generative model or reconstruction error and produce useful representations only as a side effect.

Unsupervised representation learning seems uniquely suited for meta-learning [1, 2]. Unlike most tasks where meta-learning is applied, unsupervised learning does not define an explicit objective, which makes it impossible to phrase the task as a standard optimization problem. It is possible, however, to directly express a meta-objective that captures the quality of representations produced by an unsupervised update rule by evaluating the usefulness of the representation for candidate tasks, e.g. semi-supervised classification. In this work, we propose to meta-learn an unsupervised update rule by meta-training on a meta-objective that directly optimizes the utility of the unsupervised representation.Unlike hand-designed unsupervised learning rules, this meta-objective directly targets the usefulness of a representation generated from unlabeled data for later supervised tasks.

By recasting unsupervised representation learning as meta-learning, we treat the creation of the unsupervised update rule as a transfer learning problem. Instead of learning transferable features, we learn a transferable learning rule which does not require access to labels and generalizes across both data domains and neural network architectures. 


2.1

In contrast to our work, each method imposes a manually defined training algorithm or loss function to optimize whereas we learn the algorithm that creates useful representations as determined by a meta-objective.



To our knowledge, we are the first meta-learning approach to tackle the problem of unsupervised representation learning

we are the first representation meta-learning approach to generalize across input data modalities as well as datasets, the first to generalize across permutation of the input dimensions, and the first to generalize across neural network architectures (e.g. layer width, network depth, activation function).



3

We wish for our update rule to generalize across architectures with different widths, depths, or even network topologies. To achieve this, we design our update rule to be neuron-local, so that updates are a function of pre- and post- synaptic neurons in the base model, and are defined for any base model architecture. This has the added benefit that it makes the weight updates more similar to synaptic updates in biological neurons, which depend almost exclusively on the pre- and post-synaptic neurons for each synapse [48]. 



4

We implement the above models in distributed Tensorflow [55]. Training uses 512 workers, each of which performs a sequence of partial unrolls of the inner loop UnsupervisedUpdate, and computes gradients of the meta-objective asynchronously. Training takes 8 days, and consists of 200 thousand updates to θ with minibatch size 256. Additional details can be found in Appendix C. 


但是第一天下降很快的。










感觉论文有些难。

登录查看更多
20

相关内容

Meta Learning,元学习,也叫 Learning to Learn(学会学习)。是继Reinforcement Learning(增强学习)之后又一个重要的研究分支。

知识荟萃

精品入门和进阶教程、论文和代码整理等

更多

查看相关VIP内容、论文、资讯等

Pre-training text representations has recently been shown to significantly improve the state-of-the-art in many natural language processing tasks. The central goal of pre-training is to learn text representations that are useful for subsequent tasks. However, existing approaches are optimized by minimizing a proxy objective, such as the negative log likelihood of language modeling. In this work, we introduce a learning algorithm which directly optimizes model's ability to learn text representations for effective learning of downstream tasks. We show that there is an intrinsic connection between multi-task pre-training and model-agnostic meta-learning with a sequence of meta-train steps. The standard multi-task learning objective adopted in BERT is a special case of our learning algorithm where the depth of meta-train is zero. We study the problem in two settings: unsupervised pre-training and supervised pre-training with different pre-training objects to verify the generality of our approach.Experimental results show that our algorithm brings improvements and learns better initializations for a variety of downstream tasks.

0
9
下载
预览

Recent advances in Graph Convolutional Neural Networks (GCNNs) have shown their efficiency for non-Euclidean data on graphs, which often require a large amount of labeled data with high cost. It it thus critical to learn graph feature representations in an unsupervised manner in practice. To this end, we propose a novel unsupervised learning of Graph Transformation Equivariant Representations (GraphTER), aiming to capture intrinsic patterns of graph structure under both global and local transformations. Specifically, we allow to sample different groups of nodes from a graph and then transform them node-wise isotropically or anisotropically. Then, we self-train a representation encoder to capture the graph structures by reconstructing these node-wise transformations from the feature representations of the original and transformed graphs. In experiments, we apply the learned GraphTER to graphs of 3D point cloud data, and results on point cloud segmentation/classification show that GraphTER significantly outperforms state-of-the-art unsupervised approaches and pushes greatly closer towards the upper bound set by the fully supervised counterparts.

0
6
下载
预览

Generalization, i.e., the ability to adapt to novel scenarios, is the hallmark of human intelligence. While we have systems that excel at recognizing objects, cleaning floors, playing complex games and occasionally beating humans, they are incredibly specific in that they only perform the tasks they are trained for and are miserable at generalization. Could optimizing towards fixed external goals be hindering the generalization instead of aiding it? In this thesis, we present our initial efforts toward endowing artificial agents with a human-like ability to generalize in diverse scenarios. The main insight is to first allow the agent to learn general-purpose skills in a completely self-supervised manner, without optimizing for any external goal.

To be able to learn on its own, the claim is that an artificial agent must be embodied in the world, develop an understanding of its sensory input (e.g., image stream) and simultaneously learn to map this understanding to its motor outputs (e.g., torques) in an unsupervised manner. All these considerations lead to two fundamental questions: how to learn rich representations of the world similar to what humans learn?; and how to re-use such a representation of past knowledge to incrementally adapt and learn more about the world similar to how humans do? We believe prediction is the key to this answer. We propose generic mechanisms that employ prediction as a supervisory signal in allowing the agents to learn sensory representations as well as motor control. These two abilities equip an embodied agent with a basic set of general-purpose skills which are then later repurposed to perform complex tasks.

We discuss how this framework can be instantiated to develop curiosity-driven agents (virtual as well as real) that can learn to play games, learn to walk, and learn to perform real-world object manipulation without any rewards or supervision. These self-supervised robotic agents, after exploring the environment, can generalize to find their way in office environments, tie knots using rope, rearrange object configuration, and compose their skills in a modular fashion.

成为VIP会员查看完整内容
Learning to Generalize via Self-Supervised Prediction.pdf
0
31

Learning general representations of text is a fundamental problem for many natural language understanding (NLU) tasks. Previously, researchers have proposed to use language model pre-training and multi-task learning to learn robust representations. However, these methods can achieve sub-optimal performance in low-resource scenarios. Inspired by the recent success of optimization-based meta-learning algorithms, in this paper, we explore the model-agnostic meta-learning algorithm (MAML) and its variants for low-resource NLU tasks. We validate our methods on the GLUE benchmark and show that our proposed models can outperform several strong baselines. We further empirically demonstrate that the learned representations can be adapted to new tasks efficiently and effectively.

0
5
下载
预览

This work tackles the problem of semi-supervised learning of image classifiers. Our main insight is that the field of semi-supervised learning can benefit from the quickly advancing field of self-supervised visual representation learning. Unifying these two approaches, we propose the framework of self-supervised semi-supervised learning ($S^4L$) and use it to derive two novel semi-supervised image classification methods. We demonstrate the effectiveness of these methods in comparison to both carefully tuned baselines, and existing semi-supervised learning methods. We then show that $S^4L$ and existing semi-supervised methods can be jointly trained, yielding a new state-of-the-art result on semi-supervised ILSVRC-2012 with 10% of labels.

0
4
下载
预览

The goal of few-shot learning is to learn a classifier that generalizes well even when trained with a limited number of training instances per class. The recently introduced meta-learning approaches tackle this problem by learning a generic classifier across a large number of multiclass classification tasks and generalizing the model to a new task. Yet, even with such meta-learning, the low-data problem in the novel classification task still remains. In this paper, we propose Transductive Propagation Network (TPN), a novel meta-learning framework for transductive inference that classifies the entire test set at once to alleviate the low-data problem. Specifically, we propose to learn to propagate labels from labeled instances to unlabeled test instances, by learning a graph construction module that exploits the manifold structure in the data. TPN jointly learns both the parameters of feature embedding and the graph construction in an end-to-end manner. We validate TPN on multiple benchmark datasets, on which it largely outperforms existing few-shot learning approaches and achieves the state-of-the-art results.

0
18
下载
预览

The key issue of few-shot learning is learning to generalize. In this paper, we propose a large margin principle to improve the generalization capacity of metric based methods for few-shot learning. To realize it, we develop a unified framework to learn a more discriminative metric space by augmenting the softmax classification loss function with a large margin distance loss function for training. Extensive experiments on two state-of-the-art few-shot learning models, graph neural networks and prototypical networks, show that our method can improve the performance of existing models substantially with very little computational overhead, demonstrating the effectiveness of the large margin principle and the potential of our method.

0
8
下载
预览

A major goal of unsupervised learning is to discover data representations that are useful for subsequent tasks, without access to supervised labels during training. Typically, this goal is approached by minimizing a surrogate objective, such as the negative log likelihood of a generative model, with the hope that representations useful for subsequent tasks will arise incidentally. In this work, we propose instead to directly target a later desired task by meta-learning an unsupervised learning rule, which leads to representations useful for that task. Here, our desired task (meta-objective) is the performance of the representation on semi-supervised classification, and we meta-learn an algorithm -- an unsupervised weight update rule -- that produces representations that perform well under this meta-objective. Additionally, we constrain our unsupervised update rule to a be a biologically-motivated, neuron-local function, which enables it to generalize to novel neural network architectures. We show that the meta-learned update rule produces useful features and sometimes outperforms existing unsupervised learning techniques. We further show that the meta-learned unsupervised update rule generalizes to train networks with different widths, depths, and nonlinearities. It also generalizes to train on data with randomly permuted input dimensions and even generalizes from image datasets to a text task.

0
5
下载
预览
小贴士
相关VIP内容
专知会员服务
54+阅读 · 2020年6月19日
专知会员服务
108+阅读 · 2020年5月29日
因果图,Causal Graphs,52页ppt
专知会员服务
127+阅读 · 2020年4月19日
专知会员服务
35+阅读 · 2020年3月19日
专知会员服务
85+阅读 · 2020年2月1日
专知会员服务
46+阅读 · 2019年12月22日
Uber AI NeurIPS 2019《元学习meta-learning》教程,附92页PPT下载
专知会员服务
93+阅读 · 2019年12月13日
强化学习最新教程,17页pdf
专知会员服务
58+阅读 · 2019年10月11日
相关论文
Shangwen Lv,Yuechen Wang,Daya Guo,Duyu Tang,Nan Duan,Fuqing Zhu,Ming Gong,Linjun Shou,Ryan Ma,Daxin Jiang,Guihong Cao,Ming Zhou,Songlin Hu
9+阅读 · 2020年4月12日
Continual Unsupervised Representation Learning
Dushyant Rao,Francesco Visin,Andrei A. Rusu,Yee Whye Teh,Razvan Pascanu,Raia Hadsell
5+阅读 · 2019年10月31日
Zi-Yi Dou,Keyi Yu,Antonios Anastasopoulos
5+阅读 · 2019年8月27日
Xiaohua Zhai,Avital Oliver,Alexander Kolesnikov,Lucas Beyer
4+阅读 · 2019年5月9日
Yanbin Liu,Juho Lee,Minseop Park,Saehoon Kim,Eunho Yang,Sungju Hwang,Yi Yang
18+阅读 · 2018年12月25日
Yong Wang,Xiao-Ming Wu,Qimai Li,Jiatao Gu,Wangmeng Xiang,Lei Zhang,Victor O. K. Li
8+阅读 · 2018年7月8日
Abhishek Gupta,Benjamin Eysenbach,Chelsea Finn,Sergey Levine
6+阅读 · 2018年6月12日
Luke Metz,Niru Maheswaranathan,Brian Cheung,Jascha Sohl-Dickstein
5+阅读 · 2018年5月23日
Yannis Papanikolaou,Grigorios Tsoumakas
3+阅读 · 2017年9月16日
Top