`

Timezone: »

 
Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
Andrey Malinin · Neil Band · Yarin Gal · Mark Gales · Alexander Ganshin · German Chesnokov · Alexey Noskov · Andrey Ploskonosov · Liudmila Prokhorenkova · Ivan Provilkov · Vatsal Raina · Vyas Raina · Denis Roginskiy · Mariya Shmatova · Panagiotis Tigas · Boris Yangel

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.

Author Information

Andrey Malinin (Yandex Research)
Neil Band (University of Oxford)
Yarin Gal (University of Oxford)
Mark Gales (University of Cambridge)
Alexander Ganshin (Yandex)
German Chesnokov (Yandex Self-Driving Group)
Alexey Noskov (Yandex)
Andrey Ploskonosov (Higher School of Economics)
Liudmila Prokhorenkova (Yandex)
Ivan Provilkov (Yandex Research; Moscow Institute of Physics and Technology)
Vatsal Raina (University of Cambridge)
Vyas Raina (University of Cambridge)
Denis Roginskiy
Mariya Shmatova
Panagiotis Tigas (University of Oxford)
Boris Yangel (Yandex)

More from the Same Authors