paper-with-me

Papers

Hyper-CL: Conditioning Sentence Representations with Hypernetworks

2024-03-14 · Young Hyun Yoo, Jii Cha, Changhyeon Kim, Taeuk Kim

While the introduction of contrastive learning frameworks in sentence representation learning has significantly contributed to advancements in the field, it still remains unclear whether state-of-the-art sentence embeddings can capture the fine-grained semantics of sentences, particularly when conditioned on specific perspectives. In this paper, we introduce Hyper-CL, an efficient methodology that integrates hypernetworks with contrastive learning to compute conditioned sentence representations. In our proposed approach, the hypernetwork is responsible for transforming pre-computed condition embeddings into corresponding projection layers. This enables the same sentence embeddings to be projected differently according to various conditions. Evaluation on two representative conditioning benchmarks, namely conditional semantic text similarity and knowledge graph completion, demonstrates that Hyper-CL is effective in flexibly conditioning sentence representations, showcasing its computational efficiency at the same time. We also provide a comprehensive analysis of the inner workings of our approach, leading to a better interpretation of its mechanisms.

📄 PDF Abstract BibTeX arXiv:2403.09490

Code (1)

hyu-nlp/hyper-cl 공식 구현 pytorch

Tasks

Computational EfficiencyContrastive LearningKnowledge Graph CompletionRepresentation LearningSentenceSentence Embeddingstext similarity

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
HyperNetwork A HyperNetwork is a network that generates weights for a main network. The behavior of the main network is the same with any usual neural network: it learns to map some raw…

Similar Papers 제목 키워드 기반

Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models

2025-03-02 · Jeffrey Gu, Serena Yeung-Levy

Large pre-trained models, or foundation models, have shown impressive performance when adapted to a variety of downstream tasks, often out-performing specialized models. Hypernetworks, neural networks that generate some …

HyperCGAN: Text-to-Image Synthesis with HyperNet-Modulated Conditional Generative Adversarial Networks

2021-09-29 · Kilichbek Haydarov, Aashiq Muhamed, Jovana Lazarevic, Ivan Skorokhodov 외

We present HyperCGAN: a conceptually simple and general approach for text-to-image synthesis that uses hypernetworks to condition a GAN model on text. In our setting, the generator and the discriminator weights are contr…

Image Generation

On Infinite-Width Hypernetworks

2020-03-27 · NeurIPS 2020 12 · Etai Littwin, Tomer Galanti, Lior Wolf, Greg Yang

{\em Hypernetworks} are architectures that produce the weights of a task-specific {\em primary network}. A notable application of hypernetworks in the recent literature involves learning to output functional representati…

Meta-Learning

Multi-Sensor Matching with HyperNetworks

2026-01-18 · Eli Passov, Nathan S. Netanyahu, Yosi Keller arxiv

Hypernetworks are models that generate or modulate the weights of another network. They provide a flexible mechanism for injecting context and task conditioning and have proven broadly useful across diverse applications …

Multimodal Patch MatchingDomain Generalization

Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning

2025-10-22 · M. H. I. Abdalla, Zhipin Wang, Christian Frey, Steffen Eger 외 arxiv

Large Language Model (LLM) conditioning refers to instructing an LLM to generate content in accordance with the norms and values of a specific culture, beliefs of a particular political orientation, or any desired text-s…

Prompt Engineering