mlsanityData to 14 Oct 2026

Learning Noise-Resilient and Transferable Graph-Text Alignment via Dynamic Quality Assessment

arXiv 2510.19384 ↗First posted 22 Oct 2025cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Pre-training Graph Foundation Models (GFMs) on text-attributed graphs (TAGs) is central to web-scale applications such as search, recommendation, and knowledge discovery. However, existing CLIP-style graph-text aligners face two key limitations: they assume strict one-to-one correspondences between nodes and texts, overlooking the inherent many-to-many relations in real-world graphs; and they rely on static alignment objectives that cannot adapt to varying data quality, making them brittle under noisy supervision. Together, these limitations expose a core dilemma: embracing expressive many-to-many alignment amplifies noise, while reverting to strict one-to-one strategies sacrifices semantic diversity and fails to handle inherently mismatched pairs. To address these challenges, we propose ADAligner, a dynamic, quality-aware graph-text alignment framework that dynamically adjusts between expressive many-to-many and conservative one-to-one objectives according to supervision quality. ADAligner estimates batch-level alignment reliability in real time and adapts its optimization accordingly, promoting soft, subgraph-level many-to-many alignment when supervision is clean, while emphasizing reliable one-to-one alignment by dynamically filtering low-confidence pairs under noise. Theoretically, we prove that this dynamic mechanism forms a stable negative feedback process, ensuring convergence and robustness. Comprehensive experiments on nine diverse TAG datasets demonstrate that ADAligner consistently outperforms prior graph-text aligners on zero-/few-shot node classification, link prediction and cross-modal retrieval tasks. It maintains strong robustness under noisy supervision and accelerates pre-training by approximately 2 to 3 times compared to multimodal baselines, establishing a scalable and reliable foundation for graph-text representation learning in real-world web environments.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 49 of its 74 references that are in the map. First posted on arXiv 22 Oct 2025.

Builds on

49 of 74 references.

References · 49

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  7. 2017Graph Attention Networkscited by 8,923
  8. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  9. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  10. 2017Inductive Representation Learning on Large Graphscited by 6,320
  11. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  12. 2020Graph Contrastive Learning with Augmentationscited by 1,208
37 more
  1. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  2. 2018Deep Graph Infomaxcited by 1,106
  3. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  4. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  5. 2020Contrastive Learning with Hard Negative Samplescited by 628
  6. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 541
  7. 2020Deep Graph Contrastive Representation Learningcited by 539
  8. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  9. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 448
  10. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  11. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 260
  12. 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 226
  13. 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 167
  14. 2022Learning on Large-scale Text-attributed Graphs via Variational Inferencecited by 155
  15. 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 148
  16. 2019Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labelscited by 111
  17. 2024β-DPO: Direct Preference Optimization with Dynamic βcited by 90
  18. 2024ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphscited by 85
  19. 2024A Survey of Large Language Models for Graphscited by 72
  20. 2024Can GNN be Good Adapter for LLMs?cited by 71
  21. 2023CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learningcited by 63
  22. 2023Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Promptingcited by 62
  23. 2024GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphscited by 58
  24. 2023SoftCLIP: Softer Cross-modal Alignment Makes CLIP Strongercited by 56
  25. 2023Patton: Language Model Pretraining on Text-Rich Networkscited by 49
  26. 2022Robust Contrastive Learning against Noisy Viewscited by 45
  27. 2024GLBench: A Comprehensive Benchmark for Graph with Large Language Modelscited by 36
  28. 2023GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learningcited by 33
  29. 2023ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddingscited by 32
  30. 2023GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed Graphscited by 28
  31. 2022Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphscited by 21
  32. 2022Informative Pseudo-Labeling for Graph Neural Networks with Few Labelscited by 19
  33. 2024CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learningcited by 13
  34. 2024Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labelscited by 7
  35. 2024CancerKG.ORG A Web-scale, Interactive, Verifiable Knowledge Graph-LLM Hybrid for Assisting with Optimal Cancer Treatment and Carecited by 6
  36. 2023Mutually-paced Knowledge Distillation for Cross-lingual Temporal Knowledge Graph Reasoningcited by 4
  37. 2024MLDGG: Meta-Learning for Domain Generalization on Graphscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphscited by 1
  2. 2026S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphscited by 0
  3. 2026Hierarchical Response Preservation for Continual Adaptation of Zero-Shot Graph-Text Modelscited by 0