Image de couverture de livre

How not to Stitch Representations to Measure Similarity: Task Loss Matching versus Direct Matching

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Balogh, András, Jelasity, Márk
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Verification of the Implicit World Model in a Generative Model via Adversarial Sequences
par: Balogh, András, et autres
Publié: (2026)

When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models
par: Guo, Zhixiang, et autres
Publié: (2026)

Flexible Online Representation Learning Based on Similarity Matching
par: Sridharan, Shagesh, et autres
Publié: (2026)

Hierarchy-Aware Neural Subgraph Matching with Enhanced Similarity Measure
par: Liu, Zhouyang, et autres
Publié: (2025)

No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks
par: Szász, Attila, et autres
Publié: (2025)

Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Off
par: Halmosi, Levente, et autres
Publié: (2024)

Detecting Semantic Backdoors in a Mystery Shopping Scenario
par: Berta, Arpad, et autres
Publié: (2026)

Selective Matching Losses -- Not All Scores Are Created Equal
par: Shamir, Gil I., et autres
Publié: (2025)

Half the Nonlinearity Is Wasted: Measuring and Reallocating the Transformer's MLP Budget
par: Balogh, Peter
Publié: (2026)

Disentangled Representation Learning via Flow Matching
par: Chi, Jinjin, et autres
Publié: (2026)

Kernel Representation and Similarity Measure for Incomplete Data
par: Cao, Yang, et autres
Publié: (2025)

Contrasting Multiple Representations with the Multi-Marginal Matching Gap
par: Piran, Zoe, et autres
Publié: (2024)

HeGMN: Heterogeneous Graph Matching Network for Learning Graph Similarity
par: Sang, Shilong, et autres
Publié: (2025)

Merging by Matching Models in Task Parameter Subspaces
par: Tam, Derek, et autres
Publié: (2023)

KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs
par: Sanyal, Debopam, et autres
Publié: (2026)

From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit
par: Costa, Valérie, et autres
Publié: (2025)

Charting the Design Space of Neural Graph Representations for Subgraph Matching
par: Raj, Vaibhav, et autres
Publié: (2025)

Towards Human-AI Complementarity in Matching Tasks
par: Arnaiz-Rodriguez, Adrian, et autres
Publié: (2025)

SEGMN: A Structure-Enhanced Graph Matching Network for Graph Similarity Learning
par: Wang, Wenjun, et autres
Publié: (2024)

ReSi: A Comprehensive Benchmark for Representational Similarity Measures
par: Klabunde, Max, et autres
Publié: (2024)

Flow Matching for Tabular Data Synthesis
par: Nasution, Bahrul Ilmi, et autres
Publié: (2025)

Representation Learning Preserving Ignorability and Covariate Matching for Treatment Effects
par: Nanavati, Praharsh, et autres
Publié: (2025)

Beyond Point Matching: Evaluating Multiscale Dubuc Distance for Time Series Similarity
par: Ahmadzadeh, Azim, et autres
Publié: (2025)

Similarity of Neural Network Models: A Survey of Functional and Representational Measures
par: Klabunde, Max, et autres
Publié: (2023)

What's the score? Automated Denoising Score Matching for Nonlinear Diffusions
par: Singhal, Raghav, et autres
Publié: (2024)

Explicit Flow Matching: On The Theory of Flow Matching Algorithms with Applications
par: Ryzhakov, Gleb, et autres
Publié: (2024)

Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
par: Wan, Zhengyan, et autres
Publié: (2025)

UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discovery
par: Li, Ruifeng, et autres
Publié: (2025)

Clustering Internet Memes Through Template Matching and Multi-Dimensional Similarity
par: Bloem, Tygo, et autres
Publié: (2025)

Similarity Matching Networks: Hebbian Learning and Convergence Over Multiple Time Scales
par: Centorrino, Veronica, et autres
Publié: (2025)

Random Process Flow Matching: Generative Implicit Representations of Multivariate Random Fields
par: Lalanne, Julien, et autres
Publié: (2026)

The Hidden Pitfalls of the Cosine Similarity Loss
par: Draganov, Andrew, et autres
Publié: (2024)

Approximate Subgraph Matching with Neural Graph Representations and Reinforcement Learning
par: Li, Kaiyang, et autres
Publié: (2026)

Multiple Object Stitching for Unsupervised Representation Learning
par: Shen, Chengchao, et autres
Publié: (2025)

Feature Matching Intervention: Leveraging Observational Data for Causal Representation Learning
par: Li, Haoze, et autres
Publié: (2025)

RepFlow: Representation Enhanced Flow Matching for Causal Effect Estimation
par: Xie, Yifei, et autres
Publié: (2026)

Beyond Match Maximization and Fairness: Retention-Optimized Two-Sided Matching
par: Kishimoto, Ren, et autres
Publié: (2026)

Match Made with Matrix Completion: Efficient Learning under Matching Interference
par: Tang, Zhiyuan, et autres
Publié: (2026)

What Representational Similarity Measures Imply about Decodable Information
par: Harvey, Sarah E., et autres
Publié: (2024)

The Discrete Charm of the MLP: Binary Routing of Continuous Signals in Transformer Feed-Forward Layers
par: Balogh, Peter
Publié: (2026)