Copertina

Disentangling and Mitigating the Impact of Task Similarity for Continual Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Hiratani, Naoki
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Optimal Task Order for Continual Learning of Multiple Tasks
di: Li, Ziyan, et al.
Pubblicazione: (2025)

Characterizing and Correcting Effective Target Shift in Online Learning
di: Li, Ziyan, et al.
Pubblicazione: (2026)

GED-Consistent Disentanglement of Aligned and Unaligned Substructures for Graph Similarity Learning
di: Zhan, Zhentao, et al.
Pubblicazione: (2025)

Similarity-Aware Mixture-of-Experts for Data-Efficient Continual Learning
di: Mclaughlin, Connor, et al.
Pubblicazione: (2026)

Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric
di: Uesaka, Toshimitsu, et al.
Pubblicazione: (2024)

In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasks
di: Wang, Dingzirui, et al.
Pubblicazione: (2024)

Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
di: Mucsányi, Bálint, et al.
Pubblicazione: (2024)

Task Addition and Weight Disentanglement in Closed-Vocabulary Models
di: Hazimeh, Adam, et al.
Pubblicazione: (2025)

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks
di: Kinoshita, Yuri, et al.
Pubblicazione: (2026)

Federated Learning-Based Risk-Aware Decision toMitigate Fake Task Impacts on CrowdsensingPlatforms
di: Chen, Zhiyan, et al.
Pubblicazione: (2021)

SAVGO: Learning State-Action Value Geometry with Cosine Similarity for Continuous Control
di: Orfanoudakis, Stavros, et al.
Pubblicazione: (2026)

Gradient Similarity Surgery in Multi-Task Deep Learning
di: Borsani, Thomas, et al.
Pubblicazione: (2025)

Continuous Histogram Loss: Beyond Neural Similarity
di: Zholus, Artem, et al.
Pubblicazione: (2020)

Task-Agnostic Experts Composition for Continual Learning
di: Quarantiello, Luigi, et al.
Pubblicazione: (2025)

Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings
di: Wu, Yanru, et al.
Pubblicazione: (2025)

Sequencing to Mitigate Catastrophic Forgetting in Continual Learning
di: Moussa, Hesham G., et al.
Pubblicazione: (2025)

ODIN: Disentangled Reward Mitigates Hacking in RLHF
di: Chen, Lichang, et al.
Pubblicazione: (2024)

Dynamically Anchored Prompting for Task-Imbalanced Continual Learning
di: Hong, Chenxing, et al.
Pubblicazione: (2024)

Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation
di: Jia, Chengxing, et al.
Pubblicazione: (2024)

Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge
di: Chen, Yan-Lun, et al.
Pubblicazione: (2025)

Variational Learning of Disentangled Representations
di: Slavutsky, Yuli, et al.
Pubblicazione: (2025)

Disentangling Language Roles in Multilingual LLM Task Execution
di: Zhan, Qishi, et al.
Pubblicazione: (2026)

SPINEX: Similarity-based Predictions and Explainable Neighbors Exploration for Regression and Classification Tasks in Machine Learning
di: Naser, M. Z., et al.
Pubblicazione: (2023)

Class-wise Classifier Design Capable of Continual Learning using Adaptive Resonance Theory-based Topological Clustering
di: Masuyama, Naoki, et al.
Pubblicazione: (2022)

The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting -- An Analytical Model
di: Goldfarb, Daniel, et al.
Pubblicazione: (2024)

DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts
di: Sun, Guiquan, et al.
Pubblicazione: (2026)

Mitigating Forgetting in Continual Learning with Selective Gradient Projection
di: Singh, Anika, et al.
Pubblicazione: (2026)

Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study
di: Müller, Sarah, et al.
Pubblicazione: (2026)

Multi-Task Learning with Feature-Similarity Laplacian Graphs for Predicting Alzheimer's Disease Progression
di: Xu, Zixiang, et al.
Pubblicazione: (2025)

Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
di: Jin, Ruochen, et al.
Pubblicazione: (2024)

NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
di: Qin, Xiaohan, et al.
Pubblicazione: (2025)

Continual Deep Reinforcement Learning with Task-Agnostic Policy Distillation
di: Hafez, Muhammad Burhan, et al.
Pubblicazione: (2024)

Continual Learning of Numerous Tasks from Long-tail Distributions
di: Kang, Liwei, et al.
Pubblicazione: (2024)

A Continual Offline Reinforcement Learning Benchmark for Navigation Tasks
di: Kobanda, Anthony, et al.
Pubblicazione: (2025)

TAME: Task Agnostic Continual Learning using Multiple Experts
di: Zhu, Haoran, et al.
Pubblicazione: (2022)

TSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning
di: Żurek, Dominik, et al.
Pubblicazione: (2026)

PVBF: A Framework for Mitigating Parameter Variation Imbalance in Online Continual Learning
di: Tao, Zelin, et al.
Pubblicazione: (2025)

On the Similarities of Embeddings in Contrastive Learning
di: Lee, Chungpa, et al.
Pubblicazione: (2025)

DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks
di: Cui, Wei, et al.
Pubblicazione: (2025)

Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity
di: Yoshida, Naoki, et al.
Pubblicazione: (2025)