Timezone: »
Models which can actively seek out the best quality training data hold the promise of more accurate, adaptable, and efficient machine learning. State-of-the-art techniques tend to prefer examples which are the most difficult to classify. While this works well on homogeneous datasets, we find that it can lead to catastrophic failures when performing active learning on multiple distributions which have different degrees of label noise (heteroskedasticity). Most active learning algorithms strongly prefer to draw from the distribution with more noise, even if its examples have no informative structure (such as solid color images). We find that active learning which encourages diversity and model uncertainty in the selected examples can significantly mitigate these failures. We hope these observations are immediately useful to practitioners and can lead to the construction of more realistic and challenging active learning benchmarks.
Author Information
Savya Khosla (Delhi Technological University (Delhi College of Engineering), Dhirubhai Ambani Institute Of Information and Communication Technology)
Alex Lamb (Universite de Montreal)
Jordan Ash (Microsoft Research)
Cyril Zhang (Microsoft Research NYC)
Kenji Kawaguchi (MIT)
More from the Same Authors
-
2021 : Noether Networks: Meta-Learning Useful Conserved Quantities »
Ferran Alet · Dylan Doblar · Allan Zhou · Josh Tenenbaum · Kenji Kawaguchi · Chelsea Finn -
2022 Poster: Discrete Compositional Representations as an Abstraction for Goal Conditioned Reinforcement Learning »
Riashat Islam · Hongyu Zang · Anirudh Goyal · Alex Lamb · Kenji Kawaguchi · Xin Li · Romain Laroche · Yoshua Bengio · Remi Tachet des Combes -
2022 : Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information »
Riashat Islam · Manan Tomar · Alex Lamb · Hongyu Zang · Yonathan Efroni · Dipendra Misra · Aniket Didolkar · Xin Li · Harm Van Seijen · Remi Tachet des Combes · John Langford -
2022 : Towards Data-Driven Offline Simulations for Online Reinforcement Learning »
Shengpu Tang · Felipe Vieira Frujeri · Dipendra Misra · Alex Lamb · John Langford · Paul Mineiro · Sebastian Kochman -
2022 Poster: Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit »
Boaz Barak · Benjamin Edelman · Surbhi Goel · Sham Kakade · Eran Malach · Cyril Zhang -
2022 Poster: Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms »
Surbhi Goel · Sham Kakade · Adam Kalai · Cyril Zhang -
2022 Poster: Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning »
Aniket Didolkar · Kshitij Gupta · Anirudh Goyal · Nitesh Bharadwaj Gundavarapu · Alex Lamb · Nan Rosemary Ke · Yoshua Bengio -
2021 Poster: Adversarial Training Helps Transfer Learning via Better Representations »
Zhun Deng · Linjun Zhang · Kailas Vodrahalli · Kenji Kawaguchi · James Zou -
2021 Poster: Understanding End-to-End Model-Based Reinforcement Learning Methods as Implicit Parameterization »
Clement Gehring · Kenji Kawaguchi · Jiaoyang Huang · Leslie Kaelbling -
2021 Poster: Gone Fishing: Neural Active Learning with Fisher Embeddings »
Jordan Ash · Surbhi Goel · Akshay Krishnamurthy · Sham Kakade -
2021 Poster: EIGNN: Efficient Infinite-Depth Graph Neural Networks »
Juncheng Liu · Kenji Kawaguchi · Bryan Hooi · Yiwei Wang · Xiaokui Xiao -
2021 Poster: Noether Networks: meta-learning useful conserved quantities »
Ferran Alet · Dylan Doblar · Allan Zhou · Josh Tenenbaum · Kenji Kawaguchi · Chelsea Finn -
2021 Poster: Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time »
Ferran Alet · Maria Bauza · Kenji Kawaguchi · Nurullah Giray Kuru · Tomás Lozano-Pérez · Leslie Kaelbling -
2021 Poster: Discrete-Valued Neural Communication »
Dianbo Liu · Alex Lamb · Kenji Kawaguchi · Anirudh Goyal · Chen Sun · Michael Mozer · Yoshua Bengio -
2020 Poster: On Warm-Starting Neural Network Training »
Jordan Ash · Ryan Adams -
2020 Poster: Learning Composable Energy Surrogates for PDE Order Reduction »
Alex Beatson · Jordan Ash · Geoffrey Roeder · Tianju Xue · Ryan Adams -
2020 Oral: Learning Composable Energy Surrogates for PDE Order Reduction »
Alex Beatson · Jordan Ash · Geoffrey Roeder · Tianju Xue · Ryan Adams -
2016 Poster: Deep Learning without Poor Local Minima »
Kenji Kawaguchi -
2016 Oral: Deep Learning without Poor Local Minima »
Kenji Kawaguchi -
2015 Poster: Bayesian Optimization with Exponential Convergence »
Kenji Kawaguchi · Leslie Kaelbling · Tomás Lozano-Pérez