We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Catastrophic forgetting of connectionist neural networks is caused by the global sharing of parameters among all training examples. In this … (see more)study, we analyze parameter sharing under the conditional computation framework where the parameters of a neural network are conditioned on each input example. At one extreme, if each input example uses a disjoint set of parameters, there is no sharing of parameters thus no catastrophic forgetting. At the other extreme, if the parameters are the same for every example, it reduces to the conventional neural network. We then introduce a clipped version of maxout networks which lies in the middle, i.e. parameters are shared partially among examples. Based on the parameter sharing analysis, we can locate a limited set of examples that are interfered when learning a new example. We propose to perform rehearsal on this set to prevent forgetting, which is termed as conditional rehearsal. Finally, we demonstrate the effectiveness of the proposed method in an online non-stationary setup, where updates are made after each new example and the distribution of the received example shifts over time.
Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training
William Harvey
Michael Teng
F. Wood
Hard visual attention is a promising approach to reduce the computational burden of modern computer vision methodologies. However, hard atte… (see more)ntion mechanisms can be difficult and slow to train, which is especially costly for applications like neural architecture search where multiple networks must be trained. We introduce a method to amortise the cost of training by generating an extra supervision signal for a subset of the training data. This supervision is in the form of sequences of ‘good’ locations to attend to for each image. We find that the best method to generate supervision sequences comes from framing hard attention for image classification as a Bayesian optimal experimental design (BOED) problem. From this perspective, the optimal locations to attend to are those which provide the greatest expected reduction in the entropy of the classification distribution. We introduce methodology from the BOED literature to approximate this optimal behaviour and generate ‘near-optimal’ supervision sequences. We then present a hard attention network training objective that makes use of these sequences and show that it allows faster training than prior work. We finally demonstrate the utility of faster hard attention training by incorporating supervision sequences in a neural architecture search, resulting in hard attention architectures which can outperform networks with access to the entire image.
We humans seem to have an innate understanding of the asymmetric progression of time, which we use to efficiently and safely perceive and ma… (see more)nipulate our environment. Drawing inspiration from that, we address the problem of learning an arrow of time in a Markov (Decision) Process. We illustrate how a learned arrow of time can capture meaningful information about the environment, which in turn can be used to measure reachability, detect side-effects and to obtain an intrinsic reward signal. We show empirical results on a selection of discrete and continuous environments, and demonstrate for a class of stochastic processes that the learned arrow of time agrees reasonably well with a known notion of an arrow of time given by the celebrated Jordan-Kinderlehrer-Otto result.
Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models i… (see more)n RL has been made by learning models via supervised learning. But traditional model-based approaches lead to `compounding errors' when the model is unrolled step by step. Essentially, the state transitions that the learner predicts (by unrolling the model for multiple steps) and the state transitions that the learner experiences (by acting in the environment) may not be consistent. There is enough evidence that humans build a model of the environment, not only by observing the environment but also by interacting with the environment. Interaction with the environment allows humans to carry out experiments: taking actions that help uncover true causal relationships which can be used for building better dynamics models. Analogously, we would expect such interactions to be helpful for a learning agent while learning to model the environment dynamics. In this paper, we build upon this intuition by using an auxiliary cost function to ensure consistency between what the agent observes (by acting in the real world) and what it imagines (by acting in the `learned' world). We consider several tasks - Mujoco based control tasks and Atari games - and show that the proposed approach helps to train powerful policies and better dynamics models.
Recent advances in variational inference enable the modelling of highly structured joint distributions, but are limited in their capacity to… (see more) scale to the high-dimensional setting of stochastic neural networks. This limitation motivates a need for scalable parameterizations of the noise generation process, in a manner that adequately captures the dependencies among the various parameters. In this work, we address this need and present the Kronecker Flow, a generalization of the Kronecker product to invertible mappings designed for stochastic neural networks. We apply our method to variational Bayesian neural networks on predictive tasks, PAC-Bayes generalization bound estimation, and approximate Thompson sampling in contextual bandits. In all setups, our methods prove to be competitive with existing methods and better than the baselines.
In this note, we study the relationship between the variational gap and the variance of the (log) likelihood ratio. We show that the gap can… (see more) be upper bounded by some form of dispersion measure of the likelihood ratio, which suggests the bias of variational inference can be reduced by making the distribution of the likelihood ratio more concentrated, such as via averaging and variance reduction.
We consider a communication system where multiple unknown channels are available for transmission. Each channel is a channel with state whic… (see more)h evolves in a Markov manner. The transmitter has to select L channels to use and also decide the resources (e.g., power, rate, etc.) to use for each of the selected channels. It observes the state of the channels it uses and receives no feedback on the state of the other channels. We model this problem as a partially observable Markov decision process and obtain a simplified belief state. We show that the optimal resource allocation policy can be identified in closed form. Once the optimal resource allocation policy is fixed, choosing the channel scheduling policy may be viewed as a restless bandit. We present an efficient algorithm to check indexability and compute the Whittle index for each channel. When the model is indexable, the Whittle index policy, which transmits over the L channels with the smallest Whittle indices, is an attractive heuristic policy.
2019-06-01
Canadian Workshop on Information Theory (published)
Neural abstractive summarizers generate summary texts using a language model conditioned on the input source text, and have recently achieve… (see more)d high ROUGE scores on benchmark summarization datasets. We investigate how they achieve this performance with respect to human-written gold-standard abstracts, and whether the systems are able to understand deeper syntactic and semantic structures. We generate a set of contrastive summaries which are perturbed, deficient versions of human-written summaries, and test whether existing neural summarizers score them more highly than the human-written summaries. We analyze their performance on different datasets and find that these systems fail to understand the source text, in a majority of the cases.
2019-06-01
North American Chapter of the Association for Computational Linguistics (published)
Existing controllable text generation systems rely on annotated attributes, which greatly limits their capabilities and applications. In thi… (see more)s work, we make the first successful attempt to use VAEs to achieve controllable text generation without supervision. We do so by decomposing the latent space of the VAE into two parts: one incorporates structural constraints to capture dominant global variations implicitly present in the data, e.g., sentiment or topic; the other is unstructured and is used for the reconstruction of the source sentences. With the enforced structural constraint, the underlying global variations will be discovered and disentangled during the training of the VAE. The structural constraint also provides a natural recipe for mitigating posterior collapse for the structured part, which cannot be fully resolved by the existing techniques. On the task of text style transfer, our unsupervised approach achieves significantly better performance than previous supervised approaches. By showcasing generation with finer-grained control including Cards-Against-Humanity-style topic transitions within a sentence, we demonstrate that our model can perform controlled text generation in a more flexible way than existing methods.
Contributors to open source software (OSS) communities assume diverse roles to take different responsibilities. One major limitation of the … (see more)current OSS tools and platforms is that they provide a uniform user interface regardless of the activities performed by the various types of contributors. This paper serves as a non-trivial first step towards resolving this challenge by demonstrating a methodology and establishing knowledge to understand how the contributors' roles and their dynamics, reflected in the activities contributors perform, are exhibited in OSS communities. Based on an analysis of user action data from 29 GitHub projects, we extracted six activities that distinguished four Active roles and five Supporting roles of OSS contributors, as well as patterns in role changes. Through the lens of the Activity Theory, these findings provided rich design guidelines for OSS tools to support diverse contributor roles.
2019-05-27
2019 IEEE/ACM 12th International Workshop on Cooperative and Human Aspects of Software Engineering (CHASE) (published)
Anomaly detection is of great interest in fields where abnormalities need to be identified and corrected (e.g., medicine and finance). Deep … (see more)learning methods for this task often rely on autoencoder reconstruction error, sometimes in conjunction with other penalties. We show that this approach exhibits intrinsic biases that lead to undesirable results. Reconstruction-based methods can sometimes show low error on simple-to-reconstruct points that are not part of the training data, for example the all black image. Instead, we introduce a new unsupervised Lipschitz anomaly discriminator (LAD) that does not suffer from these biases. Our anomaly discriminator is trained, similar to the discriminator of a GAN, to detect the difference between the training data and corruptions of the training data. We show that this procedure successfully detects unseen anomalies with guarantees on those that have a certain Wasserstein distance from the data or corrupted training set. These additions allow us to show improved performance on MNIST, CIFAR10, and health record data. Further, LAD does not require decoding back to the original data space, which makes anomaly detection possible in domains where it is difficult to define a decoder, such as in irregular graph structured data. Empirically, we show this framework leads to improved performance on image, health record, and graph data.
