Sign Rank Limitations for Inner Product Graph Decoders
Not on the map. Why?
Abstract (arXiv)
Inner product-based decoders are among the most influential frameworks used to extract meaningful data from latent embeddings. However, such decoders have shown limitations in representation capacity in numerous works within the literature, which have been particularly notable in graph reconstruction problems. In this paper, we provide the first theoretical elucidation of this pervasive phenomenon in graph data, and suggest straightforward modifications to circumvent this issue without deviating from the inner product framework.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 28 references that are in the map. First posted on arXiv 6 Feb 2024.
Builds on
11 of 28 references.
References · 11
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
- 2014DeepWalk: Online Learning of Social Representationscited by 1,547
- 2016Variational Graph Auto-Encoderscited by 1,382
- 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
- 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
- 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
- 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
- 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
- 2018Representation Tradeoffs for Hyperbolic Embeddingscited by 206
- 2019Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learningcited by 94
Built on by
Not cited yet.