LTF: A Label Transformation Framework for Correcting Target Shift
12. července 2020
Řečníci
Jiaxian Guo
Sprecher:in · 0 Follower:innen
Mingming Gong
Sprecher:in · 0 Follower:innen
Tongliang Liu
Sprecher:in · 0 Follower:innen
Dacheng Tao
Sprecher:in · 1 Follower:in
O prezentaci
Distribution shift is a major obstacle to the deployment of current deep learning models on real-world problems. Let Y be the class label and X the features. We focus on one type of distribution shift, label shift, where the label marginal distribution P_Y changes but the conditional distribution P_X|Y does not. Most existing methods estimate the density ratio between the source- and target-domain label distributions by density matching. However, these methods are either computationally infeasible for large-scale data or restricted to shift correction for discrete labels. In this paper, we propose an end-to-end Label Transformation Framework (LTF) for correcting label shift, which implicitly models the shift of P_Y and the conditional distribution P_X|Y using neural networks. Thanks to the flexibility of deep networks, our framework can handle continuous, discrete, and even multi-dimensional labels in a unified way and is scalable to large data. Moreover, for high dimensional X, such as images, we find that the redundant information in X severely degrades the estimation accuracy. To remedy this issue, we propose to match the distribution implied by our generative model and the target-domain distribution in a low-dimensional feature space that discards information irrelevant to Y. Both theoretical and empirical studies demonstrate the superiority of our method over previous approaches.Distribution shift is a major obstacle to the deployment of current deep learning models on real-world problems. Let Y be the class label and X the features. We focus on one type of distribution shift, label shift, where the label marginal distribution P_Y changes but the conditional distribution P_X|Y does not. Most existing methods estimate the density ratio between the source- and target-domain label distributions by density matching. However, these methods are either computationally infeasib…
Kategorie
KI und Datenwissenschaft
Kategorie · 10,8k Präsentationen
O organizátorovi (ICML 2020)
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Language Agnostic Speech Embeddings for Emotion Classification
Später ansehen
Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition
Später ansehen
Chi Jin, …
Rapid policy updating in human physical construction
Später ansehen
Logarithmic Regret for Online Control
Später ansehen
