AAAI 2023 accepted papers on Continual learning
30 of the 2,023 papers accepted at AAAI 2023 (1.5%) are on Continual learning, compared with 0.5% at AAAI 2022. They fall into 4 topics.
See AAAI 2023 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Online and replay-based · 20 papers
- Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference (51 citations)
- Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs (44 citations)
- Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task (32 citations)
- Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces (30 citations)
- Continual Learning with Scaled Gradient Projection (24 citations)
- Sparse Coding in a Dual Memory System for Lifelong Learning (20 citations)
- Overcoming Forgetting in Fine-Grained Urban Flow Inference via Adaptive Knowledge Replay (18 citations)
- Structure Aware Incremental Learning with Personalized Imitation Weights for Recommender Systems (17 citations)
- A Neural Span-Based Continual Named Entity Recognition Model (14 citations)
- Learning Dynamic Latent Spaces for Lifelong Generative Modelling (11 citations)
- Continual Variational Autoencoder via Continual Generative Knowledge Distillation (8 citations)
- Online Noisy Continual Relation Learning (4 citations)
and 8 more in the interactive map.
Class-incremental · 7 papers
- Online Hyperparameter Optimization for Class-Incremental Learning (33 citations)
- Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning (23 citations)
- One-Shot Replay: Boosting Incremental Object Detection via Retrospecting One Object (13 citations)
- Leveraging Old Knowledge to Continually Learn New Classes in Medical Images (11 citations)
- MetaZSCIL: A Meta-Learning Approach for Generalized Zero-Shot Class Incremental Learning (11 citations)
- Mixture Uniform Distribution Modeling and Asymmetric Mix Distillation for Class Incremental Learning (11 citations)
- Effective Continual Learning for Text Classification with Lightweight Snapshots (7 citations)