When Graph meets Multimodal: Benchmarking and Meditating on Multimodal Attributed Graphs Learning

• URL: http://arxiv.org/abs/2410.09132v2
• Date: Thu, 27 Feb 2025 14:51:24 GMT
• Title: When Graph meets Multimodal: Benchmarking and Meditating on Multimodal Attributed Graphs Learning
• Authors: Hao Yan, Chaozhuo Li, Jun Yin, Zhigang Yu, Weihao Han, Mingzheng Li, Zhengxin Zeng, Hao Sun, Senzhang Wang,
• Abstract summary: Multimodal Attributed Graphs (MAGs) are ubiquitous in real-world applications, encompassing extensive knowledge through multimodal attributes attached to nodes.<n>Despite its potential to advance diverse research fields like social networks and e-commerce, MAG representation learning (MAGRL) remains underexplored.<n>We first propose MAGB, a comprehensive MAG benchmark dataset, featuring curated graphs from various domains with both textual and visual attributes.
• Score: 28.555788831123447
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Attributed Graphs (MAGs) are ubiquitous in real-world applications, encompassing extensive knowledge through multimodal attributes attached to nodes (e.g., texts and images) and topological structure representing node interactions. Despite its potential to advance diverse research fields like social networks and e-commerce, MAG representation learning (MAGRL) remains underexplored due to the lack of standardized datasets and evaluation frameworks. In this paper, we first propose MAGB, a comprehensive MAG benchmark dataset, featuring curated graphs from various domains with both textual and visual attributes. Based on MAGB dataset, we further systematically evaluate two mainstream MAGRL paradigms: $\textit{GNN-as-Predictor}$, which integrates multimodal attributes via Graph Neural Networks (GNNs), and $\textit{VLM-as-Predictor}$, which harnesses Vision Language Models (VLMs) for zero-shot reasoning. Extensive experiments on MAGB reveal following critical insights: $\textit{(i)}$ Modality significances fluctuate drastically with specific domain characteristics. $\textit{(ii)}$ Multimodal embeddings can elevate the performance ceiling of GNNs. However, intrinsic biases among modalities may impede effective training, particularly in low-data scenarios. $\textit{(iii)}$ VLMs are highly effective at generating multimodal embeddings that alleviate the imbalance between textual and visual attributes. These discoveries, which illuminate the synergy between multimodal attributes and graph topologies, contribute to reliable benchmarks, paving the way for future MAG research. The MAGB dataset and evaluation pipeline are publicly available at https://github.com/sktsherlock/MAGB.

Related papers

• UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs [34.48393396390799]
  We propose a novel cross-domain graph foundation model that enables general representation learning on multimodal graphs. UniGraph2 employs modality-specific encoders alongside a graph neural network (GNN) to learn a unified low-dimensional embedding space. We show that UniGraph2 significantly outperforms state-of-the-art models in tasks such as representation learning, transfer learning, and multimodal generative tasks.
  arXiv  Detail & Related papers  (2025-02-02T14:04:53Z)
• MINIMA: Modality Invariant Image Matching [52.505282811925454]
  We present MINIMA, a unified image matching framework for multiple cross-modal cases. We scale up the modalities from cheap but rich RGB-only matching data, by means of generative models. With MD-syn, we can directly train any advanced matching pipeline on randomly selected modality pairs to obtain cross-modal ability.
  arXiv  Detail & Related papers  (2024-12-27T02:39:50Z)
• Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation [59.4356484322228]
  Graph Neural Networks (GNNs) have shown promising performance in this domain. We propose GNNs with Modality-Independent Receptive Fields, which employ separate GNNs with independent receptive fields. Our results indicate that the optimal $K$ for certain modalities on specific datasets can be as low as 1 or 2, which may restrict the GNNs' capacity to capture global information.
  arXiv  Detail & Related papers  (2024-12-18T16:12:26Z)
• Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision? [62.12375949429938]
  Building transferable Graph Neural Networks (GNNs) with CLIP pipeline is challenging because of three fundamental issues. We leverage multi-modal prompt learning to effectively adapt pre-trained GNN to downstream tasks and data. Our new paradigm embeds the graphs directly in the same space as the Large Language Models (LLMs) by learning both graph prompts and text prompts simultaneously.
  arXiv  Detail & Related papers  (2024-12-11T08:03:35Z)
• MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding [59.41495657570397]
  This dataset includes figures such as schematic diagrams, simulated images, macroscopic/microscopic photos, and experimental visualizations. We developed benchmarks for scientific figure captioning and multiple-choice questions, evaluating six proprietary and over ten open-source models. The dataset and benchmarks will be released to support further research.
  arXiv  Detail & Related papers  (2024-07-06T00:40:53Z)
• Multimodal Graph Benchmark [36.75510196380185]
  Multimodal Graph Benchmark (MM-GRAPH) is first comprehensive multi-modal graph benchmark that incorporates both textual and visual information. MM-GRAPH consists of five graph learning datasets of various scales that are appropriate for different learning tasks. MM-GRAPH aims to foster research on multimodal graph learning and drive the development of more advanced and robust graph learning algorithms.
  arXiv  Detail & Related papers  (2024-06-24T05:14:09Z)
• Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights [44.11628188443046]
  A Graph Foundation Model (GFM) can work well across different graphs and tasks with a unified backbone. Inspired by multi-modal models that align different modalities with natural language, the text has recently been adopted to provide a unified feature space for diverse graphs. Despite the great potential of these text-space GFMs, current research in this field is hampered by two problems.
  arXiv  Detail & Related papers  (2024-06-15T19:56:21Z)
• MyGO: Discrete Modality Information as Fine-Grained Tokens for Multi-modal Knowledge Graph Completion [51.80447197290866]
  We introduce MyGO to process, fuse, and augment the fine-grained modality information from MMKGs. MyGO tokenizes multi-modal raw data as fine-grained discrete tokens and learns entity representations with a cross-modal entity encoder. Experiments on standard MMKGC benchmarks reveal that our method surpasses 20 of the latest models.
  arXiv  Detail & Related papers  (2024-04-15T05:40:41Z)
• NativE: Multi-modal Knowledge Graph Completion in the Wild [51.80447197290866]
  We propose a comprehensive framework NativE to achieve MMKGC in the wild. NativE proposes a relation-guided dual adaptive fusion module that enables adaptive fusion for any modalities. We construct a new benchmark called WildKGC with five datasets to evaluate our method.
  arXiv  Detail & Related papers  (2024-03-28T03:04:00Z)
• Learning on Multimodal Graphs: A Survey [6.362513821299131]
  Multimodal data pervades various domains, including healthcare, social media, and transportation. multimodal graph learning (MGL) is essential for successful artificial intelligence (AI) applications.
  arXiv  Detail & Related papers  (2024-02-07T23:50:00Z)
• ADAMM: Anomaly Detection of Attributed Multi-graphs with Metadata: A Unified Neural Network Approach [39.211176955683285]
  We propose ADAMM, a novel graph neural network model that handles directed multi-graphs. ADAMM fuses metadata and graph-level representation learning through an unsupervised anomaly detection objective.
  arXiv  Detail & Related papers  (2023-11-13T14:19:36Z)
• Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation [68.13453771001522]
  We propose a multimodal intensive ZSL framework that matches regions of images with corresponding semantic embeddings. We conduct extensive experiments and evaluate our model on large-scale real-world data.
  arXiv  Detail & Related papers  (2023-06-14T13:07:48Z)
• Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling [96.75821232222201]
  Existing research on multimodal relation extraction (MRE) faces two co-existing challenges, internal-information over-utilization and external-information under-exploitation. We propose a novel framework that simultaneously implements the idea of internal-information screening and external-information exploiting.
  arXiv  Detail & Related papers  (2023-05-19T14:56:57Z)
• MuG: A Multimodal Classification Benchmark on Game Data with Tabular, Textual, and Visual Fields [26.450463943664822]
  We propose a multimodal classification benchmark MuG with eight datasets that allows researchers to evaluate and improve their models. We conduct multi-aspect data analysis to provide insights into the benchmark, including label balance ratios, percentages of missing features, distributions of data within each modality, and the correlations between labels and input modalities.
  arXiv  Detail & Related papers  (2023-02-06T18:09:06Z)
• Learnable Graph Convolutional Network and Feature Fusion for Multi-view Learning [30.74535386745822]
  This paper proposes a joint deep learning framework called Learnable Graph Convolutional Network and Feature Fusion (LGCN-FF) It consists of two stages: feature fusion network and learnable graph convolutional network. The proposed LGCN-FF is validated to be superior to various state-of-the-art methods in multi-view semi-supervised classification.
  arXiv  Detail & Related papers  (2022-11-16T19:07:12Z)
• MMGA: Multimodal Learning with Graph Alignment [8.349066399479938]
  We propose MMGA, a novel multimodal pre-training framework to incorporate information from graph (social network), image and text modalities on social media. In MMGA, a multi-step graph alignment mechanism is proposed to add the self-supervision from graph modality to optimize the image and text encoders. We release our dataset, the first social media multimodal dataset with graph, of 60,000 users labeled with specific topics based on 2 million posts to facilitate future research.
  arXiv  Detail & Related papers  (2022-10-18T15:50:31Z)
• Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion [112.27103169303184]
  Multimodal Knowledge Graphs (MKGs) organize visual-text factual knowledge. MKGformer can obtain SOTA performance on four datasets of multimodal link prediction, multimodal RE, and multimodal NER.
  arXiv  Detail & Related papers  (2022-05-04T23:40:04Z)
• Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction [123.20238648121445]
  We propose a new self-supervised learning framework, Graph Information Aided Node feature exTraction (GIANT) GIANT makes use of the eXtreme Multi-label Classification (XMC) formalism, which is crucial for fine-tuning the language model based on graph information. We demonstrate the superior performance of GIANT over the standard GNN pipeline on Open Graph Benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-29T19:55:12Z)
• More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification [43.35966675372692]
  We show how to train deep networks and build the network architecture. In particular, we show different fusion strategies as well as how to train deep networks and build the network architecture. Our framework is not only limited to pixel-wise classification tasks but also applicable to spatial information modeling with convolutional neural networks (CNNs)
  arXiv  Detail & Related papers  (2020-08-12T17:45:25Z)
• A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation [131.33610549540043]
  We propose a novel graph-based multi-modal fusion encoder for NMT. We first represent the input sentence and image using a unified multi-modal graph. We then stack multiple graph-based multi-modal fusion layers that iteratively perform semantic interactions to learn node representations.
  arXiv  Detail & Related papers  (2020-07-17T04:06:09Z)

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.