paper-with-me

Papers

SAIL: Self-Augmented Graph Contrastive Learning

2020-09-02 · Lu Yu, Shichao Pei, Lizhong Ding, Jun Zhou, Longfei Li, Chuxu Zhang, Xiangliang Zhang

This paper studies learning node representations with graph neural networks (GNNs) for unsupervised scenario. Specifically, we derive a theoretical analysis and provide an empirical demonstration about the non-steady performance of GNNs over different graph datasets, when the supervision signals are not appropriately defined. The performance of GNNs depends on both the node feature smoothness and the locality of graph structure. To smooth the discrepancy of node proximity measured by graph topology and node feature, we proposed SAIL - a novel \underline{S}elf-\underline{A}ugmented graph contrast\underline{i}ve \underline{L}earning framework, with two complementary self-distilling regularization modules, \emph{i.e.}, intra- and inter-graph knowledge distillation. We demonstrate the competitive performance of SAIL on a variety of graph applications. Even with a single GNN layer, SAIL has consistently competitive or even better performance on various benchmark datasets, comparing with state-of-the-art baselines.

📄 PDF Abstract BibTeX arXiv:2009.00934

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningKnowledge DistillationNode Classification

Methods 이 논문이 사용한 방법론

GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Similar Papers 제목 키워드 기반

Self-Augmented In-Context Learning for Unsupervised Word Translation

2024-02-15 · Yaoyiran Li, Anna Korhonen, Ivan Vulić

Recent work has shown that, while large language models (LLMs) demonstrate strong word translation or bilingual lexicon induction (BLI) capabilities in few-shot setups, they still cannot match the performance of 'traditi…

Bilingual Lexicon InductionCross-Lingual Word EmbeddingsFew-Shot LearningIn-Context Learning+8

SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human Feedback

2026-02-05 · Xiaoxuan He, Siming Fu, Wanli Li, Zhiyuan Li 외 arxiv

Aligning diffusion models with human preferences remains challenging, particularly when reward models are unavailable or impractical to obtain, and collecting large-scale preference datasets is prohibitively expensive. \…

SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement

2025-07-02 · Weijie Yin, Dingkang Yang, Hongyuan Dong, Zijian Kang 외 arxiv

Vision Transformers (ViTs) are essential as foundation backbones in establishing the visual comprehension capabilities of Multimodal Large Language Models (MLLMs). Although most ViTs achieve impressive performance throug…

Contrastive Learning

Embodied-Symbolic Contrastive Graph Self-Supervised Learning for Molecular Graphs

2022-05-13 · Daniel T. Chang

Dual embodied-symbolic concept representations are the foundation for deep learning and symbolic AI integration. We discuss the use of dual embodied-symbolic concept representations for molecular graph representation lea…

Graph Representation LearningRepresentation LearningSelf-Supervised Learning

Tensor-Fused Multi-View Graph Contrastive Learning

2024-10-20 · Yujia Wu, Junyi Mo, Elynn Chen, Yuzhou Chen

Graph contrastive learning (GCL) has emerged as a promising approach to enhance graph neural networks' (GNNs) ability to learn rich representations from unlabeled graph-structured data. However, current GCL models face c…

Contrastive LearningGraph Classification