The latest research innovations at all stages of the research process, from work-in-progress to recently published papers
We define “recent” as presented within one year of the workshop, e.g., the manuscript is first public available on arxiv or else no earlier than July 9, 2020.
Position or survey papers on any topics relevant to this workshop (see above)
Concretely, we ask members of the community to submit an abstract (250 words or fewer) describing the work and one or more of the following accompanying materials that describe the work in further detail. Higher quality accompanying materials improve the likelihood of acceptance and of spotlighting work with an oral presentation.
A poster (in PDF form) presenting results of work-in-progress.
A link to a blog post (e.g., distill.pub, Medium) describing results.
A workshop paper of approximately four pages in length presenting results of work-in-progress. Papers should be submitted using the NeurIPS 2021 format.
A position paper with no page limit.
A published paper in the form that it was published. We will only consider papers that were published in the year prior to this workshop.
This workshop is non-archival, and it will not have proceedings. We permit under-review or concurrent submissions. Submissions will receive one of three possible decisions:
Accept (Spotlight Presentation). The authors will be invited to present the work during the main conference, with live Q&A.
Accept (Poster Presentation). The authors will be invited to present their work as a poster during the workshop’s interactive poster sessions.
Reject. The paper will not be presented at the workshop.
Topics of Interest
Algorithms for Sparsity
Pruning both for post-training inference, and during training
Algorithms for fully sparse training (fixed or dynamic), including biologically inspired algorithms
Algorithms for ephemeral (activation) sparsity
Scaling up sparsity (e.g., large sparsely activated expert models)
Systems for Sparsity
Libraries, kernels, and compilers for accelerating sparse computation
Hardware with support for sparse computation
Theory and Science of Sparsity
When is overparameterization necessary (or not)
Optimization behavior of sparse networks
Representation ability of sparse networks
Sparsity and generalization
The stability of sparse models
Forgetting owing to sparsity, including fairness, privacy and bias concerns
Connecting neural network sparsity with traditional sparse dictionary modeling
Applications for Sparsity
Resource-efficient learning at the edge or the cloud
Data-efficient learning for sparse models
Communication-efficient distributed or federated learning with sparse models
Graph and network science applications
Our goal is to build a broad community around questions related to neural network sparsity. As such, we aim to accept all submissions that are (1) relevant to the topic area of the conference, (2) technically well-substantiated, and (3) non-trivial or previously unknown results.
Reviewing will be conducted in a single-blind fashion.