# UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs

arXiv: https://arxiv.org/abs/2502.00806 · HTML: https://mlsanity.com/paper/2502.00806/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 32 of its 60 references that are in the map.
- First posted on arXiv 2 Feb 2025.

## Placed in

- Mixture-of-experts / [Multimodal MoE models](https://mlsanity.com/moe/multimodal-moe-models/)

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training](https://mlsanity.com/paper/2006.09963/) (2020)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [Can Language Models Solve Graph Problems in Natural Language?](https://mlsanity.com/paper/2305.10037/) (2023)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [Learning on Large-scale Text-attributed Graphs via Variational Inference](https://mlsanity.com/paper/2210.14709/) (2022)
- [Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction](https://mlsanity.com/paper/2111.00064/) (2021)
- [GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner](https://mlsanity.com/paper/2304.04779/) (2023)
- [PRODIGY: Enabling In-context Learning Over Graphs](https://mlsanity.com/paper/2305.12600/) (2023)
- [Learning Multimodal Graph-to-Graph Translation for Molecular Optimization](https://mlsanity.com/paper/1812.01070/) (2018)
- [UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs](https://mlsanity.com/paper/2402.13630/) (2024)
- [Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling](https://mlsanity.com/paper/2304.02806/) (2023)
- [Multimodal learning with graphs](https://mlsanity.com/paper/2209.03299/) (2022)
- [Can LLM Graph Reasoning Generalize beyond Pattern Memorization?](https://mlsanity.com/paper/2406.15992/) (2024)
- [Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion](https://mlsanity.com/paper/2205.02357/) (2022)
- [FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering](https://mlsanity.com/paper/2405.13873/) (2024)
- [Multimodal Graph Learning for Generative Tasks](https://mlsanity.com/paper/2310.07478/) (2023)
- [Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering](https://mlsanity.com/paper/2410.08085/) (2024)
- [GraphAlign: Pretraining One Graph Neural Network on Multiple Graphs via Feature Alignment](https://mlsanity.com/paper/2406.02953/) (2024)
- [SCR: Training Graph Neural Networks with Consistency Regularization](https://mlsanity.com/paper/2112.04319/) (2021)

## Built on by (most cited first, 30 of 49)

- [Efficient Inference for Large Reasoning Models: A Survey](https://mlsanity.com/paper/2503.23077/) (2025)
- [EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems](https://mlsanity.com/paper/2510.13220/) (2025)
- [Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?](https://mlsanity.com/paper/2502.12206/) (2025)
- [TopicAttack: An Indirect Prompt Injection Attack via Topic Transition](https://mlsanity.com/paper/2507.13686/) (2025)
- [Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement](https://mlsanity.com/paper/2505.12684/) (2025)
- [Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance](https://mlsanity.com/paper/2507.17131/) (2025)
- [OpenMAG: A Comprehensive Benchmark for Multimodal-Attributed Graph](https://mlsanity.com/paper/2602.05576/) (2026)
- [MLaGA: Multimodal Large Language and Graph Assistant](https://mlsanity.com/paper/2506.02568/) (2025)
- [MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learning](https://mlsanity.com/paper/2601.22416/) (2026)
- [Graph-MLLM: Harnessing Multimodal Large Language Models for Multimodal Graph Learning](https://mlsanity.com/paper/2506.10282/) (2025)
- [EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning](https://mlsanity.com/paper/2601.22964/) (2026)
- [Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach](https://mlsanity.com/paper/2602.04116/) (2026)
- [Evaluating Progress in Graph Foundation Models: A Comprehensive Benchmark and New Insights](https://mlsanity.com/paper/2603.10033/) (2026)
- [Modality-free Graph In-context Alignment](https://mlsanity.com/paper/2603.13434/) (2026)
- [TMTE: Effective Multimodal Graph Learning with Task-aware Modality and Topology Co-evolution](https://mlsanity.com/paper/2603.27723/) (2026)
- [STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning](https://mlsanity.com/paper/2605.11919/) (2026)
- [GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning](https://mlsanity.com/paper/2510.04567/) (2025)
- [VL-KGE: Vision-Language Models Meet Knowledge Graph Embeddings](https://mlsanity.com/paper/2603.02435/) (2026)
- [Multimodal Graph Representation Learning with Dynamic Information Pathways](https://mlsanity.com/paper/2603.09258/) (2026)
- [CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation](https://mlsanity.com/paper/2605.11468/) (2026)
- [LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning](https://mlsanity.com/paper/2608.24795/) (2026)
- [Multimodal Representation Learning Conditioned on Semantic Relations](https://mlsanity.com/paper/2508.17497/) (2025)
- [Modality as Heterogeneity: Node Splitting and Graph Rewiring for Multimodal Graph Learning](https://mlsanity.com/paper/2602.00067/) (2026)
- [GraphVLM: Benchmarking Vision Language Models for Multimodal Graph Learning](https://mlsanity.com/paper/2603.13370/) (2026)
- [Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity](https://mlsanity.com/paper/2605.12584/) (2026)
- [Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models](https://mlsanity.com/paper/2605.13540/) (2026)
- [Context-aware Modality-Topology Co-Alignment for Multimodal Attributed Graphs](https://mlsanity.com/paper/2606.14172/) (2026)
- [FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning](https://mlsanity.com/paper/2606.32016/) (2026)
- [Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework](https://mlsanity.com/paper/2607.15687/) (2026)
- [One Model, Many Graphs: Learning over Attributed Graphs across Heterogeneous Modalities with Vision-Language Models](https://mlsanity.com/paper/2607.19128/) (2026)

## Abstract (arXiv)

Existing foundation models, such as CLIP, aim to learn a unified embedding space for multimodal data, enabling a wide range of downstream web-based applications like search, recommendation, and content classification. However, these models often overlook the inherent graph structures in multimodal datasets, where entities and their relationships are crucial. Multimodal graphs (MMGs) represent such graphs where each node is associated with features from different modalities, while the edges capture the relationships between these entities. On the other hand, existing graph foundation models primarily focus on text-attributed graphs (TAGs) and are not designed to handle the complexities of MMGs. To address these limitations, we propose UniGraph2, a novel cross-domain graph foundation model that enables general representation learning on MMGs, providing a unified embedding space. UniGraph2 employs modality-specific encoders alongside a graph neural network (GNN) to learn a unified low-dimensional embedding space that captures both the multimodal information and the underlying graph structure. We propose a new cross-domain multi-graph pre-training algorithm at scale to ensure effective transfer learning across diverse graph domains and modalities. Additionally, we adopt a Mixture of Experts (MoE) component to align features from different domains and modalities, ensuring coherent and robust embeddings that unify the information across modalities. Extensive experiments on a variety of multimodal graph tasks demonstrate that UniGraph2 significantly outperforms state-of-the-art models in tasks such as representation learning, transfer learning, and multimodal generative tasks, offering a scalable and flexible solution for learning on MMGs.