VN Network: Embedding Newly Emerging Entities with Virtual Neighbors

• URL: http://arxiv.org/abs/2402.14033v1
• Date: Wed, 21 Feb 2024 03:04:34 GMT
• Title: VN Network: Embedding Newly Emerging Entities with Virtual Neighbors
• Authors: Yongquan He and Zihan Wang and Peng Zhang and Zhaopeng Tu and Zhaochun Ren
• Abstract summary: We propose a novel framework, namely Virtual Neighbor (VN) network, to address three key challenges. First, to reduce the neighbor sparsity problem, we introduce the concept of the virtual neighbors inferred by rules. Secondly, we identify both logic and symmetric path rules to capture complex patterns.
• Score: 59.906332784508706
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Embedding entities and relations into continuous vector spaces has attracted a surge of interest in recent years. Most embedding methods assume that all test entities are available during training, which makes it time-consuming to retrain embeddings for newly emerging entities. To address this issue, recent works apply the graph neural network on the existing neighbors of the unseen entities. In this paper, we propose a novel framework, namely Virtual Neighbor (VN) network, to address three key challenges. Firstly, to reduce the neighbor sparsity problem, we introduce the concept of the virtual neighbors inferred by rules. And we assign soft labels to these neighbors by solving a rule-constrained problem, rather than simply regarding them as unquestionably true. Secondly, many existing methods only use one-hop or two-hop neighbors for aggregation and ignore the distant information that may be helpful. Instead, we identify both logic and symmetric path rules to capture complex patterns. Finally, instead of one-time injection of rules, we employ an iterative learning scheme between the embedding method and virtual neighbor prediction to capture the interactions within. Experimental results on two knowledge graph completion tasks demonstrate that our VN network significantly outperforms state-of-the-art baselines. Furthermore, results on Subject/Object-R show that our proposed VN network is highly robust to the neighbor sparsity problem.

Related papers

• LinSATNet: The Positive Linear Satisfiability Neural Networks [116.65291739666303]
  This paper studies how to introduce the popular positive linear satisfiability to neural networks. We propose the first differentiable satisfiability layer based on an extension of the classic Sinkhorn algorithm for jointly encoding multiple sets of marginal distributions.
  arXiv  Detail & Related papers  (2024-07-18T22:05:21Z)
• NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matching [31.61255365182462]
  We present Neural Correspondence Prior (NCP), a new paradigm for computing correspondences between 3D shapes. Our approach is fully unsupervised and can lead to high-quality correspondences even in challenging cases. We show that NCP is data-efficient, fast, and state-of-the-art results on many tasks.
  arXiv  Detail & Related papers  (2023-01-14T07:22:18Z)
• Affordance detection with Dynamic-Tree Capsule Networks [5.847547503155588]
  Affordance detection from visual input is a fundamental step in autonomous robotic manipulation. We introduce the first affordance detection network based on dynamic tree-structured capsules for sparse 3D point clouds. Our algorithm is superior to current affordance detection methods when faced with grasping previously unseen objects.
  arXiv  Detail & Related papers  (2022-11-09T21:14:08Z)
• Spatial Autoregressive Coding for Graph Neural Recommendation [38.66151035948021]
  shallow models and deep Graph Neural Networks (GNNs) fail to adequately exploit neighbor proximity in sampled subgraphs or sequences. In this paper, we propose a novel framework SAC, namely Spatial Autoregressive Coding, to solve the above problems in a unified way. Experimental results on both public recommendation datasets and a real scenario web-scale dataset demonstrate the superiority of SAC compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-05-19T12:00:01Z)
• Monkey Business: Reinforcement learning meets neighborhood search for Virtual Network Embedding [0.8312192184427761]
  We consider the Virtual Network Embedding (VNE) problem for 5G networks slicing. Inspired by the Nested Rollout Policy Adaptation (NRPA) algorithm, we propose a new algorithm that we call Neighborhood Enhanced Policy Adaptation (NEPA) NEPA learns by combining NRPA with Neighbordhood Search in a frugal manner which improves only promising solutions.
  arXiv  Detail & Related papers  (2022-02-28T12:00:56Z)
• Hierarchical Prototype Networks for Continual Graph Representation Learning [90.78466005753505]
  We present Hierarchical Prototype Networks (HPNs) which extract different levels of abstract knowledge in the form of prototypes to represent the continuously expanded graphs. We show that HPNs not only outperform state-of-the-art baseline techniques but also consume relatively less memory.
  arXiv  Detail & Related papers  (2021-11-30T14:15:14Z)
• A Sequence-to-Set Network for Nested Named Entity Recognition [38.05786148160635]
  We propose a novel sequence-to-set neural network for nested NER. We use a non-autoregressive decoder to predict the final set of entities in one pass. Experimental results show that our proposed model achieves state-of-the-art on three nested NER corpora.
  arXiv  Detail & Related papers  (2021-05-19T03:10:04Z)
• Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond [97.25179345878443]
  This paper proposes a novel light-weight module, the Attentive WaveBlock (AWB) AWB can be integrated into the dual networks of mutual learning to enhance the complementarity and further depress noise in the pseudo-labels. Experiments demonstrate that the proposed method achieves state-of-the-art performance with significant improvements on multiple UDA person re-identification tasks.
  arXiv  Detail & Related papers  (2020-06-11T15:40:40Z)
• Neighborhood Matching Network for Entity Alignment [71.24217694278616]
  Neighborhood Matching Network (NMN) is a novel entity alignment framework. NMN estimates the similarities between entities to capture both the topological structure and the neighborhood difference. It first uses a novel graph sampling method to distill a discriminative neighborhood for each entity. It then adopts a cross-graph neighborhood matching module to jointly encode the neighborhood difference for a given entity pair.
  arXiv  Detail & Related papers  (2020-05-12T08:26:15Z)
• Learning multiview 3D point cloud registration [74.39499501822682]
  We present a novel, end-to-end learnable, multiview 3D point cloud registration algorithm. Our approach outperforms the state-of-the-art by a significant margin, while being end-to-end trainable and computationally less costly.
  arXiv  Detail & Related papers  (2020-01-15T03:42:14Z)

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.