Cover Image

Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Joonkyu, Kim, Yejin, Sohn, Jy-yong
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
by: Lee, Chungpa, et al.
Published: (2026)

ERD: A Framework for Improving LLM Reasoning for Cognitive Distortion Classification
by: Lim, Sehee, et al.
Published: (2024)

Analysis of Using Sigmoid Loss for Contrastive Learning
by: Lee, Chungpa, et al.
Published: (2024)

Soft Task-Aware Routing of Experts for Equivariant Representation Learning
by: Jeon, Jaebyeong, et al.
Published: (2025)

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

Memorization Capacity for Additive Fine-Tuning with Small ReLU Networks
by: Sohn, Jy-yong, et al.
Published: (2024)

A Theoretical Framework for Preventing Class Collapse in Supervised Contrastive Learning
by: Lee, Chungpa, et al.
Published: (2025)

Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback
by: Kim, Jungtaek, et al.
Published: (2026)

How to Correctly Report LLM-as-a-Judge Evaluations
by: Lee, Chungpa, et al.
Published: (2025)

Buffer-based Gradient Projection for Continual Federated Learning
by: Dai, Shenghong, et al.
Published: (2024)

Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
by: Kwon, Jihoon, et al.
Published: (2026)

Dynamic Time-aware Continual User Representation Learning
by: Choi, Seungyoon, et al.
Published: (2025)

Can Separators Improve Chain-of-Thought Prompting?
by: Park, Yoonjeong, et al.
Published: (2024)

Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions
by: Kwon, Jihoon, et al.
Published: (2025)

Federated Learning for Estimating Heterogeneous Treatment Effects
by: Makhija, Disha, et al.
Published: (2024)

Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metrics
by: Kong, Insung, et al.
Published: (2025)

Improving Multi-lingual Alignment Through Soft Contrastive Learning
by: Park, Minsu, et al.
Published: (2024)

Linq-Embed-Mistral Technical Report
by: Choi, Chanyeol, et al.
Published: (2024)

Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning
by: Kim, Yejin, et al.
Published: (2025)

Towards Diverse Evaluation of Class Incremental Learning: A Representation Learning Perspective
by: Cha, Sungmin, et al.
Published: (2022)

Score-based Causal Representation Learning: Linear and General Transformations
by: Varıcı, Burak, et al.
Published: (2024)

Linear Representations of Political Perspective Emerge in Large Language Models
by: Kim, Junsol, et al.
Published: (2025)

Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responses
by: Kim, Juyeon, et al.
Published: (2024)

Identifying General Mechanism Shifts in Linear Causal Representations
by: Chen, Tianyu, et al.
Published: (2024)

One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning
by: Kim, Doyoung, et al.
Published: (2023)

Learning Covariance-Based Multi-Scale Representation of Neuroimaging Measures for Alzheimer Classification
by: Baek, Seunghun, et al.
Published: (2025)

FedShift: Robust Federated Learning Aggregation Scheme in Resource Constrained Environment via Weight Shifting
by: Seo, Jungwon, et al.
Published: (2024)

ReTaSA: A Nonparametric Functional Estimation Approach for Addressing Continuous Target Shift
by: Kim, Hwanwoo, et al.
Published: (2024)

Achieving Fairness Across Local and Global Models in Federated Learning
by: Makhija, Disha, et al.
Published: (2024)

Approximate Bayesian Class-Conditional Models under Continuous Representation Shift
by: Lee, Thomas L., et al.
Published: (2023)

MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular Data
by: Ling, Yaobin, et al.
Published: (2024)

Configuring Data Augmentations to Reduce Variance Shift in Positional Embedding of Vision Transformers
by: Kim, Bum Jun, et al.
Published: (2024)

MIRRAMS: Learning Robust Tabular Models under Unseen Missingness Shifts
by: Lee, Jihye, et al.
Published: (2025)

Continual Learning as Shared-Manifold Continuation Under Compatible Shift
by: Kobs, Henry J.
Published: (2026)

A Composite Activation Function for Learning Stable Binary Representations
by: Park, Seokhun, et al.
Published: (2026)

Learning Equi-angular Representations for Online Continual Learning
by: Seo, Minhyuk, et al.
Published: (2024)

Addressing Distribution Shift in RTB Markets via Exponential Tilting
by: Kim, Minji, et al.
Published: (2023)

Decision by Supervised Learning with Deep Ensembles: A Practical Framework for Robust Portfolio Optimization
by: Kim, Juhyeong, et al.
Published: (2025)

Knowledge Vector Weakening: Efficient Training-free Unlearning for Large Vision-Language Models
by: Kim, Yejin, et al.
Published: (2026)

Transfer Learning for Benign Overfitting in High-Dimensional Linear Regression
by: Kim, Yeichan, et al.
Published: (2025)