Browse > Methodology > Continual Learning

Continual Learning

74 papers with code · Methodology

Leaderboards

No evaluation results yet. Help compare methods by submit evaluation metrics.

Latest papers with code

Visually Grounded Continual Learning of Compositional Semantics

2 May 2020INK-USC/VG-CCL

Children's language acquisition from the visual world is a real-world example of continual learning from dynamic and evolving environments; yet we lack a realistic setup to study neural networks' capability in human-like language acquisition.

CONTINUAL LEARNING LANGUAGE ACQUISITION LANGUAGE MODELLING

2
02 May 2020

Generative Feature Replay For Class-Incremental Learning

20 Apr 2020xialeiliu/GFR-IL

To prevent forgetting, we combine generative feature replay in the classifier with feature distillation in the feature extractor.

CONTINUAL LEARNING IMAGE GENERATION

9
20 Apr 2020

CLOPS: Continual Learning of Physiological Signals

20 Apr 2020danikiyasseh/CLOPS

Deep learning algorithms are known to experience destructive interference when instances violate the assumption of being independent and identically distributed (i. i. d).

CONTINUAL LEARNING MULTI-TASK LEARNING

0
20 Apr 2020

Continual Reinforcement Learning with Multi-Timescale Replay

16 Apr 2020ChristosKap/multi_timescale_replay

In this paper, we propose a multi-timescale replay (MTR) buffer for improving continual learning in RL agents faced with environments that are changing continuously over time at timescales that are unknown to the agent.

CONTINUAL LEARNING CONTINUOUS CONTROL

6
16 Apr 2020

Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation

31 Mar 2020vict0rsch/LiSS

Unpaired Image-to-Image Translation (I2IT) tasks often suffer from lack of data, a problem which self-supervised learning (SSL) has recently been very popular and successful at tackling.

COLORIZATION CONTINUAL LEARNING IMAGE-TO-IMAGE TRANSLATION SELF-SUPERVISED LEARNING

0
31 Mar 2020

Adversarial Continual Learning

21 Mar 2020facebookresearch/Adversarial-Continual-Learning

We show that shared features are significantly less prone to forgetting and propose a novel hybrid continual learning framework that learns a disjoint representation for task-invariant and task-specific features required to solve a sequence of tasks.

CONTINUAL LEARNING IMAGE CLASSIFICATION

56
21 Mar 2020

Evaluating Logical Generalization in Graph Neural Networks

14 Mar 2020facebookresearch/GraphLog

Recent research has highlighted the role of relational inductive biases in building learning agents that can generalize and reason in a compositional manner.

CONTINUAL LEARNING KNOWLEDGE GRAPHS RELATIONAL REASONING

67
14 Mar 2020

Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning

12 Mar 2020ElementAI/osaka

As a remedy, we propose a more general scenario where an agent must quickly solve (new) out-of-distribution tasks, while also requiring fast remembering.

CONTINUAL LEARNING META-LEARNING

18
12 Mar 2020

Training Binary Neural Networks using the Bayesian Learning Rule

25 Feb 2020team-approx-bayes/BayesBiNN

Our work provides a principled approach for training binary neural networks which justifies and extends existing approaches.

CONTINUAL LEARNING

9
25 Feb 2020

Learning to Continually Learn

21 Feb 2020uvm-neurobotics-lab/ANML

Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it.

CONTINUAL LEARNING META-LEARNING

65
21 Feb 2020