Methods › General › Loss Functions › InfoNCE
InfoNCE
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
InfoNCE, where NCE stands for Noise-Contrastive Estimation, is a type of contrastive loss function used for self-supervised learning.
Given a set X ={x₁, …, x_N} of N random samples containing one positive sample from p(xₜ₊ₖ|cₜ) and N − 1 negative samples from the 'proposal' distribution p(xₜ₊ₖ), we optimize:
ℒ_N = - 𝔼_X[log(fₖ(xₜ₊ₖ, cₜ))/(∑_(xⱼ∈X)fₖ(xⱼ, cₜ))]
Optimizing this loss will result in fₖ(xₜ₊ₖ, cₜ) estimating the density ratio, which is:
fₖ(xₜ₊ₖ, cₜ) ∝(p(xₜ₊ₖ|cₜ))/(p(xₜ₊ₖ))
Papers archive 2025-07-28
30 shown of 418, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Generalizing Supervised Contrastive learning: A Projection Perspective 11 Jun 2025 · 0 repositories · arXiv:2506.09810
-
Probabilistic Variational Contrastive Learning 11 Jun 2025 · 0 repositories · arXiv:2506.10159
-
Integration of Contrastive Predictive Coding and Spiking Neural Networks 10 Jun 2025 · 1 repository · arXiv:2506.09194
-
Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data 25 May 2025 · 1 repository · arXiv:2505.19274
-
Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization 22 May 2025 · 1 repository · arXiv:2505.16471Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
-
Contrastive Alignment with Semantic Gap-Aware Corrections in Text-Video Retrieval 18 May 2025 · 1 repository · arXiv:2505.12499
-
Adversarial Robustness for Unified Multi-Modal Encoders via Efficient Calibration 17 May 2025 · 0 repositories · arXiv:2505.11895
-
Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning 12 May 2025 · 0 repositories · arXiv:2505.07921
-
sEEG-based Encoding for Sentence Retrieval: A Contrastive Learning Approach to Brain-Language Alignment 20 Apr 2025 · 0 repositories · arXiv:2504.14468
-
Koopman-Based Event-Triggered Control from Data 19 Apr 2025 · 0 repositories · arXiv:2504.14334
-
Variational Self-Supervised Learning 6 Apr 2025 · 0 repositories · arXiv:2504.04318
-
Node Embeddings via Neighbor Embeddings 31 Mar 2025 · 0 repositories · arXiv:2503.23822
-
Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance 29 Mar 2025 · 1 repository · arXiv:2503.23239
-
Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling 23 Mar 2025 · 1 repository · arXiv:2503.17908Syntology ran 2 of 2 samples · 0 unverified
-
Weighted Graph Structure Learning with Attention Denoising for Node Classification 15 Mar 2025 · 1 repository · arXiv:2503.12157
-
OASIS: Order-Augmented Strategy for Improved Code Search 11 Mar 2025 · 0 repositories · arXiv:2503.08161Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
-
Advancing Vietnamese Information Retrieval with Learning Objective and Benchmark 10 Mar 2025 · 0 repositories · arXiv:2503.07470
-
Task-Specific Knowledge Distillation from the Vision Foundation Model for Enhanced Medical Image Segmentation 10 Mar 2025 · 0 repositories · arXiv:2503.06976
-
Learning Transformer-based World Models with Contrastive Predictive Coding 6 Mar 2025 · 0 repositories · arXiv:2503.04416
-
LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning 4 Mar 2025 · 0 repositories · arXiv:2503.04812
-
Teaching Dense Retrieval Models to Specialize with Listwise Distillation and LLM Data Augmentation 27 Feb 2025 · 1 repository · arXiv:2502.19712
-
Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence 24 Feb 2025 · 0 repositories · arXiv:2502.17028
-
Dataset Ownership Verification in Contrastive Pre-trained Models 11 Feb 2025 · 1 repository · arXiv:2502.07276
-
Temperature-Free Loss Function for Contrastive Learning 29 Jan 2025 · 0 repositories · arXiv:2501.17683
-
CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectors 28 Jan 2025 · 0 repositories · arXiv:2501.16665
-
Self-supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets? 26 Jan 2025 · 0 repositories · arXiv:2501.15431
-
Contrastive Representation Learning Helps Cross-institutional Knowledge Transfer: A Study in Pediatric Ventilation Management 23 Jan 2025 · 0 repositories · arXiv:2501.13587
-
Language modulates vision: Evidence from neural networks and human brain-lesion models 23 Jan 2025 · 0 repositories · arXiv:2501.13628
-
An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against Label Noise 2 Jan 2025 · 0 repositories · arXiv:2501.01130
-
Performance-Barrier Event-Triggered PDE Control of Traffic Flow 1 Jan 2025 · 0 repositories · arXiv:2501.00722
Tasks archive 2025-07-28
20 shown of 343 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections