Sparse Meta Networks for Sequential Adaptation and its Application to Adaptive Language Modelling

2020-09-03 · Tsendsuren Munkhdalai

Training a deep neural network requires a large amount of single-task data and involves a long time-consuming optimization phase. This is not scalable to complex, realistic environments with new unexpected changes. Humans can perform fast incremental learning on the fly and memory systems in the brain play a critical role. We introduce Sparse Meta Networks -- a meta-learning approach to learn online sequential adaptation algorithms for deep neural networks, by using deep neural networks. We augment a deep neural network with a layer-specific fast-weight memory. The fast-weights are generated sparsely at each time step and accumulated incrementally through time providing a useful inductive bias for online continual adaptation. We demonstrate strong performance on a variety of sequential adaptation scenarios, from a simple online reinforcement learning to a large scale adaptive language modelling.

📄 PDF Abstract BibTeX arXiv:2009.01803

Code (0)

등록된 구현이 없습니다.

Tasks

Incremental LearningInductive BiasLanguage Modelling Meta-Learning Reinforcement Learning (RL)

Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start Recommendation

2023-02-28 · Minchang Kim, Yongjin Yang, Jung Hyun Ryu, Taesup Kim

Sequential recommenders have made great strides in capturing a user's preferences. Nevertheless, the cold-start recommendation remains a fundamental challenge as they typically involve limited user-item interactions for …

Few-Shot Learning Meta-Learning Sequential Recommendation

User-Adaptive Meta-Learning for Cold-Start Medication Recommendation with Uncertainty Filtering

2026-01-30 · Arya Hadizadeh Moghaddam, Mohsen Nayebi Kerdabadi, Dongjie Wang, Mei Liu 외 arxiv

Large-scale Electronic Health Record (EHR) databases have become indispensable in supporting clinical decision-making through data-driven treatment recommendations. However, existing medication recommender methods often …

Knowledge Graphs

Memory Sequence Length of Data Sampling Impacts the Adaptation of Meta-Reinforcement Learning Agents

2024-06-18 · Menglong Zhang, Fuyuan Qian, Quanying Liu

Fast adaptation to new tasks is extremely important for embodied agents in the real world. Meta-reinforcement learning (meta-RL) has emerged as an effective method to enable fast adaptation in unknown environments. Compa…

continuous-control Continuous Control Meta Reinforcement Learning MuJoCo+1

Adaptive Batching for Gaussian Process Surrogates with Application in Noisy Level Set Estimation

2020-03-19 · Xiong Lyu, Mike Ludkovski

We develop adaptive replicated designs for Gaussian process metamodels of stochastic experiments. Adaptive batching is a natural extension of sequential design heuristics with the benefit of replication growing as respon…

Lightweight Test-Time Adaptation for EMG-Based Gesture Recognition

2026-01-07 · Nia Touko, Matthew O A Ellis, Cristiano Capone, Alessio Burrello 외 arxiv

Reliable long-term decoding of gestures from surface electromyography (EMG) is hindered by signal drift caused by electrode displacement, muscle fatigue, and/or posture changes. Although modern models achieve high intra-…

Test-time Adaptation Gesture Recognition