Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models

2026-05-13 · Haonan Yuan, Qingyun Sun, Junhua Shi, Xingcheng Fu, Jianxin Li, Philip S. Yu arxiv

Dynamic graphs are ubiquitous in real-world systems, and building generalizable dynamic Graph Foundation Models has become a frontier in graph learning. However, dynamic graphs from different domains pose fundamental challenges to unified modeling, as their semantic and temporal patterns are inherently inconsistent, making the multi-domain pre-training difficult. Consequently, the widely used "pretrain-then-finetune" paradigm often suffers from severe negative knowledge transfer. To the best of our knowledge, there exists no multi-domain dynamic GFM. In this work, we propose DyGFM, a Dynamic Graph Foundation Model over multiple domains based on decoupled and divergence-conditioned prompting. To disentangle transferable semantics from the domain-specific dynamics, we introduce a dual-branch pre-training strategy with semantic-temporal decoupling. To alleviate negative transfer during domain adaptation, we further develop a cross-domain routing mechanism with divergence-aware expert selection. To enable efficient downstream fine-tuning, we design a divergence-conditioned prompt generator that injects lightweight, learnable graph prompts tailored to semantic and temporal traits. Extensive experiments on continuous dynamic graph benchmarks demonstrate that DyGFM consistently outperforms 12 state-of-the-art baselines on both node classification and link prediction tasks, achieving superior effectiveness and efficiency.

📄 PDF Abstract BibTeX arXiv:2605.13540

Code (0)

등록된 구현이 없습니다.

Tasks

Node Classification Domain Adaptation Link Prediction Graph Learning

DPL: Decoupled Prompt Learning for Vision-Language Models

2023-08-19 · Chen Xu, Yuhan Zhu, Guozhen Zhang, Haocheng Shen 외

Prompt learning has emerged as an efficient and effective approach for transferring foundational Vision-Language Models (e.g., CLIP) to downstream tasks. However, current methods tend to overfit to seen categories, there…

Prompt Learning

DeSAM: Decoupled Segment Anything Model for Generalizable Medical Image Segmentation

2023-06-01 · Yifan Gao, Wei Xia, Dingdu Hu, Wenkui Wang 외

Deep learning-based medical image segmentation models often suffer from domain shift, where the models trained on a source domain do not generalize well to other unseen domains. As a prompt-driven foundation model with p…

Decoder Domain Generalization Image Segmentation Medical Image Segmentation+2

KL Divergence Estimation with Multi-group Attribution

2022-02-28 · Parikshit Gopalan, Nina Narodytska, Omer Reingold, Vatsal Sharan 외

Estimating the Kullback-Leibler (KL) divergence between two distributions given samples from them is well-studied in machine learning and information theory. Motivated by considerations of multi-group fairness, we seek K…

Fairness

PromptKD: Unsupervised Prompt Distillation for Vision-Language Models

2024-03-05 · CVPR 2024 1 · Zheng Li, Xiang Li, Xinyi Fu, Xin Zhang 외

Prompt learning has emerged as a valuable technique in enhancing vision-language models (VLMs) such as CLIP for downstream tasks in specific domains. Existing work mainly focuses on designing various learning forms of pr…

Knowledge Distillation Prompt Engineering Prompt Learning Zero-Shot Image Classification

Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning

2026-06-13 · Ali Dasdan, Manan Shah, W. Russell Neuman, Chad Coleman 외 arxiv

Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it. We use Transluce, an AI-driven mechanistic-interpretability platform, to examine LLaMA 3…