Robustness of Graph Self-Supervised Learning to Real-World Noise: A Case Study on Text-Driven Biomedical Graphs

• URL: http://arxiv.org/abs/2605.05463v1
• Date: Wed, 06 May 2026 21:38:38 GMT
• Title: Robustness of Graph Self-Supervised Learning to Real-World Noise: A Case Study on Text-Driven Biomedical Graphs
• Abstract summary: Graph Self-Supervised Learning (GSSL) offers a powerful paradigm for learning graph representations without labeled data.<n>Recent advances in NLP enable the large-scale automatic extraction of knowledge graphs from text.<n>We present the first comprehensive evaluation of GSSL methods on text-driven graphs for unsupervised term typing.
• Score: 1.9307742024764771
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph Self-Supervised Learning (GSSL) offers a powerful paradigm for learning graph representations without labeled data. However, existing work assumes clean, manually curated graphs. Recent advances in NLP enable the large-scale automatic extraction of knowledge graphs from text, opening new opportunities for GSSL while introducing substantial real-world noise. This type of noise remains largely unexplored, as prior robustness studies typically rely on synthetic perturbations. To address this gap, we present the first comprehensive evaluation of GSSL methods on text-driven graphs for unsupervised term typing. We introduce Noise-Aware Text-Driven Graph GSSL (NATD-GSSL), a unified framework that combines automatic graph construction, graph refinement, and GSSL. Our evaluation follows a dual-graph protocol that contrasts a noisy graph derived from MedMentions with a clean Unified Medical Language System (UMLS) reference graph, aligned through a shared gold standard. Our results reveal variability in robustness across both pretext tasks and Graph Neural Network (GNN) architectures. Relation reconstruction is highly sensitive to noise and benefits from well-defined schemas, whereas feature reconstruction is considerably more robust, achieving performance comparable to clean-graph settings. Contrastive objectives are generally less affected by noise but depend strongly on alignment with downstream tasks. GNN architecture also plays a critical role: bidirectional relational message-passing designs are better suited to noisy, text-driven graphs, while unidirectional relational ones perform best on clean graphs. Overall, NATD-GSSL provides practical guidance for applying GSSL to real-world, noisy graphs and achieves up to a 7\% improvement over pretrained language model baselines. All code and benchmarks are publicly available at https://github.com/OthmaneKabal/MC2GAE.

Related papers

• Graph Topology Information Enhanced Heterogeneous Graph Representation Learning [46.12931110810428]
  We propose a novel Graph Topology learning Enhanced Heterogeneous Graph Representation Learning framework (ToGRL)<n>ToGRL learns high-quality graph structures and representations for downstream tasks by incorporating task-relevant latent topology information.<n>Our ToGRL outperforms state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2026-04-07T11:35:45Z)
• Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs [62.544129365882014]
  We propose a novel Semi-supervised Instruction Tuning pipeline for Graph Learning, named SIT-Graph.<n> SIT-Graph is model-agnostic and can be seamlessly integrated into any graph instruction tuning method that utilizes LLMs as the predictor.<n>Extensive experiments demonstrate that when incorporated into state-of-the-art graph instruction tuning methods, SIT-Graph significantly enhances their performance on text-attributed graph benchmarks.
  arXiv  Detail & Related papers  (2026-01-19T08:10:53Z)
• 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)
• Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation [79.75818239774952]
  Large language models (LLMs) have demonstrated remarkable capabilities, but still struggle with issues like hallucinations and outdated information.<n>Retrieval-augmented generation (RAG) addresses these issues by grounding LLM outputs in external knowledge with an Information Retrieval (IR) system.<n>We propose Align-GRAG, a novel reasoning-guided dual alignment framework in post-retrieval phrase.
  arXiv  Detail & Related papers  (2025-05-22T05:15:27Z)
• Scale-Free Graph-Language Models [44.283149785253286]
  Graph-language models (GLMs) have demonstrated great potential in graph-based semi-supervised learning.<n>This paper introduces a novel GLM that integrates graph generation and text embedding within a unified framework.
  arXiv  Detail & Related papers  (2025-02-21T03:41:43Z)
• Beyond Message Passing: Neural Graph Pattern Machine [50.78679002846741]
  We introduce the Neural Graph Pattern Machine (GPM), a novel framework that bypasses message passing by learning directly from graph substructures.<n>GPM efficiently extracts, encodes, and prioritizes task-relevant graph patterns, offering greater expressivity and improved ability to capture long-range dependencies.
  arXiv  Detail & Related papers  (2025-01-30T20:37:47Z)
• GraphGPT: Graph Instruction Tuning for Large Language Models [27.036935149004726]
  Graph Neural Networks (GNNs) have evolved to understand graph structures. To enhance robustness, self-supervised learning (SSL) has become a vital tool for data augmentation. Our research tackles this by advancing graph model generalization in zero-shot learning environments.
  arXiv  Detail & Related papers  (2023-10-19T06:17:46Z)
• 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)
• Graph Structure Learning with Variational Information Bottleneck [70.62851953251253]
  We propose a novel Variational Information Bottleneck guided Graph Structure Learning framework, namely VIB-GSL. VIB-GSL learns an informative and compressive graph structure to distill the actionable information for specific downstream tasks.
  arXiv  Detail & Related papers  (2021-12-16T14:22:13Z)
• Deep Graph Structure Learning for Robust Representations: A Survey [20.564611153151834]
  Graph Neural Networks (GNNs) are widely used for analyzing graph-structured data. To improve the robustness of GNN models, many studies have been proposed around the central concept of Graph Structure Learning.
  arXiv  Detail & Related papers  (2021-03-04T13:49:25Z)

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.