2000 character limit reached
Sign Rank Limitations for Inner Product Graph Decoders
Published 6 Feb 2024 in cs.LG | (2402.06662v2)
Abstract: 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.
- Distributed large-scale natural graph factorization. Proceedings of the 22nd International Conference on World Wide Web, pp. 37–48, 2013.
- Sign rank versus vapnik-chervonenkis dimension. Sbornik: Mathematics, 208(12), 2017.
- Laplacian eigenmaps and spectral techniques for embedding and clustering. Advances in Neural Information Processing Systems, 14, 2001.
- Symmetric graph convolutional autoencoder for unsupervised graph representation learning. Advances in Neural Information Processing Systems, 26, 2013.
- Geometric deep learning: Going beyond euclidean data. IEEE Signal Processing Magazine, 34(4):18–42, 2017.
- Grarep: Learning graph representations with global structural information. Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pp. 891–900, 2015.
- Cogmol: Target-specific and selective drug design for covid-19 using deep generative models. Advances in Neural Information Processing Systems, 33:4320–4332, 2020.
- Molecular representations in ai-driven drug discovery: a review and practical guide. Journal of Cheminformatics, 12(56), 2020.
- Automatic chemical design using a data-driven continuous representation of molecules. ACS Central Science, 4(2):268––276, 2018.
- Node2vec: Scalable feature learning for networks. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 855–864, 2016.
- Learning mixed-curvature representations in product spaces. International Conference on Learning Representations, 2018.
- Hamilton, W. Graph representation learning. Synthesis Lectures on Artificial Intelligence and Machine Learning, 14(3):1–159, 2020.
- Lower bound methods for sign-rank and their limitations. Approximation, Randomization, and Combinatorial Optimization (APPROX/RANDOM 2022). Schloss Dagstuhl-Leibniz-Zentrum für Informatik, 2022.
- Low-rank sparse decomposition of graph adjacency matrices for extracting clean clusters. 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1153–1159, 2018.
- Variational graph auto-encoders. ArXiv, 2016.
- An approximation algorithm for approximation rank. 2009 24th Annual IEEE Conference on Computational Complexity, pp. 351–357, 2009.
- Neural word embedding as implicit matrix factorization. Advances in Neural Information Processing Systems, 27, 2014.
- Continuous latent spaces sampling for graph autoencoder. Applied Sciences, 13(11), 2023.
- Distributed representations of words and phrases and their compositionality. Advances in Neural Information Processing Systems, 26, 2013.
- Tudataset: A collection of benchmark datasets for learning with graphs. Graph Representation Learning and Beyond, ICML 2020 Workshop, 2020.
- Asymmetric transitivity preserving graph embedding. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1105–1114, 2016.
- Adversarially regularized graph autoencoder for graph embedding. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, pp. 2609–2615, 2018.
- Symmetric graph convolutional autoencoder for unsupervised graph representation learning. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 6518–6527, 2019.
- Deepwalk: Online learning of social representations. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 14:701–710, 2014.
- Representation tradeoffs for hyperbolic embeddings. Proceedings of the 35th International Conference on Machine Learning, (80):4460–4469, 2018.
- Mgae: Marginalized graph autoencoder for graph clustering. Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, (10):889–898, 2017.
- Moleculenet: A benchmark for molecular machine learning. Chemical Science, 9(2):513–530, 2018.
- Revisiting semi-supervised learning with graph embeddings. International Conference on Machine Learning, 33, 2016.
- Deep generative molecular design reshapes drug discovery. Cell Reports Medicine, 2022a.
- Accurate prediction of molecular properties and drug targets using a self-supervised image representation learning framework. Nature Machine Intelligence, 4(11):1004–1016, 2022b.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
