paper-with-me

홈 › Papers

Lifelong Infinite Mixture Model Based on Knowledge-Driven Dirichlet Process

2021-08-25 · ICCV 2021 10 · Fei Ye, Adrian G. Bors

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.

📄 PDF Abstract BibTeX arXiv:2108.12278

Code (1)

dtuzi123/lifelong-infinite-mixture-model 공식 구현 tf

Tasks

Lifelong learning

Methods 이 논문이 사용한 방법론

LIMix 설명 없음

Similar Papers 제목 키워드 기반

A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning

2022-05-22 · Zhi Wang, Chunlin Chen, Daoyi Dong

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 Navigation

Lifelong Mixture of Variational Autoencoders

2021-07-09 · Fei Ye, Adrian G. Bors

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-Experts

Infinite Mixture of Inverted Dirichlet Distributions

2018-07-27 · Zhanyu Ma, Yuping Lai

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 Inference

Unsupervised Outlier Detection using Random Subspace and Subsampling Ensembles of Dirichlet Process Mixtures

2024-01-01 · DongWook Kim, Juyeon Park, Hee Cheol Chung, Seonghyun Jeong

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 Inference

LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

2023-06-05 · NeurIPS 2023 11

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