arXiv Machine Learning

Why Does Graph Learning Fail to Fully Benefit from a Text Teacher?

The paper examines a multimodal approach that combines a self‑supervised GNN encoder with an alternating optimization scheme involving a language‑model teacher. Despite the expectation that this joint strategy would enhance predictive performance, the authors find that the combined model fails to deliver significant gains. They identify six key factors—ranging from anchor strength trade‑offs to misaligned representation spaces—that explain why the integration of text knowledge does not fully benefit graph learning.

arXiv Machine Learning

4d ago

Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models

The paper introduces a feedforward graph architecture that uses several frozen large language models as computational nodes connected through a shared continuous latent space via learned linear projections. By jointly optimizing projection matrices through backpropagation, the system combines the representations of three small frozen models with two larger ones, culminating in a lightweight cross‑attention output node. With only 17.6 M trainable parameters, the architecture attains state‑of‑the‑art results on ARC‑Challenge, OpenBookQA, and MMLU, surpassing both individual constituent models and parameter‑matched learned classifiers.

By Marcus Armstrong, Navid Ayoobi, Arjun Mukherjee

llms diffusion benchmarks

arXiv Machine Learning

Jun 11

Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching

arXiv:2606. 11583v1 Announce Type: new Abstract: Text-attributed graphs (TAGs) underlie real-world applications such as citation networks, social media, and e-commerce.

By Zhuoyi Peng, Hanlin Gu, Lixin Fan, Yi Yang

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 17

Multimodal Graph Negative Learning

arXiv:2606. 12863v2 Announce Type: replace Abstract: Multimodal attributed graphs (MAGs) integrate graph topology with heterogeneous modality attributes, such as text and images, thereby enabling richer modeling of complex relational systems.

By Zhengyu Wu, Xu Wang, Hongchao Qin, Xunkai Li, Guang Zeng, Rong-Hua Li, Guoren Wang

multimodal safety

arXiv Machine Learning

Sep 10

Chimaera: A Mixture-of-Graph-Experts Architecture for Cross-Task and Cross-Dataset Graph Learning

arXiv:2609.08709v1 Announce Type: new Abstract: Designing foundation models for graphs is challenging due to the irregular structure of graphs and the different sizes and characteristics of embedding...

By Jonathan Frank, David Richerby, Ansgar Scherp

llms rag benchmarks

arXiv AI

Aug 6

NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning

arXiv:2608. 04381v1 Announce Type: cross Abstract: Self-supervised learning on graphs is largely shaped by contrastive methods that depend on carefully designed augmentations, and by generative methods that reconstruct node attributes in the input space.

By Tinghe Zhang, Jian Xu, Jiaheng Chen, Jiaxing Li, Yucheng Xiao, Qiang Wang

rag diffusion fine-tuning benchmarks

arXiv AI

Jun 11

GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning

arXiv:2510. 04567v3 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) are powerful tools for processing relational data but often struggle to generalize to unseen graphs, giving rise to the development of Graph Foundational Models (GFMs).

By Weishuo Ma, Yanbo Wang, Xiyuan Wang, Lei Zou, Muhan Zhang

llms

arXiv Machine Learning

Sep 4

LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models

The paper introduces PromptGFM, a Graph Foundation Model designed for text‑attributed graphs (TAGs). It integrates Large Language Models (LLMs) and Graph Neural Networks (GNNs) through a Graph Understanding Module that prompts LLMs to emulate GNN workflows, and a Graph Inference Module that creates a language‑based graph vocabulary for better alignment and scalability. Experiments show PromptGFM outperforms existing methods and transfers effectively across various graphs and tasks.

By Xi Zhu, Haochen Xue, Ziwei Zhao, Wujiang Xu, Jingyuan Huang, Minghao Guo, Qifan Wang, Kaixiong Zhou, Imran Razzak, Yongfeng Zhang

llms fine-tuning safety

arXiv Machine Learning

Jun 2

G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs

arXiv:2606. 01873v1 Announce Type: new Abstract: LLM-as-Aligner has emerged as a prevalent pre-training paradigm for Text-Attributed Graphs(TAGS), aligning graph and text modalities into a shared embedding space via CLIP-style contrastive learning.

By Yuhan Wang, Yibo Ding, Yutong Ye, Mufan Zhao, Wenbo Zhang, Ruijie Wang, Jianxin Li

llms rag fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jul 22

One Model, Many Graphs: Learning over Attributed Graphs across Heterogeneous Modalities with Vision-Language Models

arXiv:2607. 19128v1 Announce Type: new Abstract: Vision-language models (VLMs) provide a unified representation space for textual and visual information, yet their potential as general-purpose backbones for graph-structured data remains largely unexplored.

By Jiayi Yang, Yifang Chen, Yuanfu Sun, Jiajin Liu, Qiaoyu Tan

llms rag multimodal benchmarks

arXiv Machine Learning

Jun 30

GLIP: Graph and LLM Joint Pretraining for Graph-Level Tasks

arXiv:2606. 29773v1 Announce Type: new Abstract: Graphs are widely used to model relational systems, with applications in domains such as social networks, finance, and biomedicine.

By Haoxin Sun, Yiqing Lin, Yajun Huang, Chenhui Dong, Mingjun Li, Zhongzhi Zhang

llms diffusion fine-tuning benchmarks safety

arXiv AI

3d ago

Ventriloquist LLMs: Linear Alignment of Late-Stage Representations

arXiv:2603.18908v5 Announce Type: replace Abstract: Independently trained language models often learn compatible late-stage representations, despite differences in training objectives, architectures,...

By Matt Gorbett, Suman Jana

llms rag nlp fine-tuning safety

arXiv Machine Learning

Jun 15

Natively Unlearnable Large Language Models

arXiv:2606. 13873v1 Announce Type: new Abstract: Unlearning aims to remove the influence of specific training data sources, but this has proved challenging because the contributions of different sources are entangled within the model.

By Gaurav R. Ghosal, Pratyush Maini, Aditi Raghunathan

llms benchmarks safety

Related stories