Lifelong Infinite Mixture Model Based on Knowledge-Driven Dirichlet Process
Recent research efforts in lifelong learning propose to grow a mixture of models to adapt to an increasing number of tasks. The proposed methodology shows promising results in overcoming catastrophic forgetting. However, the theory behind these successful models is still not well understood. In this paper, we perform the theoretical analysis for lifelong learning models by deriving the risk bounds based on the discrepancy distance between the probabilistic representation of data generated by the model and that corresponding to the target dataset. Inspired by the theoretical analysis, we introduce a new lifelong learning approach, namely the Lifelong Infinite Mixture (LIMix) model, which can automatically expand its network architectures or choose an appropriate component to adapt its parameters for learning a new task, while preserving its previously learnt information. We propose to incorporate the knowledge by means of Dirichlet processes by using a gating mechanism which computes the dependence between the knowledge learnt previously and stored in each component, and a new set of data. Besides, we train a compact Student model which can accumulate cross-domain representations over time and make quick inferences. The code is available at https://github.com/dtuzi123/Lifelong-infinite-mixture-model.
Code (1)
Tasks
Lifelong learningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning
While reinforcement learning (RL) algorithms are achieving state-of-the-art performance in various challenging tasks, they can easily encounter catastrophic forgetting or interference when faced with lifelong streaming i…
reinforcement-learningReinforcement Learning (RL)Robot NavigationLifelong Mixture of Variational Autoencoders
In this paper, we propose an end-to-end lifelong learning mixture of experts. Each expert is implemented by a Variational Autoencoder (VAE). The experts in the mixture system are jointly trained by maximizing a mixture o…
Lifelong learningMixture-of-ExpertsInfinite Mixture of Inverted Dirichlet Distributions
In this work, we develop a novel Bayesian estimation method for the Dirichlet process (DP) mixture of the inverted Dirichlet distributions, which has been shown to be very flexible for modeling vectors with positive elem…
Variational InferenceUnsupervised Outlier Detection using Random Subspace and Subsampling Ensembles of Dirichlet Process Mixtures
Probabilistic mixture models are recognized as effective tools for unsupervised outlier detection owing to their interpretability and global characteristics. Among these, Dirichlet process mixture models stand out as a s…
Outlier DetectionVariational InferenceLIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
Lifelong learning offers a promising paradigm of building a generalist agent that learns and adapts over its lifespan. Unlike traditional lifelong learning problems in image and text domains, which primarily involve the …
BenchmarkingDecision MakingLifelong learning+2