Large language models on graphs: A comprehensive survey
Large language models (LLMs), such as GPT4 and LLaMA, are creating significant
advancements in natural language processing, due to their strong text encoding/decoding …
advancements in natural language processing, due to their strong text encoding/decoding …
Graph prompt learning: A comprehensive survey and beyond
Artificial General Intelligence (AGI) has revolutionized numerous fields, yet its integration
with graph data, a cornerstone in our interconnected world, remains nascent. This paper …
with graph data, a cornerstone in our interconnected world, remains nascent. This paper …
Llmrec: Large language models with graph augmentation for recommendation
The problem of data sparsity has long been a challenge in recommendation systems, and
previous studies have attempted to address this issue by incorporating side information …
previous studies have attempted to address this issue by incorporating side information …
A survey of large language models for graphs
Graphs are an essential data structure utilized to represent relationships in real-world
scenarios. Prior research has established that Graph Neural Networks (GNNs) deliver …
scenarios. Prior research has established that Graph Neural Networks (GNNs) deliver …
G-retriever: Retrieval-augmented generation for textual graph understanding and question answering
Given a graph with textual attributes, we enable users tochat with their graph': that is, to ask
questions about the graph using a conversational interface. In response to a user's …
questions about the graph using a conversational interface. In response to a user's …
Graph chain-of-thought: Augmenting large language models by reasoning on graphs
Large language models (LLMs), while exhibiting exceptional performance, suffer from
hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment …
hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment …
Knowledgeable preference alignment for llms in domain-specific question answering
Deploying large language models (LLMs) to real scenarios for domain-specific question
answering (QA) is a key thrust for LLM applications, which poses numerous challenges …
answering (QA) is a key thrust for LLM applications, which poses numerous challenges …
Breaking the trilemma of privacy, utility, and efficiency via controllable machine unlearning
Machine Unlearning (MU) algorithms have become increasingly critical due to the
imperative adherence to data privacy regulations. The primary objective of MU is to erase …
imperative adherence to data privacy regulations. The primary objective of MU is to erase …
Fairness-aware graph neural networks: A survey
Graph Neural Networks (GNNs) have become increasingly important due to their
representational power and state-of-the-art predictive performance on many fundamental …
representational power and state-of-the-art predictive performance on many fundamental …
Promptmm: Multi-modal knowledge distillation for recommendation with prompt-tuning
Multimedia online platforms (eg, Amazon, TikTok) have greatly benefited from the
incorporation of multimedia (eg, visual, textual, and acoustic) content into their personal …
incorporation of multimedia (eg, visual, textual, and acoustic) content into their personal …