# ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs

arXiv: https://arxiv.org/abs/2606.10461 · HTML: https://mlsanity.com/paper/2606.10461/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 55 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Builds on (most cited first, 30 of 34)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One](https://mlsanity.com/paper/1912.03263/) (2019)
- [How to Train Your Energy-Based Models](https://mlsanity.com/paper/2101.03288/) (2021)
- [Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks](https://mlsanity.com/paper/2007.02901/) (2020)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [GraphGPT: Graph Instruction Tuning for Large Language Models](https://mlsanity.com/paper/2310.13023/) (2023)
- [A Theory of Generative ConvNet](https://mlsanity.com/paper/1602.03264/) (2016)
- [Learning on Large-scale Text-attributed Graphs via Variational Inference](https://mlsanity.com/paper/2210.14709/) (2022)
- [GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph](https://mlsanity.com/paper/2105.02605/) (2021)
- [Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction](https://mlsanity.com/paper/2111.00064/) (2021)
- [Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning](https://mlsanity.com/paper/2305.19523/) (2023)
- [The Cramer Distance as a Solution to Biased Wasserstein Gradients](https://mlsanity.com/paper/1705.10743/) (2017)
- [Energy-Based Diffusion Language Models for Text Generation](https://mlsanity.com/paper/2410.21357/) (2024)
- [SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning](https://mlsanity.com/paper/2308.02565/) (2023)
- [Can GNN be Good Adapter for LLMs?](https://mlsanity.com/paper/2402.12984/) (2024)
- [GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks](https://mlsanity.com/paper/2402.07197/) (2024)
- [LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings](https://mlsanity.com/paper/2408.14512/) (2024)
- [Efficient Tuning and Inference for Large Language Models on Textual Graphs](https://mlsanity.com/paper/2401.15569/) (2024)
- [Patton: Language Model Pretraining on Text-Rich Networks](https://mlsanity.com/paper/2305.12268/) (2023)
- [Graph Machine Learning in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2404.14928/) (2024)
- [Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs](https://mlsanity.com/paper/2310.09872/) (2023)
- [EGC: Image Generation and Classification via a Diffusion Energy-Based Model](https://mlsanity.com/paper/2304.02012/) (2023)

## Built on by (most cited first, 1 of 1)

- [DeKoR: Decomposed Knowledge Routing for Efficient GNN--LLM Fusion](https://mlsanity.com/paper/2610.14710/) (2026)

## Abstract (arXiv)

Text-attributed Graphs (TAGs) incorporate textual node attributes with graph structures to describe rich relational semantics. Recent efforts to integrate Graph Neural Networks (GNNs) and Large Language Models (LLMs) have shown promise for learning on TAGs, yet achieving well-aligned representations remains challenging. Prior studies largely rely on heuristics that perform coarse-grained matching. They lack sufficient constraints and ignore distributional alignment, leading to representation drift and limited generalization. Building on Energy-based Models (EBMs), we propose an Energy-based Representation Alignment (ERAlign) framework that projects GNN-encoded graph structure and LLM-derived text embeddings in a shared latent space to achieve distribution consistency. Concretely, layer-wise alignment is quantified by a distance metric and optimized via an EBM objective. By decreasing energy values, our framework yields well-aligned representations for downstream tasks. During training, we introduce Energy Discrepancy (ED) to avoid high sampling costs associated with intractable normalization. ED also carries theoretical guarantees of higher training efficiency and reduced energy landscape distortion. Empirical evaluations on eight TAG datasets demonstrate that ERAlign obtains state-of-the-art performance across varying levels of supervision and cross-task transfer scenarios.