Expert Gate: Lifelong Learning with a Network of Experts

By Rahaf Aljundi, Punarjay Chakravarty, Tinne Tuytelaars. 2016

771 citations recorded by the source corpus.

In this paper we introduce a model of lifelong learning, based on a Network of Experts. New tasks / experts are learned and added to the model sequentially, building on what was learned before. To ensure scalability of this process, data from previous tasks cannot be stored and hence is not available when learning a new task. A critical issue in such context, not addressed in the literature so far, relates to the decision which expert to deploy at test time. We introduce a set of gating autoencoders that learn a representation for the task at hand, and, at test time, automatically forward the test sample to the relevant expert. This also brings memory efficiency as only one expert network has to be loaded into memory at any given time. Further, the autoencoders inherently capture the relatedness of one task to another, based on which the most relevant prior model to be used for training a new expert, with fine-tuning or learning-without-forgetting, can be selected. We evaluate our method on image classification and video prediction problems.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging, Representation & Self-Supervised Learning, Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

In Representation & Self-Supervised Learning

In Optimization & Training

Citations in the corpus

Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer (2017, background): “Other work has focused on different expert conﬁgurations such as a hierarchical structure (Yao et al., 2009), inﬁnite numbers of experts (Rasmussen & Ghahramani, 2002), and adding experts sequentially (Aljundi et al., 2016).”
A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “Expert Gate [243] employs a mixture of experts to learn incremental tasks, expanding one expert as each task is introduced.”
ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations (2019, background): “Aljundi et al. (2017) learns a gating function to make expert network assignments.”
Towards causal generative scene models via competition of experts (2020, background): “More recently, these ideas have been successfully applied to tasks such as lifelong learning (Aljundi et al., 2017), learning independent causal mechanisms (Parascandolo et al., 2018), training mixtures of generative models (Locatello et al., 2018), as well as to dynamical systems via…”
Learning Independent Causal Mechanisms (2017, background): “Aljundi et al. (2017) train a network of experts on multiple tasks, with a focus on lifelong learning; au-toencoders are trained for each task and used as gating mechanisms.”
Gradient Episodic Memory for Continual Learning (2017, methodology): “This relates to methods that leverage a modular structure of the network with primitives that can be shared across tasks [Rusu et al., 2016, Fernando et al., 2017, Aljundi et al., 2016, Denoyer and Gallinari, 2015, Eigen et al., 2014].”
Progress & Compress: A scalable framework for continual learning (2018, background): “Other examples include (Aljundi et al., 2016) which introduces a gating mechanism between columns and (Rozantsev et al.”
Learnability and Algorithm for Continual Learning (2023, methodology): “, 2020), Expert Gate (Aljundi et al., 2017), HyperNet (von Oswald et al.”
RMM: Reinforced Memory Management for Class-Incremental Learning (2023, background): “Similar tasks are also referred to as continual learning [12, 32] and lifelong learning [3, 9].”
A Theoretical Study on Solving Continual Learning (2022, methodology): “Expert Gate [64] constructs a separate autoencoder for each task.”
DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning (2022, methodology): “Parameter isolation methods [3, 29, 40, 42] are based on dynamically allocating a set of parameters for each task so that the training does not interfere with each other.”
Balancing Stability and Plasticity through Advanced Null Space in Continual Learning (2022, methodology): “Architecture-based methods allocate diﬀerent parameters or add new parameters for the new task, while sharing parameters across tasks to reduce the interference of previous tasks [3, 22, 27–29, 41, 42, 44, 53, 56, 60].”
Online Continual Learning with Contrastive Vision Transformer (2022, background): “Recent studies have focused on a more practical Task-free protocol, which evaluates the network on all classes observed during training without requiring the identity of the task [3,81,8,95,37,90,13].”
Incremental Task Learning with Incremental Rank Updates (2022, background): “Incremental task learning is a subcategory of continual learning or lifelong learning approaches aim to address the problem of catastrophic forgetting by adapting the network or training process to learn new tasks without forgetting the previously learned ones [23,16,3,2,4,6,28,29,12].”
CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One (2022, neutral): “Most current applications focus on learning each single task with a sub-network [39,2,49], which can be seen as a special case of dynamic architecture.”
NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks (2022, methodology): “This parameter isolation is often achieved by growing new branches for tasks and freezing previous task parameters (Rusu et al., 2016; Li et al., 2021; Sahbi & Zhan, 2021; Yoon et al., 2018; Aljundi et al., 2017; Rosenfeld & Tsotsos, 2018).”
Class-Incremental Learning with Strong Pre-trained Models (2022, background): “The exceptions infer the task identity typically by learning a routing classifier [1, 4], or estimating confidence scores [27].”