Graph Your Own Prompt

• URL: http://arxiv.org/abs/2509.23373v2
• Date: Sun, 12 Oct 2025 15:43:09 GMT
• Title: Graph Your Own Prompt
• Authors: Xi Ding, Lei Wang, Piotr Koniusz, Yongsheng Gao,
• Abstract summary: Graph Consistency Regularization (GCR) is a framework that injects relational graph structures, derived from model predictions, into the learning process.<n>GCR promotes cleaner feature structure, stronger intra-class cohesion, and improved generalization, offering a new perspective on learning from prediction structure.
• Score: 44.358377952850994
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose Graph Consistency Regularization (GCR), a novel framework that injects relational graph structures, derived from model predictions, into the learning process to promote class-aware, semantically meaningful feature representations. Functioning as a form of self-prompting, GCR enables the model to refine its internal structure using its own outputs. While deep networks learn rich representations, these often capture noisy inter-class similarities that contradict the model's predicted semantics. GCR addresses this issue by introducing parameter-free Graph Consistency Layers (GCLs) at arbitrary depths. Each GCL builds a batch-level feature similarity graph and aligns it with a global, class-aware masked prediction graph, derived by modulating softmax prediction similarities with intra-class indicators. This alignment enforces that feature-level relationships reflect class-consistent prediction behavior, acting as a semantic regularizer throughout the network. Unlike prior work, GCR introduces a multi-layer, cross-space graph alignment mechanism with adaptive weighting, where layer importance is learned from graph discrepancy magnitudes. This allows the model to prioritize semantically reliable layers and suppress noisy ones, enhancing feature quality without modifying the architecture or training procedure. GCR is model-agnostic, lightweight, and improves semantic structure across various networks and datasets. Experiments show that GCR promotes cleaner feature structure, stronger intra-class cohesion, and improved generalization, offering a new perspective on learning from prediction structure. [Project website](https://darcyddx.github.io/gcr/) [Code](https://github.com/Darcyddx/graph-prompt)

Related papers

• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
  Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
  arXiv  Detail & Related papers  (2025-10-06T08:09:15Z)
• Adaptive Homophily Clustering: Structure Homophily Graph Learning with Adaptive Filter for Hyperspectral Image [21.709368882043897]
  Hyperspectral image (HSI) clustering has been a fundamental but challenging task with zero training labels.<n>In this paper, a homophily structure graph learning with an adaptive filter clustering method (AHSGC) for HSI is proposed.<n>Our AHSGC contains high clustering accuracy, low computational complexity, and strong robustness.
  arXiv  Detail & Related papers  (2025-01-03T01:54:16Z)
• Self-Supervised Contrastive Graph Clustering Network via Structural Information Fusion [15.293684479404092]
  We propose a novel deep graph clustering method called CGCN. Our approach introduces contrastive signals and deep structural information into the pre-training process. Our method has been experimentally validated on multiple real-world graph datasets.
  arXiv  Detail & Related papers  (2024-08-08T09:49:26Z)
• Synergistic Deep Graph Clustering Network [14.569867830074292]
  We propose a graph clustering framework named Synergistic Deep Graph Clustering Network (SynC) In our approach, we design a Transform Input Graph Auto-Encoder (TIGAE) to obtain high-quality embeddings for guiding structure augmentation. Notably, representation learning and structure augmentation share weights, significantly reducing the number of model parameters.
  arXiv  Detail & Related papers  (2024-06-22T09:40:34Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning [56.45977379288308]
  Masked autoencoder (MAE) learns to reconstruct masked graph edges or node features. Contrastive Learning (CL) maximizes the similarity between augmented views of the same graph. We propose graph contrastive masked autoencoder (GCMAE) framework to unify MAE and CL.
  arXiv  Detail & Related papers  (2023-10-24T05:06:06Z)
• Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking [18.950919307926824]
  We propose the SeeGera model, which is based on the family of self-supervised variational graph auto-encoder (VGAE) SeeGera co-embeds both nodes and features in the encoder and reconstructs both links and features in the decoder. We conduct extensive experiments comparing SeeGera with 9 other state-of-the-art competitors.
  arXiv  Detail & Related papers  (2023-01-29T15:00:43Z)
• Towards Unsupervised Deep Graph Structure Learning [67.58720734177325]
  We propose an unsupervised graph structure learning paradigm, where the learned graph topology is optimized by data itself without any external guidance. Specifically, we generate a learning target from the original data as an "anchor graph", and use a contrastive loss to maximize the agreement between the anchor graph and the learned graph.
  arXiv  Detail & Related papers  (2022-01-17T11:57:29Z)
• Learnable Structural Semantic Readout for Graph Classification [23.78861906423389]
  We propose structural semantic readout (SSRead) to summarize the node representations at the position-level. SSRead aims to identify structurally-meaningful positions by using the semantic alignment between its nodes and structural prototypes. Our experimental results demonstrate that SSRead significantly improves the classification performance and interpretability of GNN classifiers.
  arXiv  Detail & Related papers  (2021-11-22T20:44:27Z)
• Self-supervised Graph-level Representation Learning with Local and Global Structure [71.45196938842608]
  We propose a unified framework called Local-instance and Global-semantic Learning (GraphLoG) for self-supervised whole-graph representation learning. Besides preserving the local similarities, GraphLoG introduces the hierarchical prototypes to capture the global semantic clusters. An efficient online expectation-maximization (EM) algorithm is further developed for learning the model.
  arXiv  Detail & Related papers  (2021-06-08T05:25:38Z)
• Adaptive Graph Auto-Encoder for General Data Clustering [90.8576971748142]
  Graph-based clustering plays an important role in the clustering area. Recent studies about graph convolution neural networks have achieved impressive success on graph type data. We propose a graph auto-encoder for general data clustering, which constructs the graph adaptively according to the generative perspective of graphs.
  arXiv  Detail & Related papers  (2020-02-20T10:11:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.