Extracting and composing robust features with denoising autoencoders
Extracting and composing robust features with denoising autoencoders is a research paper published in Proceedings of the 25th international conference on Machine learning - ICML '08 (2008). On theSindex it has a DataRank of 1.3. It has been cited 7,303 times.
Abstract
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to useful intermediate representations. We introduce and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern. This approach can be used to train autoencoders, and these denoising autoencoders can be stacked to initialize deep architectures. The algorithm can be motivated from a manifold learning and information theoretic perspective or from a generative model perspective. Comparative experiments clearly show the surprising advantage of corrupting the input of autoencoders on a pattern classification benchmark suite.
›Data sources & pipeline
FAIR Checklist
Context only (not used in score)- Has DOI
FAIR checklist signals are shown for context only and do not affect DataRank scoring.
DataRank Breakdown
Base Score Contribution
1.3
From this paper's citation signal
Citation Network Contribution
0
Citation network not refreshed for this result
This paper's DataRank is currently driven only by its base citation score. Citation network data was not refreshed for this result.
Learn more about DataRank methodology →Why this DataRank?
DataRank blends this paper's own citation count with the influence of the papers that cite it. Here, roughly 100% comes from its base citations and 0% from the citation network.
- Base score B(p)
- log1p(citation_count) — grows sub-linearly, so a paper with 1,000 citations is not 10× a paper with 100.
- Network N(p)
- Σ over citers of log1p(Cq) ÷ max(outdegreeq, 1). Being cited by a highly-cited paper with few references counts most.
- Damping factor d = 0.85
- DataRank = (1−d)·B(p) + d·N(p) — the two cards above are each already multiplied by their share.
- Self-citations excluded
- Citers sharing any OpenAlex author ID with this paper are filtered out before the network sum.
Citers are pulled from OpenAlex sorted by cited_by_count:descand capped per paper, so when the cap binds we keep the highest-signal references and the score is reproducible across reruns.