Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning

• URL: http://arxiv.org/abs/2204.04813v1
• Date: Mon, 11 Apr 2022 00:58:27 GMT
• Title: Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning
• Authors: Swarnadeep Saha, Prateek Yadav, Mohit Bansal
• Abstract summary: We study pre-trained language models that generate explanation graphs in an end-to-end manner. We propose simple yet effective ways of graph perturbations via node and edge edit operations. Our methods lead to significant improvements in both structural and semantic accuracy of explanation graphs.
• Score: 84.35102534158621
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pre-trained sequence-to-sequence language models have led to widespread success in many natural language generation tasks. However, there has been relatively less work on analyzing their ability to generate structured outputs such as graphs. Unlike natural language, graphs have distinct structural and semantic properties in the context of a downstream NLP task, e.g., generating a graph that is connected and acyclic can be attributed to its structural constraints, while the semantics of a graph can refer to how meaningfully an edge represents the relation between two node concepts. In this work, we study pre-trained language models that generate explanation graphs in an end-to-end manner and analyze their ability to learn the structural constraints and semantics of such graphs. We first show that with limited supervision, pre-trained language models often generate graphs that either violate these constraints or are semantically incoherent. Since curating large amount of human-annotated graphs is expensive and tedious, we propose simple yet effective ways of graph perturbations via node and edge edit operations that lead to structurally and semantically positive and negative graphs. Next, we leverage these graphs in different contrastive learning models with Max-Margin and InfoNCE losses. Our methods lead to significant improvements in both structural and semantic accuracy of explanation graphs and also generalize to other similar graph generation tasks. Lastly, we show that human errors are the best negatives for contrastive learning and also that automatically generating more such human-like negative graphs can lead to further improvements. Our code and models are publicly available at https://github.com/swarnaHub/ExplagraphGen

Related papers

• Robust Graph Structure Learning under Heterophily [12.557639223778722]
  We propose a novel robust graph structure learning method to achieve a high-quality graph from heterophilic data for downstream tasks. We first apply a high-pass filter to make each node more distinctive from its neighbors by encoding structure information into the node features. Then, we learn a robust graph with an adaptive norm characterizing different levels of noise.
  arXiv  Detail & Related papers  (2024-03-06T12:29:13Z)
• Graph Generation with Diffusion Mixture [57.78958552860948]
  Generation of graphs is a major challenge for real-world tasks that require understanding the complex nature of their non-Euclidean structures. We propose a generative framework that models the topology of graphs by explicitly learning the final graph structures of the diffusion process.
  arXiv  Detail & Related papers  (2023-02-07T17:07:46Z)
• Spectral Augmentations for Graph Contrastive Learning [50.149996923976836]
  Contrastive learning has emerged as a premier method for learning representations with or without supervision. Recent studies have shown its utility in graph representation learning for pre-training. We propose a set of well-motivated graph transformation operations to provide a bank of candidates when constructing augmentations for a graph contrastive objective.
  arXiv  Detail & Related papers  (2023-02-06T16:26:29Z)
• State of the Art and Potentialities of Graph-level Learning [54.68482109186052]
  Graph-level learning has been applied to many tasks including comparison, regression, classification, and more. Traditional approaches to learning a set of graphs rely on hand-crafted features, such as substructures. Deep learning has helped graph-level learning adapt to the growing scale of graphs by extracting features automatically and encoding graphs into low-dimensional representations.
  arXiv  Detail & Related papers  (2023-01-14T09:15:49Z)
• Graph Self-supervised Learning with Accurate Discrepancy Learning [64.69095775258164]
  We propose a framework that aims to learn the exact discrepancy between the original and the perturbed graphs, coined as Discrepancy-based Self-supervised LeArning (D-SLA) We validate our method on various graph-related downstream tasks, including molecular property prediction, protein function prediction, and link prediction tasks, on which our model largely outperforms relevant baselines.
  arXiv  Detail & Related papers  (2022-02-07T08:04:59Z)
• ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning [65.15423587105472]
  We present a new generative and structured commonsense-reasoning task (and an associated dataset) of explanation graph generation for stance prediction. Specifically, given a belief and an argument, a model has to predict whether the argument supports or counters the belief and also generate a commonsense-augmented graph that serves as non-trivial, complete, and unambiguous explanation for the predicted stance. A significant 83% of our graphs contain external commonsense nodes with diverse structures and reasoning depths.
  arXiv  Detail & Related papers  (2021-04-15T17:51:36Z)
• Generating a Doppelganger Graph: Resembling but Distinct [5.618335078130568]
  We propose an approach to generating a doppelganger graph that resembles a given one in many graph properties. The approach is an orchestration of graph representation learning, generative adversarial networks, and graph realization algorithms.
  arXiv  Detail & Related papers  (2021-01-23T22:08:27Z)
• Towards Interpretable Multi-Task Learning Using Bilevel Programming [18.293397644865454]
  Interpretable Multi-Task Learning can be expressed as learning a sparse graph of the task relationship based on the prediction performance of the learned models. We show empirically how the induced sparse graph improves the interpretability of the learned models and their relationship on synthetic and real data, without sacrificing generalization performance.
  arXiv  Detail & Related papers  (2020-09-11T15:04:27Z)
• Non-Parametric Graph Learning for Bayesian Graph Neural Networks [35.88239188555398]
  We propose a novel non-parametric graph model for constructing the posterior distribution of graph adjacency matrices. We demonstrate the advantages of this model in three different problem settings: node classification, link prediction and recommendation.
  arXiv  Detail & Related papers  (2020-06-23T21:10:55Z)

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.