Publications

A principled approach for generating adversarial images under non-smooth dissimilarity metrics

Aram-Alexandre Pooladian

Chris J. Finlay

Tim Hoheisel

Adam M. Oberman

Deep neural networks perform well on real world data but are prone to adversarial perturbations: small changes in the input easily lead to m… (see more)isclassification. In this work, we propose an attack methodology not only for cases where the perturbations are measured by

2019-08-05

ArXiv (preprint)

An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation

Vincent Michalski

Vikram Voleti

Samira Ebrahimi Kahou

Anthony Ortiz

Pascal Vincent

Chris Pal

Batch normalization has been widely used to improve optimization in deep neural networks. While the uncertainty in batch statistics can act … (see more)as a regularizer, using these dataset statistics specific to the training set impairs generalization in certain tasks. Recently, alternative methods for normalizing feature activations in neural networks have been proposed. Among them, group normalization has been shown to yield similar, in some domains even superior performance to batch normalization. All these methods utilize a learned affine transformation after the normalization operation to increase representational power. Methods used in conditional computation define the parameters of these transformations as learnable functions of conditioning information. In this work, we study whether and where the conditional formulation of group normalization can improve generalization compared to conditional batch normalization. We evaluate performances on the tasks of visual question answering, few-shot learning, and conditional image generation.

2019-07-31

ArXiv (preprint)

On the impressive performance of randomly weighted encoders in summarization tasks

Jonathan Pilault

Jaehong Park

Chris Pal

In this work, we investigate the performance of untrained randomly initialized encoders in a general class of sequence to sequence models an… (see more)d compare their performance with that of fully-trained encoders on the task of abstractive summarization. We hypothesize that random projections of an input text have enough representational power to encode the hierarchical structure of sentences and semantics of documents. Using a trained decoder to produce abstractive text summaries, we empirically demonstrate that architectures with untrained randomly initialized encoders perform competitively with respect to the equivalent architectures with fully-trained encoders. We further find that the capacity of the encoder not only improves overall model generalization but also closes the performance gap between untrained randomly initialized and full-trained encoders. To our knowledge, it is the first time that general sequence to sequence models with attention are assessed for trained and randomly projected representations on abstractive summarization.

2019-07-28

ArXiv (preprint)

Combined Reinforcement Learning via Abstract Representations

Vincent Francois-Lavet

Yoshua Bengio

Joelle Pineau

In the quest for efficient and robust reinforcement learning methods, both model-free and model-based approaches offer advantages. In this p… (see more)aper we propose a new way of explicitly bridging both approaches via a shared low-dimensional learned encoding of the environment, meant to capture summarizing abstractions. We show that the modularity brought by this approach leads to good generalization while being computationally efficient, with planning happening in a smaller latent state space. In addition, this approach recovers a sufficient low-dimensional representation of the environment, which opens up new strategies for interpretable AI, exploration and transfer learning.

2019-07-17

Proceedings of the AAAI Conference on Artificial Intelligence (published)

A Comparative Analysis of Expected and Distributional Reinforcement Learning

Clare Lyle

Pablo Samuel Castro

Marc Gendron-Bellemare

Since their introduction a year ago, distributional approaches to reinforcement learning (distributional RL) have produced strong results re… (see more)lative to the standard approach which models expected values (expected RL). However, aside from convergence guarantees, there have been few theoretical results investigating the reasons behind the improvements distributional RL provides. In this paper we begin the investigation into this fundamental question by analyzing the differences in the tabular, linear approximation, and non-linear approximation settings. We prove that in many realizations of the tabular and linear approximation settings, distributional RL behaves exactly the same as expected RL. In cases where the two methods behave differently, distributional RL can in fact hurt performance when it does not induce identical behaviour. We then continue with an empirical analysis comparing distributional and expected RL methods in control settings with non-linear approximators to tease apart where the improvements from distributional RL methods are coming from.

2019-07-17

Proceedings of the AAAI Conference on Artificial Intelligence (published)

Contextualized Non-local Neural Networks for Sequence Learning

Pengfei Liu

Shuaichen Chang

Xuanjing Huang

Jian Tang

Jackie Cheung

Recently, a large number of neural mechanisms and models have been proposed for sequence learning, of which selfattention, as exemplified by… (see more) the Transformer model, and graph neural networks (GNNs) have attracted much attention. In this paper, we propose an approach that combines and draws on the complementary strengths of these two methods. Specifically, we propose contextualized non-local neural networks (CN3), which can both dynamically construct a task-specific structure of a sentence and leverage rich local dependencies within a particular neighbourhood.Experimental results on ten NLP tasks in text classification, semantic matching, and sequence labelling show that our proposed model outperforms competitive baselines and discovers task-specific dependency structures, thus providing better interpretability to users.

2019-07-17

Proceedings of the AAAI Conference on Artificial Intelligence (published)

Generating Character Descriptions for Automatic Summarization of Fiction

Weiwei Zhang

Jackie Cheung

J. Oren

Summaries of fictional stories allow readers to quickly decide whether or not a story catches their interest. A major challenge in automatic… (see more) summarization of fiction is the lack of standardized evaluation methodology or high-quality datasets for experimentation. In this work, we take a bottomup approach to this problem by assuming that story authors are uniquely qualified to inform such decisions. We collect a dataset of one million fiction stories with accompanying author-written summaries from Wattpad, an online story sharing platform. We identify commonly occurring summary components, of which a description of the main characters is the most frequent, and elicit descriptions of main characters directly from the authors for a sample of the stories. We propose two approaches to generate character descriptions, one based on ranking attributes found in the story text, the other based on classifying into a list of pre-defined attributes. We find that the classification-based approach performs the best in predicting character descriptions.

2019-07-17

Proceedings of the AAAI Conference on Artificial Intelligence (published)

Learning Multi-Task Communication with Message Passing for Sequence Learning

Pengfei Liu

Jie Fu

Yue Dong

Xipeng Qiu

Jackie Cheung

We present two architectures for multi-task learning with neural sequence models. Our approach allows the relationships between different ta… (see more)sks to be learned dynamically, rather than using an ad-hoc pre-defined structure as in previous work. We adopt the idea from message-passing graph neural networks, and propose a general graph multi-task learning framework in which different tasks can communicate with each other in an effective and interpretable way. We conduct extensive experiments in text classification and sequence labelling to evaluate our approach on multi-task learning and transfer learning. The empirical results show that our models not only outperform competitive baselines, but also learn interpretable and transferable patterns across tasks.

2019-07-17

Proceedings of the AAAI Conference on Artificial Intelligence (published)

Learning Options with Interest Functions

Khimya Khetarpal

Learning temporal abstractions which are partial solutions to a task and could be reused for solving other tasks is an ingredient that can h… (see more)elp agents to plan and learn efficiently. In this work, we tackle this problem in the options framework. We aim to autonomously learn options which are specialized in different state space regions by proposing a notion of interest functions, which generalizes initiation sets from the options framework for function approximation. We build on the option-critic framework to derive policy gradient theorems for interest functions, leading to a new interest-option-critic architecture.

2019-07-17

Proceedings of the AAAI Conference on Artificial Intelligence (published)

Leveraging Observations in Bandits: Between Risks and Benefits

Andrei-Stefan Lupu

Audrey Durand

Imitation learning has been widely used to speed up learning in novice agents, by allowing them to leverage existing data from experts. Allo… (see more)wing an agent to be influenced by external observations can benefit to the learning process, but it also puts the agent at risk of following sub-optimal behaviours. In this paper, we study this problem in the context of bandits. More specifically, we consider that an agent (learner) is interacting with a bandit-style decision task, but can also observe a target policy interacting with the same environment. The learner observes only the target’s actions, not the rewards obtained. We introduce a new bandit optimism modifier that uses conditional optimism contingent on the actions of the target in order to guide the agent’s exploration. We analyze the effect of this modification on the well-known Upper Confidence Bound algorithm by proving that it preserves a regret upper-bound of order O(lnT), even in the presence of a very poor target, and we derive the dependency of the expected regret on the general target policy. We provide empirical results showing both great benefits as well as certain limitations inherent to observational learning in the multi-armed bandit setting. Experiments are conducted using targets satisfying theoretical assumptions with high probability, thus narrowing the gap between theory and application.

2019-07-17

Proceedings of the AAAI Conference on Artificial Intelligence (published)

Online Adaptative Curriculum Learning for GANs

Thang Doan

Joao Monteiro

Isabela Albuquerque

Generative Adversarial Networks (GANs) can successfully approximate a probability distribution and produce realistic samples. However, open … (see more)questions such as sufficient convergence conditions and mode collapse still persist. In this paper, we build on existing work in the area by proposing a novel framework for training the generator against an ensemble of discriminator networks, which can be seen as a one-student/multiple-teachers setting. We formalize this problem within the full-information adversarial bandit framework, where we evaluate the capability of an algorithm to select mixtures of discriminators for providing the generator with feedback during learning. To this end, we propose a reward function which reflects the progress made by the generator and dynamically update the mixture weights allocated to each discriminator. We also draw connections between our algorithm and stochastic optimization methods and then show that existing approaches using multiple discriminators in literature can be recovered from our framework. We argue that less expressive discriminators are smoother and have a general coarse grained view of the modes map, which enforces the generator to cover a wide portion of the data distribution support. On the other hand, highly expressive discriminators ensure samples quality. Finally, experimental results show that our approach improves samples quality and diversity over existing baselines by effectively learning a curriculum. These results also support the claim that weaker discriminators have higher entropy improving modes coverage.

2019-07-17

Proceedings of the AAAI Conference on Artificial Intelligence (published)