Conditional Representation Learning For Customized Tasks

Abstract

Conventional representation learning methods learn a universal representation that primarily captures dominant semantics, which may not always align with customized downstream tasks. For instance, in animal habitat analysis, researchers prioritize scene-related features, whereas universal embeddings emphasize categorical semantics, leading to suboptimal results. As a solution, existing approaches resort to supervised fine-tuning, which however incurs high computational and annotation costs. In this paper, we propose Conditional Representation Learning (CRL), aiming to extract representations tailored to arbitrary user-specified criteria. Specifically, we reveal that the semantics of a space are determined by its basis, thereby enabling a set of descriptive words to approximate the basis for a customized feature space. Building upon this insight, given a user-specified criterion, CRL first employs a large language model (LLM) to generate descriptive texts to construct the semantic basis

Stats

• citations0
• S2 citations—
• github stars46
• HF likes0
• heat score3.34
• arxiv keyliu2025conditional

Related papers

• Multimodal Representation Learning Conditioned On Semantic Relations (2025)0.00
• Matryoshka Representation Learning (2022)12.37
• TRACE: Task-adaptive Reasoning And Representation Learning For Universal Multimodal Retrieval (2026)0.00
• Cross-modal Discrete Representation Learning (2021)10.61
• CREM: Compression-driven Representation Enhancement For Multimodal Retrieval And Comprehension (2026)0.00
• Beyond Matryoshka: Revisiting Sparse Coding For Adaptive Representation (2025)4.30
• CSPLADE: Learned Sparse Retrieval With Causal Language Models (2025)0.00
• Unified Representation Learning For Cross Model Compatibility (2020)5.24