# Deep Structural Knowledge Exploitation and Synergy for Estimating Node Importance Value on Heterogeneous Information Networks

arXiv: https://arxiv.org/abs/2402.12411 · HTML: https://mlsanity.com/paper/2402.12411/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 61 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding](https://mlsanity.com/paper/2002.01680/) (2020)
- [PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning](https://mlsanity.com/paper/2211.11682/) (2022)
- [Do Large Language Models Know about Facts?](https://mlsanity.com/paper/2310.05177/) (2023)
- [Spectral Feature Augmentation for Graph Contrastive Learning and Beyond](https://mlsanity.com/paper/2212.01026/) (2022)
- [Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks](https://mlsanity.com/paper/1905.08865/) (2019)
- [SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction](https://mlsanity.com/paper/2004.02438/) (2020)
- [Statistical, Robustness, and Computational Guarantees for Sliced Wasserstein Distances](https://mlsanity.com/paper/2210.09160/) (2022)
- [Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation](https://mlsanity.com/paper/2108.06468/) (2021)
- [CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checking](https://mlsanity.com/paper/2206.11863/) (2022)
- [Unsupervised Text Generation by Learning from Search](https://mlsanity.com/paper/2007.08557/) (2020)
- [Semi-supervised Relation Extraction via Incremental Meta Self-Training](https://mlsanity.com/paper/2010.16410/) (2020)
- [Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction](https://mlsanity.com/paper/2109.06415/) (2021)
- [Dynamically Expandable Graph Convolution for Streaming Recommendation](https://mlsanity.com/paper/2303.11700/) (2023)
- [Unsupervised Hashing with Contrastive Information Bottleneck](https://mlsanity.com/paper/2105.06138/) (2021)
- [A Unified Strategy for Multilingual Grammatical Error Correction with Pre-trained Cross-Lingual Language Model](https://mlsanity.com/paper/2201.10707/) (2022)
- [Attentive Knowledge-aware Graph Convolutional Networks with Collaborative Guidance for Personalized Recommendation](https://mlsanity.com/paper/2109.02046/) (2021)
- [Learning Binarized Graph Representations with Multi-faceted Quantization Reinforcement for Top-K Recommendation](https://mlsanity.com/paper/2206.02115/) (2022)
- [MultiImport: Inferring Node Importance in a Knowledge Graph from Multiple Input Signals](https://mlsanity.com/paper/2006.12001/) (2020)
- [Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender System](https://mlsanity.com/paper/2308.07760/) (2023)
- [WSFE: Wasserstein Sub-graph Feature Encoder for Effective User Segmentation in Collaborative Filtering](https://mlsanity.com/paper/2305.04410/) (2023)
- [A Literature Review of Recent Graph Embedding Techniques for Biomedical Data](https://mlsanity.com/paper/2101.06569/) (2021)
- [Efficient Document Retrieval by End-to-End Refining and Quantizing BERT Embedding with Contrastive Product Quantization](https://mlsanity.com/paper/2210.17170/) (2022)

## Built on by (most cited first, 9 of 9)

- [Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking](https://mlsanity.com/paper/2503.04636/) (2025)
- [DP-DGAD: A Generalist Dynamic Graph Anomaly Detector with Dynamic Prototypes](https://mlsanity.com/paper/2508.00664/) (2025)
- [Semi-supervised Node Importance Estimation with Informative Distribution Modeling for Uncertainty Regularization](https://mlsanity.com/paper/2503.20697/) (2025)
- [CSPO: Cross-Market Synergistic Stock Price Movement Forecasting with Pseudo-volatility Optimization](https://mlsanity.com/paper/2503.22740/) (2025)
- [Node Importance Estimation Leveraging LLMs for Semantic Augmentation in Knowledge Graphs](https://mlsanity.com/paper/2412.00478/) (2024)
- [Critical Nodes Identification in Complex Networks: A Survey](https://mlsanity.com/paper/2507.06164/) (2025)
- [TRACE: Intra-visit Clinical Event Nowcasting via Effective Patient Trajectory Encoding](https://mlsanity.com/paper/2503.23072/) (2025)
- [Explaining Synergistic Effects in Social Recommendations](https://mlsanity.com/paper/2601.18151/) (2026)
- [Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption](https://mlsanity.com/paper/2605.30089/) (2026)

## Abstract (arXiv)

Node importance estimation problem has been studied conventionally with homogeneous network topology analysis. To deal with network heterogeneity, a few recent methods employ graph neural models to automatically learn diverse sources of information. However, the major concern revolves around that their full adaptive learning process may lead to insufficient information exploration, thereby formulating the problem as the isolated node value prediction with underperformance and less interpretability. In this work, we propose a novel learning framework: SKES. Different from previous automatic learning designs, SKES exploits heterogeneous structural knowledge to enrich the informativeness of node representations. Based on a sufficiently uninformative reference, SKES estimates the importance value for any input node, by quantifying its disparity against the reference. This establishes an interpretable node importance computation paradigm. Furthermore, SKES dives deep into the understanding that "nodes with similar characteristics are prone to have similar importance values" whilst guaranteeing that such informativeness disparity between any different nodes is orderly reflected by the embedding distance of their associated latent features. Extensive experiments on three widely-evaluated benchmarks demonstrate the performance superiority of SKES over several recent competing methods.