Mapping Text to Multiplex Graph: Prompt Compression as Lévy Walk-Guided Graph Pruning

• URL: http://arxiv.org/abs/2607.01241v1
• Date: Mon, 04 May 2026 01:41:31 GMT
• Title: Mapping Text to Multiplex Graph: Prompt Compression as Lévy Walk-Guided Graph Pruning
• Abstract summary: RAGP formulates prompt compression as Redundancy-Aware Graph Pruning on a multiplex graph.<n> Experiments on LongBench show that RAGP achieves an average score of 49.3 under a 4x compression ratio.
• Score: 55.43705665875779
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing prompt compression methods treat text as flat token sequences, failing to capture the distributed nature of important information, which is often spread across multiple locations and connected through both local syntactic dependencies and global semantic relations. Such relational structure is naturally represented as a graph, where tokens or sentences become nodes and their dependencies become edges. To this end, we propose RAGP, which formulates prompt compression as Redundancy-Aware Graph Pruning on a multiplex graph that jointly models fine-grained attention-based dependencies and coarse-grained semantic relations. To efficiently identify non-redundant nodes in this heterogeneous structure (dense local subgraphs and sparse global connections), we employ Levy walks whose heavy-tailed step distribution naturally balances local exploitation with global exploration. Experiments on LongBench show that RAGP achieves an average score of 49.3 under a 4x compression ratio, outperforming existing LLM-based compression methods, such as LongLLMLingua, which attains 48.8 at a 3x compression ratio. Besides, RAGP also surpasses state-of-the-art vision-based text compression paradigms on multiple tasks. The code is available at https://anonymous.4open.science/r/RAGP-B0CB.

Related papers

• Columnar-Embedder: A Biologically Inspired Cortical Architecture for Binary Sparse Distributed Graph Representations [0.0]
  We present the Columnar-Embedder architecture for learning binary Sparse Distributed Representations of graph nodes.<n>The architecture exhibits portability, resilience to noise, and robustness to data corruption.<n>Across five graph benchmarks, the performance of SDRs is competitive with that of real-valued dense embeddings.
  arXiv  Detail & Related papers  (2026-08-12T03:31:39Z)
• AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation [3.6194630559312113]
  GraphRAG is an extension of retrieval-augmented generation (RAG) that supports large language models (LLMs) by referring to graph-structured data as external knowledge.<n>We tackle this issue by introducing the it Adaptive-masking for Graph Embedding (AGE).<n>AGE employs a Transformer in a mask-based self-supervised learning (SSL) approach, addressing the latent feature misalignment.
  arXiv  Detail & Related papers  (2026-06-30T01:23:09Z)
• STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning [48.96526409527749]
  Federated graph learning (FGL) enables collaborative training on graph data across multiple clients.<n>The key challenge is that clients from different modality domains may not share a common semantic space.<n>We propose textbfSTAGE, a protocol-first framework for MM-FGL.
  arXiv  Detail & Related papers  (2026-05-12T10:35:43Z)
• Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression [55.51959317490934]
  Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding.<n>We argue that graphs inherently contain rich structural and semantic information, and that their effective exploitation can unlock potential gains in LLMs reasoning performance.<n>We propose Homophily-aware Structural and Semantic Compression for LLMs (HS2C), a framework centered on exploiting graph homophily.
  arXiv  Detail & Related papers  (2026-01-13T03:35:18Z)
• Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks [16.5175121704107]
  Graph Neural Networks learn on graph-structured data by iteratively aggregating local neighborhood information.<n>In this work we inject randomized global embeddings of node features into standard GNNs, enabling them to efficiently capture long-range dependencies.<n> Experimental results on real-world graph learning tasks confirm that this strategy consistently improves performance over baseline GNNs.
  arXiv  Detail & Related papers  (2025-11-05T19:41:56Z)
• Schreier-Coset Graph Propagation [2.0339465062586566]
  This work introduces Schrier-Coset Graph Propagation (SCGP), a group-theoretic augmentation method that enriches node features through Schreier-coset embeddings without altering the input graph topology.<n>SCGP embeds bottleneck-free connectivity patterns into a compact feature space, improving long-range message passing while maintaining computational efficiency.
  arXiv  Detail & Related papers  (2025-05-15T15:14:02Z)
• Beyond Message Passing: Neural Graph Pattern Machine [50.78679002846741]
  We introduce the Neural Graph Pattern Machine (GPM), a novel framework that bypasses message passing by learning directly from graph substructures.<n>GPM efficiently extracts, encodes, and prioritizes task-relevant graph patterns, offering greater expressivity and improved ability to capture long-range dependencies.
  arXiv  Detail & Related papers  (2025-01-30T20:37:47Z)
• Semi-supervised Domain Adaptation on Graphs with Contrastive Learning and Minimax Entropy [12.209076900021621]
  Semi-supervised domain adaptation (SSDA) on graphs aims to leverage the knowledge of a labeled source graph to aid in node classification on a target graph with limited labels. This paper proposes a novel method called SemiGCL to tackle the graph textbfSemi-supervised domain adaptation with textbfGraph textbfContrastive textbfL and minimax entropy training.
  arXiv  Detail & Related papers  (2023-09-14T03:15:57Z)
• Partition and Code: learning how to compress graphs [50.29024357495154]
  "Partition and Code" framework entails three steps: first, a partitioning algorithm decomposes the graph into elementary structures, then these are mapped to the elements of a small dictionary on which we learn a probability distribution, and finally, an entropy encoder translates the representation into bits. Our algorithms are quantitatively evaluated on diverse real-world networks obtaining significant performance improvements with respect to different families of non-parametric and parametric graph compressor.
  arXiv  Detail & Related papers  (2021-07-05T11:41:16Z)
• Factorizable Graph Convolutional Networks [90.59836684458905]
  We introduce a novel graph convolutional network (GCN) that explicitly disentangles intertwined relations encoded in a graph. FactorGCN takes a simple graph as input, and disentangles it into several factorized graphs. We evaluate the proposed FactorGCN both qualitatively and quantitatively on the synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2020-10-12T03:01:40Z)

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.