The effects of negative adaptation in Model-Agnostic Meta-Learning
Tristan Deleu
The capacity of meta-learning algorithms to quickly adapt to a variety of tasks, including ones they did not experience during meta-training… (see more), has been a key factor in the recent success of these methods on few-shot learning problems. This particular advantage of using meta-learning over standard supervised or reinforcement learning is only well founded under the assumption that the adaptation phase does improve the performance of our model on the task of interest. However, in the classical framework of meta-learning, this constraint is only mildly enforced, if not at all, and we only see an improvement on average over a distribution of tasks. In this paper, we show that the adaptation in an algorithm like MAML can significantly decrease the performance of an agent in a meta-reinforcement learning setting, even on a range of meta-training tasks.
Learning Typed Entailment Graphs with Global Soft Constraints
Mohammad Javad Hosseini
Nathanael Chambers
Xavier R. Holt
Shay B. Cohen
Mark Johnson
Mark Steedman
This paper presents a new method for learning typed entailment graphs from text. We extract predicate-argument structures from multiple-sour… (see more)ce news corpora, and compute local distributional similarity scores to learn entailments between predicates with typed arguments (e.g., person contracted disease). Previous work has used transitivity constraints to improve local decisions, but these constraints are intractable on large graphs. We instead propose a scalable method that learns globally consistent similarity scores based on new soft constraints that consider both the structures across typed entailment graphs and inside each graph. Learning takes only a few hours to run over 100K predicates and our results show large improvements over local similarity scores on two entailment data sets. We further show improvements over paraphrases and entailments from the Paraphrase Database, and prior state-of-the-art entailment graphs. We show that the entailment graphs improve performance in a downstream task.
Contextual Bandits for Adapting Treatment in a Mouse Model of de Novo Carcinogenesis
Charis Achilleos
Demetris C Iacovides
Katerina Strati
Georgios D. Mitsis
In this work, we present a specific case study where we aim to design effective treatment allocation strategies and validate these using a m… (see more)ouse model of skin cancer. Collecting data for modelling treatments effectiveness on animal models is an expensive and time consuming process. Moreover, acquiring this information during the full range of disease stages is hard to achieve with a conventional random treatment allocation procedure, as poor treatments cause deterioration of subject health. We therefore aim to design an adaptive allocation strategy to improve the efficiency of data collection by allocating more samples for exploring promising treatments. We cast this application as a contextual bandit problem and introduce a simple and practical algorithm for exploration-exploitation in this framework. The work builds on a recent class of approaches for non-contextual bandits that relies on subsampling to compare treatment options using an equivalent amount of information. On the technical side, we extend the subsampling strategy to the case of bandits with context, by applying subsampling within Gaussian Process regression. On the experimental side, preliminary results using 10 mice with skin tumours suggest that the proposed approach extends by more than 50% the subjects life duration compared with baseline strategies: no treatment, random treatment allocation, and constant chemotherapeutic agent. By slowing the tumour growth rate, the adaptive procedure gathers information about treatment effectiveness on a broader range of tumour volumes, which is crucial for eventually deriving sequential pharmacological treatment strategies for cancer.
Understanding the impact of entropy in policy learning
Zafarali Ahmed
Mohammad Norouzi
Dale Schuurmans
Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with \emph{explorat… (see more)ion} by encouraging the selection of more stochastic policies. In this work, we analyze this claim using new visualizations of the optimization landscape based on randomly perturbing the loss function. We first show that even with access to the exact gradient, policy optimization is difficult due to the geometry of the objective function. Then, we qualitatively show that in some environments, a policy with higher entropy can make the optimization landscape smoother, thereby connecting local optima and enabling the use of larger learning rates. This paper presents new tools for understanding the optimization landscape, shows that policy entropy serves as a regularizer, and highlights the challenge of designing general-purpose policy optimization algorithms.
Environments for Lifelong Reinforcement Learning
To achieve general artificial intelligence, reinforcement learning (RL) agents should learn not only to optimize returns for one specific ta… (see more)sk but also to constantly build more complex skills and scaffold their knowledge about the world, without forgetting what has already been learned. In this paper, we discuss the desired characteristics of environments that can support the training and evaluation of lifelong reinforcement learning agents, review existing environments from this perspective, and propose recommendations for devising suitable environments in the future.
Multi-task Learning over Graph Structures
Pengfei Liu
Jie Fu
Yue Dong
Xipeng Qiu
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 \textbf{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 labeling 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.
Planning in Dynamic Environments with Conditional Autoregressive Models
Johanna Hansen
Kyle Kastner
We demonstrate the use of conditional autoregressive generative models (van den Oord et al., 2016a) over a discrete latent space (van den Oo… (see more)rd et al., 2017b) for forward planning with MCTS. In order to test this method, we introduce a new environment featuring varying difficulty levels, along with moving goals and obstacles. The combination of high-quality frame generation and classical planning approaches nearly matches true environment performance for our task, demonstrating the usefulness of this method for model-based planning in dynamic environments.
Keep Drawing It: Iterative language-based image generation and editing
Alaaeldin El-Nouby
Shikhar Sharma
Hannes Schulz
Layla El Asri
Graham W. Taylor
Conditional text-to-image generation approaches commonly focus on generating a single image in a single step. One practical extension beyond… (see more) one-step generation is an interactive system that generates an image iteratively, conditioned on ongoing linguistic input / feedback. This is significantly more challenging as such a system must understand and keep track of the ongoing context and history. In this work, we present a recurrent image generation model which takes into account both the generated output up to the current step as well as all past instructions for generation. We show that our model is able to generate the background, add new objects, apply simple transformations to existing objects, and correct previous mistakes. We believe our approach is an important step toward interactive generation.
Interpretable Convolutional Filters with SincNet
Deep learning is currently playing a crucial role toward higher levels of artificial intelligence. This paradigm allows neural networks to l… (see more)earn complex and abstract representations, that are progressively obtained by combining simpler ones. Nevertheless, the internal "black-box" representations automatically discovered by current neural architectures often suffer from a lack of interpretability, making of primary interest the study of explainable machine learning techniques. This paper summarizes our recent efforts to develop a more interpretable neural model for directly processing speech from the raw waveform. In particular, we propose SincNet, a novel Convolutional Neural Network (CNN) that encourages the first layer to discover more meaningful filters by exploiting parametrized sinc functions. In contrast to standard CNNs, which learn all the elements of each filter, only low and high cutoff frequencies of band-pass filters are directly learned from data. This inductive bias offers a very compact way to derive a customized filter-bank front-end, that only depends on some parameters with a clear physical meaning. Our experiments, conducted on both speaker and speech recognition, show that the proposed architecture converges faster, performs better, and is more interpretable than standard CNNs.
Harmonic Recomposition using Conditional Autoregressive Modeling
Kyle Kastner
Rithesh Kumar
Tim Cooijmans
We demonstrate a conditional autoregressive pipeline for efficient music recomposition, based on methods presented in van den Oord et al.(20… (see more)17). Recomposition (Casal & Casey, 2010) focuses on reworking existing musical pieces, adhering to structure at a high level while also re-imagining other aspects of the work. This can involve reuse of pre-existing themes or parts of the original piece, while also requiring the flexibility to generate new content at different levels of granularity. Applying the aforementioned modeling pipeline to recomposition, we show diverse and structured generation conditioned on chord sequence annotations.
On Training Recurrent Neural Networks for Lifelong Learning
Shagun Sodhani
Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we stud… (see more)y these challenges in the context of sequential supervised learning with emphasis on recurrent neural networks. To evaluate the models in the lifelong learning setting, we propose a curriculum-based, simple, and intuitive benchmark where the models are trained on tasks with increasing levels of difficulty. To measure the impact of catastrophic forgetting, the model is tested on all the previous tasks as it completes any task. As a step towards developing true lifelong learning systems, we unify Gradient Episodic Memory (a catastrophic forgetting alleviation approach) and Net2Net(a capacity expansion approach). Both these models are proposed in the context of feedforward networks and we evaluate the feasibility of using them for recurrent networks. Evaluation on the proposed benchmark shows that the unified model is more suitable than the constituent models for lifelong learning setting.
Blindfold Baselines for Embodied QA
We explore blindfold (question-only) baselines for Embodied Question Answering. The EmbodiedQA task requires an agent to answer a question b… (see more)y intelligently navigating in a simulated environment, gathering necessary visual information only through first-person vision before finally answering. Consequently, a blindfold baseline which ignores the environment and visual information is a degenerate solution, yet we show through our experiments on the EQAv1 dataset that a simple question-only baseline achieves state-of-the-art results on the EmbodiedQA task in all cases except when the agent is spawned extremely close to the object.