Rethinking Importance Weighting for Transfer Learning

• URL: http://arxiv.org/abs/2112.10157v1
• Date: Sun, 19 Dec 2021 14:35:25 GMT
• Title: Rethinking Importance Weighting for Transfer Learning
• Authors: Nan Lu, Tianyi Zhang, Tongtong Fang, Takeshi Teshima, Masashi Sugiyama
• Abstract summary: Key assumption in supervised learning is that training and test data follow the same probability distribution. As real-world machine learning tasks are becoming increasingly complex, novel approaches are explored to cope with such challenges.
• Score: 71.81262398144946
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A key assumption in supervised learning is that training and test data follow the same probability distribution. However, this fundamental assumption is not always satisfied in practice, e.g., due to changing environments, sample selection bias, privacy concerns, or high labeling costs. Transfer learning (TL) relaxes this assumption and allows us to learn under distribution shift. Classical TL methods typically rely on importance-weighting -- a predictor is trained based on the training losses weighted according to the importance (i.e., the test-over-training density ratio). However, as real-world machine learning tasks are becoming increasingly complex, high-dimensional, and dynamical, novel approaches are explored to cope with such challenges recently. In this article, after introducing the foundation of TL based on importance-weighting, we review recent advances based on joint and dynamic importance-predictor estimation. Furthermore, we introduce a method of causal mechanism transfer that incorporates causal structure in TL. Finally, we discuss future perspectives of TL research.

Related papers

• Lessons Learned from a Unifying Empirical Study of Parameter-Efficient Transfer Learning (PETL) in Visual Recognition [36.031972728327894]
  We study representative PETL methods in the context of Vision Transformers. PETL methods can obtain similar accuracy in the low-shot benchmark VTAB-1K. PETL is also useful in many-shot regimes -- it achieves comparable and sometimes better accuracy than full FT.
  arXiv  Detail & Related papers  (2024-09-24T19:57:40Z)
• Dissecting Deep RL with High Update Ratios: Combatting Value Divergence [21.282292112642747]
  We show that deep reinforcement learning algorithms can retain their ability to learn without resetting network parameters. We employ a simple unit-ball normalization that enables learning under large update ratios.
  arXiv  Detail & Related papers  (2024-03-09T19:56:40Z)
• Hypothesis Transfer Learning with Surrogate Classification Losses: Generalization Bounds through Algorithmic Stability [3.908842679355255]
  Hypothesis transfer learning (HTL) contrasts domain adaptation by allowing for a previous task leverage, named the source, into a new one, the target. This paper studies the learning theory of HTL through algorithmic stability, an attractive theoretical framework for machine learning algorithms analysis.
  arXiv  Detail & Related papers  (2023-05-31T09:38:21Z)
• Adapting to Continuous Covariate Shift via Online Density Ratio Estimation [64.8027122329609]
  Dealing with distribution shifts is one of the central challenges for modern machine learning. We propose an online method that can appropriately reuse historical information. Our density ratio estimation method is proven to perform well by enjoying a dynamic regret bound.
  arXiv  Detail & Related papers  (2023-02-06T04:03:33Z)
• Tracking changes using Kullback-Leibler divergence for the continual learning [2.0305676256390934]
  This article introduces a novel method for monitoring changes in the probabilistic distribution of multi-dimensional data streams. As a measure of the rapidity of changes, we analyze the popular Kullback-Leibler divergence. We show how to use this metric to predict the concept drift occurrence and understand its nature.
  arXiv  Detail & Related papers  (2022-10-10T17:30:41Z)
• Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport [78.9167477093745]
  We propose a novel distribution calibration method by learning the adaptive weight matrix between novel samples and base classes. Experimental results on standard benchmarks demonstrate that our proposed plug-and-play model outperforms competing approaches.
  arXiv  Detail & Related papers  (2022-10-09T02:32:57Z)
• Crude Oil-related Events Extraction and Processing: A Transfer Learning Approach [0.7476901945542385]
  This paper presents a complete framework for extracting and processing crude oil-related events found in CrudeOilNews corpus. We place special emphasis on event properties (Polarity, Modality, and Intensity) classification to determine the factual certainty of each event.
  arXiv  Detail & Related papers  (2022-05-01T03:21:18Z)
• Counterfactual Representation Learning with Balancing Weights [74.67296491574318]
  Key to causal inference with observational data is achieving balance in predictive features associated with each treatment type. Recent literature has explored representation learning to achieve this goal. We develop an algorithm for flexible, scalable and accurate estimation of causal effects.
  arXiv  Detail & Related papers  (2020-10-23T19:06:03Z)
• Accurate and Robust Feature Importance Estimation under Distribution Shifts [49.58991359544005]
  PRoFILE is a novel feature importance estimation method. We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
  arXiv  Detail & Related papers  (2020-09-30T05:29:01Z)
• Value-driven Hindsight Modelling [68.658900923595]
  Value estimation is a critical component of the reinforcement learning (RL) paradigm. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. We develop an approach for representation learning in RL that sits in between these two extremes. This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
  arXiv  Detail & Related papers  (2020-02-19T18:10:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.