Graph-to-Text Generation with Dynamic Structure Pruning

• URL: http://arxiv.org/abs/2209.07258v1
• Date: Thu, 15 Sep 2022 12:48:10 GMT
• Title: Graph-to-Text Generation with Dynamic Structure Pruning
• Authors: Liang Li, Ruiying Geng, Bowen Li, Can Ma, Yinliang Yue, Binhua Li, and Yongbin Li
• Abstract summary: We propose a Structure-Aware Cross-Attention (SACA) mechanism to re-encode the input graph representation conditioning on the newly generated context. We achieve new state-of-the-art results on two graph-to-text datasets, LDC2020T02 and ENT-DESC, with only minor increase on computational cost.
• Score: 19.37474618180399
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most graph-to-text works are built on the encoder-decoder framework with cross-attention mechanism. Recent studies have shown that explicitly modeling the input graph structure can significantly improve the performance. However, the vanilla structural encoder cannot capture all specialized information in a single forward pass for all decoding steps, resulting in inaccurate semantic representations. Meanwhile, the input graph is flatted as an unordered sequence in the cross attention, ignoring the original graph structure. As a result, the obtained input graph context vector in the decoder may be flawed. To address these issues, we propose a Structure-Aware Cross-Attention (SACA) mechanism to re-encode the input graph representation conditioning on the newly generated context at each decoding step in a structure aware manner. We further adapt SACA and introduce its variant Dynamic Graph Pruning (DGP) mechanism to dynamically drop irrelevant nodes in the decoding process. We achieve new state-of-the-art results on two graph-to-text datasets, LDC2020T02 and ENT-DESC, with only minor increase on computational cost.

Related papers

• Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention [12.409982249220812]
  We introduce Graph Attention with Structures (GRASS), a novel GNN architecture, to enhance graph relative attention. GRASS rewires the input graph by superimposing a random regular graph to achieve long-range information propagation. It also employs a novel additive attention mechanism tailored for graph-structured data.
  arXiv  Detail & Related papers  (2024-07-08T06:21:56Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• Graph Transformers without Positional Encodings [0.7252027234425334]
  We introduce Eigenformer, a Graph Transformer employing a novel spectrum-aware attention mechanism cognizant of the Laplacian spectrum of the graph. We empirically show that it achieves performance competetive with SOTA Graph Transformers on a number of standard GNN benchmarks.
  arXiv  Detail & Related papers  (2024-01-31T12:33:31Z)
• Discrete Graph Auto-Encoder [52.50288418639075]
  We introduce a new framework named Discrete Graph Auto-Encoder (DGAE) We first use a permutation-equivariant auto-encoder to convert graphs into sets of discrete latent node representations. In the second step, we sort the sets of discrete latent representations and learn their distribution with a specifically designed auto-regressive model.
  arXiv  Detail & Related papers  (2023-06-13T12:40:39Z)
• Self-Attention in Colors: Another Take on Encoding Graph Structure in Transformers [25.683127388426175]
  We introduce a novel self-attention mechanism, which we call CSA (Chromatic Self-Attention) We showcase CSA in a fully-attentional graph Transformer CGT (Chromatic Graph Transformer)
  arXiv  Detail & Related papers  (2023-04-21T13:08:53Z)
• GraphMAE: Self-Supervised Masked Graph Autoencoders [52.06140191214428]
  We present a masked graph autoencoder GraphMAE that mitigates issues for generative self-supervised graph learning. We conduct extensive experiments on 21 public datasets for three different graph learning tasks. The results manifest that GraphMAE--a simple graph autoencoder with our careful designs--can consistently generate outperformance over both contrastive and generative state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-05-22T11:57:08Z)
• Structure-Aware Transformer for Graph Representation Learning [7.4124458942877105]
  We show that node representations generated by the Transformer with positional encoding do not necessarily capture structural similarity between them. We propose the Structure-Aware Transformer, a class of simple and flexible graph transformers built upon a new self-attention mechanism. Our framework can leverage any existing GNN to extract the subgraph representation, and we show that it systematically improves performance relative to the base GNN model.
  arXiv  Detail & Related papers  (2022-02-07T09:53:39Z)
• Structural Information Preserving for Graph-to-Text Generation [59.00642847499138]
  The task of graph-to-text generation aims at producing sentences that preserve the meaning of input graphs. We propose to tackle this problem by leveraging richer training signals that can guide our model for preserving input information. Experiments on two benchmarks for graph-to-text generation show the effectiveness of our approach over a state-of-the-art baseline.
  arXiv  Detail & Related papers  (2021-02-12T20:09:01Z)
• Promoting Graph Awareness in Linearized Graph-to-Text Generation [72.83863719868364]
  We study the ability of linearized models to encode local graph structures. Our findings motivate solutions to enrich the quality of models' implicit graph encodings. We find that these denoising scaffolds lead to substantial improvements in downstream generation in low-resource settings.
  arXiv  Detail & Related papers  (2020-12-31T18:17:57Z)
• Dirichlet Graph Variational Autoencoder [65.94744123832338]
  We present Dirichlet Graph Variational Autoencoder (DGVAE) with graph cluster memberships as latent factors. Motivated by the low pass characteristics in balanced graph cut, we propose a new variant of GNN named Heatts to encode the input graph into cluster memberships.
  arXiv  Detail & Related papers  (2020-10-09T07:35:26Z)
• Graph-Aware Transformer: Is Attention All Graphs Need? [5.240000443825077]
  GRaph-Aware Transformer (GRAT) is first Transformer-based model which can encode and decode whole graphs in end-to-end fashion. GRAT has shown very promising results including state-of-the-art performance on 4 regression tasks in QM9 benchmark.
  arXiv  Detail & Related papers  (2020-06-09T12:13:56Z)

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.