Graph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learning

• URL: http://arxiv.org/abs/2508.14859v1
• Date: Wed, 20 Aug 2025 17:13:19 GMT
• Title: Graph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learning
• Authors: Jiafeng Xiong, Rizos Sakellariou,
• Abstract summary: We propose a versatile framework that integrates Graph Structure Learning (GSL) with Temporal Graph Information Bottleneck (TGIB)<n>We design a novel two-step GSL-based structural enhancer to enrich and optimize node neighborhoods.<n>The TGIB refines the optimized graph by extending the information bottleneck principle to temporal graphs, regularizing both edges and features.
• Score: 1.3728301825671199
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Temporal graph learning is crucial for dynamic networks where nodes and edges evolve over time and new nodes continuously join the system. Inductive representation learning in such settings faces two major challenges: effectively representing unseen nodes and mitigating noisy or redundant graph information. We propose GTGIB, a versatile framework that integrates Graph Structure Learning (GSL) with Temporal Graph Information Bottleneck (TGIB). We design a novel two-step GSL-based structural enhancer to enrich and optimize node neighborhoods and demonstrate its effectiveness and efficiency through theoretical proofs and experiments. The TGIB refines the optimized graph by extending the information bottleneck principle to temporal graphs, regularizing both edges and features based on our derived tractable TGIB objective function via variational approximation, enabling stable and efficient optimization. GTGIB-based models are evaluated to predict links on four real-world datasets; they outperform existing methods in all datasets under the inductive setting, with significant and consistent improvement in the transductive setting.

Related papers

• GADPN: Graph Adaptive Denoising and Perturbation Networks via Singular Value Decomposition [6.24191713518868]
  GADPN is a graph structure learning framework that adaptively refines graph topology via low-rank denoising and generalized structural perturbation.<n>It achieves state-of-the-art performance while significantly improving efficiency.<n>It shows particularly strong gains on challenging disassortative graphs, validating its ability to robustly learn enhanced graph structures.
  arXiv  Detail & Related papers  (2026-01-13T05:25:32Z)
• 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)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)
• Robust Graph Structure Learning with the Alignment of Features and Adjacency Matrix [8.711977569042865]
  Many approaches have been proposed for graph structure learning (GSL) to jointly learn a clean graph structure and corresponding representations. This paper proposes a novel regularized GSL approach, particularly with an alignment of feature information and graph information. We conduct experiments on real-world graphs to evaluate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-07-05T09:05:14Z)
• Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment [53.72873672076391]
  Temporal graph learning aims to generate high-quality representations for graph-based tasks with dynamic information. We propose a self-supervised method called S2T for temporal graph learning, which extracts both temporal and structural information. S2T achieves at most 10.13% performance improvement compared with the state-of-the-art competitors on several datasets.
  arXiv  Detail & Related papers  (2023-02-15T06:36:04Z)
• Directed Acyclic Graph Structure Learning from Dynamic Graphs [44.21230819336437]
  Estimating the structure of directed acyclic graphs (DAGs) of features (variables) plays a vital role in revealing the latent data generation process. We study the learning problem of node feature generation mechanism on such ubiquitous dynamic graph data.
  arXiv  Detail & Related papers  (2022-11-30T14:22:01Z)
• EGRC-Net: Embedding-induced Graph Refinement Clustering Network [66.44293190793294]
  We propose a novel graph clustering network called Embedding-Induced Graph Refinement Clustering Network (EGRC-Net) EGRC-Net effectively utilizes the learned embedding to adaptively refine the initial graph and enhance the clustering performance. Our proposed methods consistently outperform several state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-19T09:08:43Z)
• 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)
• Dynamic Graph Representation Learning via Graph Transformer Networks [41.570839291138114]
  We propose a Transformer-based dynamic graph learning method named Dynamic Graph Transformer (DGT) DGT has spatial-temporal encoding to effectively learn graph topology and capture implicit links. We show that DGT presents superior performance compared with several state-of-the-art baselines.
  arXiv  Detail & Related papers  (2021-11-19T21:44:23Z)
• Graph Contrastive Learning with Adaptive Augmentation [23.37786673825192]
  We propose a novel graph contrastive representation learning method with adaptive augmentation. Specifically, we design augmentation schemes based on node centrality measures to highlight important connective structures. Our proposed method consistently outperforms existing state-of-the-art baselines and even surpasses some supervised counterparts.
  arXiv  Detail & Related papers  (2020-10-27T15:12:21Z)
• Graph Information Bottleneck [77.21967740646784]
  Graph Neural Networks (GNNs) provide an expressive way to fuse information from network structure and node features. Inheriting from the general Information Bottleneck (IB), GIB aims to learn the minimal sufficient representation for a given task. We show that our proposed models are more robust than state-of-the-art graph defense models.
  arXiv  Detail & Related papers  (2020-10-24T07:13:00Z)
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings [53.58077686470096]
  We propose an end-to-end graph learning framework, namely Iterative Deep Graph Learning (IDGL) for jointly and iteratively learning graph structure and graph embedding. Our experiments show that our proposed IDGL models can consistently outperform or match the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-06-21T19:49:15Z)

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.