All Articles

Hot Papers 2021-01-20

1. Does Continual Learning = Catastrophic Forgetting?

Anh Thai, Stefan Stojanov, Isaac Rehg, James M. Rehg

  • retweets: 241, favorites: 78 (01/21/2021 10:23:52)
  • links: abs | pdf
  • cs.LG | cs.CV

Continual learning is known for suffering from catastrophic forgetting, a phenomenon where earlier learned concepts are forgotten at the expense of more recent samples. In this work, we challenge the assumption that continual learning is inevitably associated with catastrophic forgetting by presenting a set of tasks that surprisingly do not suffer from catastrophic forgetting when learned continually. We attempt to provide an insight into the property of these tasks that make them robust to catastrophic forgetting and the potential of having a proxy representation learning task for continual classification. We further introduce a novel yet simple algorithm, YASS that outperforms state-of-the-art methods in the class-incremental categorization learning task. Finally, we present DyRT, a novel tool for tracking the dynamics of representation learning in continual models. The codebase, dataset and pre-trained models released with this article can be found at https://github.com/ngailapdi/CLRec.

2. ArtEmis: Affective Language for Visual Art

Panos Achlioptas, Maks Ovsjanikov, Kilichbek Haydarov, Mohamed Elhoseiny, Leonidas Guibas

  • retweets: 173, favorites: 73 (01/21/2021 10:23:52)
  • links: abs | pdf
  • cs.CV | cs.CL

We present a novel large-scale dataset and accompanying machine learning models aimed at providing a detailed understanding of the interplay between visual content, its emotional effect, and explanations for the latter in language. In contrast to most existing annotation datasets in computer vision, we focus on the affective experience triggered by visual artworks and ask the annotators to indicate the dominant emotion they feel for a given image and, crucially, to also provide a grounded verbal explanation for their emotion choice. As we demonstrate below, this leads to a rich set of signals for both the objective content and the affective impact of an image, creating associations with abstract concepts (e.g., “freedom” or “love”), or references that go beyond what is directly visible, including visual similes and metaphors, or subjective references to personal experiences. We focus on visual art (e.g., paintings, artistic photographs) as it is a prime example of imagery created to elicit emotional responses from its viewers. Our dataset, termed ArtEmis, contains 439K emotion attributions and explanations from humans, on 81K artworks from WikiArt. Building on this data, we train and demonstrate a series of captioning systems capable of expressing and explaining emotions from visual stimuli. Remarkably, the captions produced by these systems often succeed in reflecting the semantic and abstract content of the image, going well beyond systems trained on existing datasets. The collected dataset and developed methods are available at https://artemisdataset.org.

3. Fitting very flexible models: Linear regression with large numbers of parameters

David W. Hogg, Soledad Villar

There are many uses for linear fitting; the context here is interpolation and denoising of data, as when you have calibration data and you want to fit a smooth, flexible function to those data. Or you want to fit a flexible function to de-trend a time series or normalize a spectrum. In these contexts, investigators often choose a polynomial basis, or a Fourier basis, or wavelets, or something equally general. They also choose an order, or number of basis functions to fit, and (often) some kind of regularization. We discuss how this basis-function fitting is done, with ordinary least squares and extensions thereof. We emphasize that it is often valuable to choose far more parameters than data points, despite folk rules to the contrary: Suitably regularized models with enormous numbers of parameters generalize well and make good predictions for held-out data; over-fitting is not (mainly) a problem of having too many parameters. It is even possible to take the limit of infinite parameters, at which, if the basis and regularization are chosen correctly, the least-squares fit becomes the mean of a Gaussian process. We recommend cross-validation as a good empirical method for model selection (for example, setting the number of parameters and the form of the regularization), and jackknife resampling as a good empirical method for estimating the uncertainties of the predictions made by the model. We also give advice for building stable computational implementations.

4. Paraconsistent Foundations for Quantum Probability

Ben Goertzel

  • retweets: 42, favorites: 41 (01/21/2021 10:23:52)
  • links: abs | pdf
  • cs.AI

It is argued that a fuzzy version of 4-truth-valued paraconsistent logic (with truth values corresponding to True, False, Both and Neither) can be approximately isomorphically mapped into the complex-number algebra of quantum probabilities. I.e., p-bits (paraconsistent bits) can be transformed into close approximations of qubits. The approximation error can be made arbitrarily small, at least in a formal sense, and can be related to the degree of irreducible “evidential error” assumed to plague an observer’s observations. This logical correspondence manifests itself in program space via an approximate mapping between probabilistic and quantum types in programming languages.

5. ES-ENAS: Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning

Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder, Yunhao Tang, Daiyi Peng, Deepali Jain, Wenbo Gao, Aldo Pacchiano, Tamas Sarlos, Yuxiang Yang

We introduce ES-ENAS, a simple neural architecture search (NAS) algorithm for the purpose of reinforcement learning (RL) policy design, by combining Evolutionary Strategies (ES) and Efficient NAS (ENAS) in a highly scalable and intuitive way. Our main insight is noticing that ES is already a distributed blackbox algorithm, and thus we may simply insert a model controller from ENAS into the central aggregator in ES and obtain weight sharing properties for free. By doing so, we bridge the gap from NAS research in supervised learning settings to the reinforcement learning scenario through this relatively simple marriage between two different lines of research, and are one of the first to apply controller-based NAS techniques to RL. We demonstrate the utility of our method by training combinatorial neural network architectures for RL problems in continuous control, via edge pruning and weight sharing. We also incorporate a wide variety of popular techniques from modern NAS literature, including multiobjective optimization and varying controller methods, to showcase their promise in the RL field and discuss possible extensions. We achieve >90% network compression for multiple tasks, which may be special interest in mobile robotics with limited storage and computational resources.

6. Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach

Ashish Sharma, Inna W. Lin, Adam S. Miner, David C. Atkins, Tim Althoff

  • retweets: 32, favorites: 26 (01/21/2021 10:23:52)
  • links: abs | pdf
  • cs.CL | cs.SI

Online peer-to-peer support platforms enable conversations between millions of people who seek and provide mental health support. If successful, web-based mental health conversations could improve access to treatment and reduce the global disease burden. Psychologists have repeatedly demonstrated that empathy, the ability to understand and feel the emotions and experiences of others, is a key component leading to positive outcomes in supportive conversations. However, recent studies have shown that highly empathic conversations are rare in online mental health platforms. In this paper, we work towards improving empathy in online mental health support conversations. We introduce a new task of empathic rewriting which aims to transform low-empathy conversational posts to higher empathy. Learning such transformations is challenging and requires a deep understanding of empathy while maintaining conversation quality through text fluency and specificity to the conversational context. Here we propose PARTNER, a deep reinforcement learning agent that learns to make sentence-level edits to posts in order to increase the expressed level of empathy while maintaining conversation quality. Our RL agent leverages a policy network, based on a transformer language model adapted from GPT-2, which performs the dual task of generating candidate empathic sentences and adding those sentences at appropriate positions. During training, we reward transformations that increase empathy in posts while maintaining text fluency, context specificity and diversity. Through a combination of automatic and human evaluation, we demonstrate that PARTNER successfully generates more empathic, specific, and diverse responses and outperforms NLP methods from related tasks like style transfer and empathic dialogue generation. Our work has direct implications for facilitating empathic conversations on web-based platforms.

7. Disentangled Recurrent Wasserstein Autoencoder

Jun Han, Martin Renqiang Min, Ligong Han, Li Erran Li, Xuan Zhang

  • retweets: 12, favorites: 40 (01/21/2021 10:23:52)
  • links: abs | pdf
  • cs.LG | cs.AI

Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framework. However, only a few works have explored unsupervised disentangled sequential representation learning due to challenges of generating sequential data. In this paper, we propose recurrent Wasserstein Autoencoder (R-WAE), a new framework for generative modeling of sequential data. R-WAE disentangles the representation of an input sequence into static and dynamic factors (i.e., time-invariant and time-varying parts). Our theoretical analysis shows that, R-WAE minimizes an upper bound of a penalized form of the Wasserstein distance between model distribution and sequential data distribution, and simultaneously maximizes the mutual information between input data and different disentangled latent factors, respectively. This is superior to (recurrent) VAE which does not explicitly enforce mutual information maximization between input data and disentangled latent representations. When the number of actions in sequential data is available as weak supervision information, R-WAE is extended to learn a categorical latent representation of actions to improve its disentanglement. Experiments on a variety of datasets show that our models outperform other baselines with the same settings in terms of disentanglement and unconditional video generation both quantitatively and qualitatively.

8. A Unifying Generative Model for Graph Learning Algorithms: Label Propagation, Graph Convolutions, and Combinations

Junteng Jia, Austin R. Benson

  • retweets: 36, favorites: 14 (01/21/2021 10:23:53)
  • links: abs | pdf
  • cs.LG

Semi-supervised learning on graphs is a widely applicable problem in network science and machine learning. Two standard algorithms — label propagation and graph neural networks — both operate by repeatedly passing information along edges, the former by passing labels and the latter by passing node features, modulated by neural networks. These two types of algorithms have largely developed separately, and there is little understanding about the structure of network data that would make one of these approaches work particularly well compared to the other or when the approaches can be meaningfully combined. Here, we develop a Markov random field model for the data generation process of node attributes, based on correlations of attributes on and between vertices, that motivates and unifies these algorithmic approaches. We show that label propagation, a linearized graph convolutional network, and their combination can all be derived as conditional expectations under our model, when conditioning on different attributes. In addition, the data model highlights deficiencies in existing graph neural networks (while producing new algorithmic solutions), serves as a rigorous statistical framework for understanding graph learning issues such as over-smoothing, creates a testbed for evaluating inductive learning performance, and provides a way to sample graphs attributes that resemble empirical data. We also find that a new algorithm derived from our data generation model, which we call a Linear Graph Convolution, performs extremely well in practice on empirical data, and provide theoretical justification for why this is the case.

Published 21 Jan 2021

ML Lead at Beatrust. (https://beatrust.com)Tatsuya Shirakawa on Twitter