Online Deep Learning from Doubly-Streaming Data

Abstract

This paper investigates a new online learning problem with doubly-streaming data, where the data streams are described by feature spaces that constantly evolve, with new features emerging and old features fading away. The challenges of this problem are two folds: 1) Data samples ceaselessly flowing in may carry shifted patterns over time, requiring learners to update hence adapt on-the-fly. 2) Newly emerging features are described by very few samples, resulting in weak learners that tend to make error predictions. A plausible idea to overcome the challenges is to establish relationship between the pre-and-post evolving feature spaces, so that an online learner can leverage the knowledge learned from the old features to better the learning performance on the new features. Unfortunately, this idea does not scale up to high-dimensional media streams with complex feature interplay, which suffers an tradeoff between onlineness (biasing shallow learners) and expressiveness(requiring deep learners). Motivated by this, we propose a novel OLD^3S paradigm, where a shared latent subspace is discovered to summarize information from the old and new feature spaces, building intermediate feature mapping relationship. A key trait of OLD^3S is to treat the model capacity as a learnable semantics, yields optimal model depth and parameters jointly, in accordance with the complexity and non-linearity of the input data streams in an online fashion. Both theoretical analyses and empirical studies substantiate the viability and effectiveness of our proposal.

arXiv commentHave accepted by ACMMM 2022. Legends mistake in Figure 4 has been corrected

References in corpus (13)

• Auto-Encoding Variational Bayes
• Variational Inference: A Review for Statisticians
• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• FractalNet: Ultra-Deep Neural Networks without Residuals
• The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
• Generalization in Deep Learning
• The History of Digital Spam
• On the Universality of Online Mirror Descent
• A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions
• Learning with Feature Evolvable Streams
• Lifelong Learning of Graph Neural Networks for Open-World Node Classification
• Online mirror descent and dual averaging: keeping pace in the dynamic case
• HONES: A Fast and Tuning-free Homotopy Method For Online Newton Step