text-attributed graphs
PulseAugur coverage of text-attributed graphs — every cluster mentioning text-attributed graphs across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New research tackles text-attributed graph learning challenges
Two new research papers introduce methods and benchmarks for improving the learning capabilities of text-attributed graphs (TAGs), which combine relational structures with textual data. The first paper, "Semi-Supervised…
-
New Diffusion Language Model Unifies Text and Graph Learning
Researchers have developed TAG-DLM, a novel approach that unifies textual reasoning and graph message passing within a masked diffusion language model. This method linearizes local graph neighborhoods into token sequenc…
-
New PromptGNN-sim framework fuses GNNs and LLMs for enhanced graph learning
Researchers have introduced PromptGNN-sim, a novel framework designed to enhance the learning capabilities of Text-Attributed Graphs (TAGs) by deeply integrating Graph Neural Networks (GNNs) and Large Language Models (L…
-
New LLM Attention Method Boosts Graph Reasoning
Researchers have identified a key mechanism, termed structural distortion, that hinders Large Language Models (LLMs) from effectively reasoning over text-attributed graphs. This distortion arises from the linearization …
-
GraspLLM framework enhances LLM generalization on text-attributed graphs
Researchers have developed GraspLLM, a new framework designed to improve the generalization capabilities of Large Language Models (LLMs) when applied to text-attributed graphs (TAGs). The framework integrates graph stru…
-
ERAlign framework aligns GNN and LLM representations on text-attributed graphs
Researchers have developed ERAlign, a novel framework for aligning representations from Graph Neural Networks (GNNs) and Large Language Models (LLMs) on text-attributed graphs. This approach utilizes Energy-based Models…
-
New G2LoRA framework tackles LLM forgetting in graph learning
Researchers have introduced G2LoRA, a new framework designed to improve continual learning for large language models (LLMs) applied to text-attributed graphs. This method addresses the issue of catastrophic forgetting, …
-
New framework interprets LLM reasoning as k-means clustering
Researchers have proposed a new framework called KCoT that interprets Chain-of-Thought (CoT) reasoning in large language models as a form of clustering. This approach offers a $k$-means interpretation of how iterative r…
-
New S2Aligner framework enhances graph-text pre-training on sparse data
Researchers have developed S2Aligner, a new framework designed to improve pre-training for text-attributed graphs, particularly those with sparse textual information. This method decouples semantic alignment from struct…