Luka Kolar

Cedric Renggli, Xiaozhe Yao, Luka Kolar et al.

Transfer learning can be seen as a data- and compute-efficient alternative to training models from scratch. The emergence of rich model repositories, such as TensorFlow Hub, enables practitioners and researchers to unleash the potential of these models across a wide range of downstream tasks. As these repositories keep growing exponentially, efficiently selecting a good model for the task at hand becomes paramount. By carefully comparing various selection and search strategies, we realize that no single method outperforms the others, and hybrid or mixed strategies can be beneficial. Therefore, we propose SHiFT, the first downstream task-aware, flexible, and efficient model search engine for transfer learning. These properties are enabled by a custom query language SHiFT-QL together with a cost-based decision maker, which we empirically validate. Motivated by the iterative nature of machine learning development, we further support efficient incremental executions of our queries, which requires a careful implementation when jointly used with our optimizations.

Cedric Renggli, Luka Rimanic, Luka Kolar et al.

In our experience of working with domain experts who are using today's AutoML systems, a common problem we encountered is what we call "unrealistic expectations" -- when users are facing a very challenging task with a noisy data acquisition process, while being expected to achieve startlingly high accuracy with machine learning (ML). Many of these are predestined to fail from the beginning. In traditional software engineering, this problem is addressed via a feasibility study, an indispensable step before developing any software system. In this paper, we present Snoopy, with the goal of supporting data scientists and machine learning engineers performing a systematic and theoretically founded feasibility study before building ML applications. We approach this problem by estimating the irreducible error of the underlying task, also known as the Bayes error rate (BER), which stems from data quality issues in datasets used to train or evaluate ML model artifacts. We design a practical Bayes error estimator that is compared against baseline feasibility study candidates on 6 datasets (with additional real and synthetic noise of different levels) in computer vision and natural language processing. Furthermore, by including our systematic feasibility study with additional signals into the iterative label cleaning process, we demonstrate in end-to-end experiments how users are able to save substantial labeling time and monetary efforts.

Luka Kolar, Rok Šikonja, Lenart Treven

We present a novel method for inferring ground-truth signal from multiple degraded signals, affected by different amounts of sensor exposure. The algorithm learns a multiplicative degradation effect by performing iterative corrections of two signals solely from the ratio between them. The degradation function d should be continuous, satisfy monotonicity, and d(0) = 1. We use smoothed monotonic regression method, where we easily incorporate the aforementioned criteria to the fitting part. We include theoretical analysis and prove convergence to the ground-truth signal for the noiseless measurement model. Lastly, we present an approach to fuse the noisy corrected signals using Gaussian processes. We use sparse Gaussian processes that can be utilized for a large number of measurements together with a specialized kernel that enables the estimation of noise values of all sensors. The data fusion framework naturally handles data gaps and provides a simple and powerful method for observing the signal trends on multiple timescales(long-term and short-term signal properties). The viability of correction method is evaluated on a synthetic dataset with known ground-truth signal.