REVIEW 12 cited by
LLaGA: Large Language and Graph Assistant
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Graph Neural Networks (GNNs) have empowered the advance in graph-structured data analysis. Recently, the rise of Large Language Models (LLMs) like GPT-4 has heralded a new era in deep learning. However, their application to graph data poses distinct challenges due to the inherent difficulty of translating graph structures to language. To this end, we introduce the Large Language and Graph Assistant (LLaGA), an innovative model that effectively integrates LLM capabilities to handle the complexities of graph-structured data. LLaGA retains the general-purpose nature of LLMs while adapting graph data into a format compatible with LLM input. LLaGA achieves this by reorganizing graph nodes to structure-aware sequences and then mapping these into the token embedding space through a versatile projector. LLaGA excels in versatility, generalizability and interpretability, allowing it to perform consistently well across different datasets and tasks, extend its ability to unseen datasets or tasks, and provide explanations for graphs. Our extensive experiments across popular graph benchmarks show that LLaGA delivers outstanding performance across four datasets and three tasks using one single model, surpassing state-of-the-art graph models in both supervised and zero-shot scenarios. Our code is available at \url{https://github.com/VITA-Group/LLaGA}.
Forward citations
Cited by 12 Pith papers
-
GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks
GABench provides the first agentic graph-analysis benchmark with 10,400 executable tasks, and finds existing LLM agents succeed on under 40% of complex graph tasks.
-
One Model, Many Graphs: Learning over Attributed Graphs across Heterogeneous Modalities with Vision-Language Models
OMG-VLM is a single VLM-based model that handles text-, image-, and multi-attributed graphs through structure-aware adapters, reporting gains on several node/link prediction benchmarks.
-
Harnessing Adaptive Topology Representations for Zero-Shot Graph Question Answering
DynamicTRF learns question-level preferences over eight graph representations and routes each query to the best one, improving zero-shot graph QA accuracy and output brevity on seven algorithmic and two downstream tasks.
-
Text-Attributed Graph Anomaly Detection via Multi-Scale Cross- and Uni-Modal Contrastive Learning
A joint text-graph contrastive learning framework detects anomalies in text-attributed graphs and outperforms eleven baselines across eight new datasets.
-
Graph World Model
The Graph World Model uses action nodes and graph message passing to unify multimodal and graph-structured tasks, but its 'outperforms or matches' claim is contradicted by results on Goodreads.
-
H$^2$GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs
A graph foundation model with text-encoded meta-relations and a mixture of context-adaptive transformers improves accuracy across homogeneous and heterogeneous text-attributed graphs.
-
MLaGA: Multimodal Large Language and Graph Assistant
MLaGA extends LLM-based graph reasoning from text-only graphs to multimodal graphs with image and text node attributes via a structure-aware aligner and multimodal instruction tuning.
-
UNIT: Unleash Large Language Models Potential for Graph Continual Learning
UNIT reaches SOTA graph continual learning by one-shot LLM instruction tuning plus uncertainty-aware semantic and structural class anchors that jointly set classifier weights.
-
GSTBench: A Benchmark Study on the Transferability of Graph Self-Supervised Learning
GSTBench finds that masked feature reconstruction (GraphMAE) is the only one of five graph self-supervised pretraining objectives that consistently transfers across eight datasets, while contrastive methods often perf...
-
TrustGLM: Evaluating the Robustness of GraphLLMs Against Prompt, Text, and Structure Attacks
GraphLLMs are broadly vulnerable to text, graph structure, and prompt label attacks, but the severity depends heavily on the model and dataset.
-
Graph-MLLM: Harnessing Multimodal Large Language Models for Multimodal Graph Learning
A unified comparison across six multimodal graph datasets shows that fine-tuned multimodal LLMs used as direct predictors achieve the highest node classification accuracy, even without graph structure input.
-
Masked Language Models are Good Heterogeneous Graph Generalizers
A masked language model fine-tuned on metapath-derived text and cloze-style task templates transfers across heterogeneous graph datasets better than HGNN and LLM baselines, though link prediction results are compromis...
Discussion (0). Sign in to comment.