Distributional shift

Distributional shift is the mismatch between training and deployment data that is ubiquitous in the real-world. Studying this phenomenon can enable safer and more reliable ML systems.

Area 3. Distributional Shift.svg

Posts

Publications

  • Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks

    Machine translationNatural language processing Tabular dataDistributional shiftUncertainty estimation
    Andrey Malinin
    Neil Band
    Yarin Gal
    Mark J. F. Gales
    Alexander Ganshin
    German Chesnokov
    Alexey Noskov
    Andrey Ploskonosov
    Liudmila Prokhorenkova
    Ivan Provilkov
    Vatsal Raina
    Vyas Raina
    Denis Roginskiy
    Mariya Shmatova
    Panos Tigas
    Boris Yangel
    NeurIPS Benchmarks,
    2021

    Published at NeurIPS Datasets and Benchmarks Track.

    There has been significant research done on developing methods for improving robustness to distributional shift and uncertainty estimation. In contrast, only limited work has examined developing standard datasets and benchmarks for assessing these approaches. Additionally, most work on uncertainty estimation and robustness has developed new techniques based on small-scale regression or image classification tasks. However, many tasks of practical interest have different modalities, such as tabular data, audio, text, or sensor data, which offer significant challenges involving regression and discrete or continuous structured prediction. Thus, given the current state of the field, a standardized large-scale dataset of tasks across a range of modalities affected by distributional shifts is necessary. This will enable researchers to meaningfully evaluate the plethora of recently developed uncertainty quantification methods, as well as assessment criteria and state-of-the-art baselines. In this work, we propose the \emph{Shifts Dataset} for evaluation of uncertainty estimates and robustness to distributional shift. The dataset, which has been collected from industrial sources and services, is composed of three tasks, with each corresponding to a particular data modality: tabular weather prediction, machine translation, and self-driving car (SDC) vehicle motion prediction. All of these data modalities and tasks are affected by real, ‘in-the-wild’ distributional shifts and pose interesting challenges with respect to uncertainty estimation. In this work we provide a description of the dataset and baseline results for all tasks.

  • Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets

    Natural language processing Machine translationSpeech processingComputer visionOptimizationDistributional shiftUncertainty estimation Probabilistic machine learning
    Max Ryabinin
    Andrey Malinin
    Mark Gales
    NeurIPS,
    2021

    Ensembles of machine learning models yield improved system performance as well as robust and interpretable uncertainty estimates; however, their inference costs can be prohibitively high. Ensemble Distribution Distillation (EnD^2) is an approach that allows a single model to efficiently capture both the predictive performance and uncertainty estimates of an ensemble. For classification, this is achieved by training a Dirichlet distribution over the ensemble members' output distributions via the maximum likelihood criterion. Although theoretically principled, this work shows that the criterion exhibits poor convergence when applied to large-scale tasks where the number of classes is very high. Specifically, we show that for the Dirichlet log-likelihood criterion classes with low probability induce larger gradients than high-probability classes. Hence during training the model focuses on the distribution of the ensemble tail-class probabilities rather than the probability of the correct and closely related classes. We propose a new training objective which minimizes the reverse KL-divergence to a Proxy-Dirichlet target derived from the ensemble. This loss resolves the gradient issues of EnD^2, as we demonstrate both theoretically and empirically on the ImageNet, LibriSpeech, and WMT17 En-De datasets containing 1000, 5000, and 40,000 classes, respectively.

  • Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance

    Natural language processing Distributional shiftUncertainty estimation Bayesian methods
    Carel van Niekerk
    Andrey Malinin
    Christian Geishauser
    Michael Heck
    Hsien-chin Lin
    Nurul Lubis
    Shutong Feng
    Milica Gašic
    EMNLP,
    2021

    The ability to identify and resolve uncertainty is crucial for the robustness of a dialogue system. Indeed, this has been confirmed empirically on systems that utilise Bayesian approaches to dialogue belief tracking. However, such systems consider only confidence estimates and have difficulty scaling to more complex settings. Neural dialogue systems, on the other hand, rarely take uncertainties into account. They are therefore overconfident in their decisions and less robust. Moreover, the performance of the tracking task is often evaluated in isolation, without consideration of its effect on the downstream policy optimisation. We propose the use of different uncertainty measures in neural belief tracking. The effects of these measures on the downstream task of policy optimisation are evaluated by adding selected measures of uncertainty to the feature space of the policy and training policies through interaction with a user simulator. Both human and simulated user results show that incorporating these measures leads to improvements both of the performance and of the robustness of the downstream dialogue policy. This highlights the importance of developing neural dialogue belief trackers that take uncertainty into account.