Call for Papers

Important Dates

Deadline for submission of papers: 18th September, 2019 at 23:59 AoE

Notification of acceptance: 30th September, 2019

Submission info

Submission website: OpenReview

Page limit: 4 pages (without references, unlimited supplementary material)

Please use the NeurIPS 2019 submission format

Please make submission double blind. Submitted papers are not publicly viewable.

If you are doing a dual submission, please contact us first.

Please note that at least one author of each accepted paper must be available to present the paper at the workshop.

We suggest that authors join the NeurIPS ticket lottery in case we do not have sufficient reserved tickets for authors.

Call for Papers

Classic problems for which the input and/or output is set-valued are ubiquitous in machine learning. For example, multi-instance learning, estimating population statistics, and point cloud classification are all problem domains in which the input is set-valued. In multi-label classification the output is a set of labels, and in clustering, the output is a partition. New tasks that take sets as input are also rapidly emerging in a variety of application areas including: high energy physics, cosmology, crystallography, and art. As a natural means of succinctly capturing large collections of items, techniques for learning representations of sets and partitions have significant potential to enhance scalability, capture complex dependencies, and improve interpretability. The importance and potential of improved set processing has led to recent work on permutation invariant and equivariant representations (Ravanbakhsh et al, 2016; Zaheer et al, 2017; Ilse et al, 2018; Hartford et al, 2018; Lee et al, 2019, Cotter et al, 2019, Bloom-Reddy & Teh, 2019, and more) and continuous representations of set-based outputs and partitions (Tai and Lin, 2012; Belanger & McCallum, 2016; Wiseman et al, 2016; Caron et al, 2018; Vikram et al, 2019).


The goal of this workshop is to explore:

  • Permutation invariant and equivariant representations; empirical performance, limitations, implications, inductive biases of proposed representations of sets and partitions, as well as rich models of interaction among set elements;
  • Inference methods for predicting sets or clusterings; approaches based on gradient-descent, continuous representations, amenable to end-to-end optimization with other models;
  • New applications of set and partition-based models.


The First Workshop on Sets and Partitions, to be held as a part of the NeurIPS 2019 conference, focuses on models for tasks with set-based inputs/outputs as well as models of partitions and novel clustering methodology. The workshop welcomes both methodological and theoretical contributions, and also new applications. Connections to related problems in optimization, algorithms, theory as well as investigations of learning approaches to set/partition problems are also highly relevant to the workshop. We invite both paper submissions and submissions of open problems. We hope that the workshops will inspire further progress in this important field.

Topics

We invite two types of submissions to the workshop:

  1. contributed talks and/or posters
  2. open problems

For the latter, we request the authors to prepare a few slides that clearly present, motivate, and explain an important open problem --- the main aim here is to foster active discussion. The topics of interest for the open problem session are the same as those for regular submissions; please see below for details. In addition to open problems, we invite high quality submissions for presentation as talks or poster presentations during the workshop. We are especially interested in participants who can contribute theory / algorithms, applications. The main topics are, including, but not limited to:

  • Set Learning
    • Set Input Scalar Output
    • Set Input Set Output Regression/Distribution to Distribution Regression
    • Permutations and sequence ordering problems
    • Interactions Across Sets
    • Injecting Domain Knowledge
    • General Group Invariance and Equivariance function structure
    • Scalable learning
  • Applications of set-based models
    • Anomaly detection
    • Collaborative Filtering
    • Point Clouds
    • 3D Shape Recognition
    • Natural Language Processing such as Fine-grained Entity Type Prediction, Entity Resolution, and Relation Prediction
    • Basic Sciences: Cosmology, Using Molecular Geometry, Crystal Orientation and Property prediction, Approximating DFT Calculations
  • Clustering/Hierarchical Clustering
    • Streaming
    • Scalability
    • Gradient-Based Methods
    • Graph clustering
    • Joint representation learning
    • Hyperbolic Space Representations
  • Structured Prediction, especially multi-label classification and other tasks with unordered output spaces
  • Generative Models
    • Density Estimation
    • Bayesian Hierarchical Models
    • Deep Hierarchical Generation
    • Implicit Generation for Set Data
    • Encoders of Set Data for Conditional Generation
  • Optimization for Sets and Partitions

Point Cloud Representation, Classification & Segmentation [Image from Qi et al, 2017]

Molecular property prediction - permutation equivariance

Anomaly detection [Image from Lee et al, 2019]

Gradient based hierarchical clustering

Hierarchical clustering representations [Image from Vikram et al, 2019]