RECORD
Submodlib: A Submodular Optimization Library
Machine Learning · Submitted 22 Feb 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim In this work, we present Submodlib which is an open-source, easy-to-use, efficient and scalable Python library for submodular optimization with a C++ optimization engine.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Submodular functions are a special class of set functions which naturally model the notion of representativeness, diversity, coverage etc. and have been shown to be computationally very efficient. A lot of past work has applied submodular optimization to find optimal subsets in various contexts. Some examples include data summarization for efficient human consumption, finding effective smaller subsets of training data to reduce the model development time (training, hyper parameter tuning), finding effective subsets of unlabeled data to reduce the labeling costs, etc. A recent work has also leveraged submodular functions to propose submodular information measures which have been found to be very useful in solving the problems of guided subset selection and guided summarization. In this work, we present Submodlib which is an open-source, easy-to-use, efficient and scalable Python library for submodular optimization with a C++ optimization engine. Submodlib finds its application in summarization, data subset selection, hyper parameter tuning, efficient training and more. Through a rich API, it offers a great deal of flexibility in the way it can be used. Source of Submodlib is available at https://github.com/decile-team/submodlib.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Submodular functions are a special class of set functions which naturally model the notion of representativeness, diversity, coverage etc. and have been shown to be computationally very efficient. | background 1.00 | 0.06 | 0.04 | asserted 1.00 |
| s1 | A lot of past work has applied submodular optimization to find optimal subsets in various contexts. | background 1.00 | 0.03 | 0.02 | asserted 1.00 |
| s2 | Some examples include data summarization for efficient human consumption, finding effective smaller subsets of training data to reduce the model development time (training, hyper parameter tuning), finding effective subsets of unlabeled data to reduce the labeling costs, etc. | background 1.00 | 0.04 | 0.03 | asserted 0.96 |
| s3 | A recent work has also leveraged submodular functions to propose submodular information measures which have been found to be very useful in solving the problems of guided subset selection and guided summarization. | background 1.00 | 0.05 | 0.04 | asserted 1.00 |
| s4 | In this work, we present Submodlib which is an open-source, easy-to-use, efficient and scalable Python library for submodular optimization with a C++ optimization engine. | contribution 1.00 | 0.91 | 0.45 | asserted 1.00 |
| s5 | Submodlib finds its application in summarization, data subset selection, hyper parameter tuning, efficient training and more. | contribution 0.91 | 0.33 | 0.16 | asserted 1.00 |
| s6 | Through a rich API, it offers a great deal of flexibility in the way it can be used. | contribution 0.67 | 0.55 | 0.05 | asserted 1.00 |
| s7 | Source of Submodlib is available at https://github.com/decile-team/submodlib. | contribution 0.80 | 0.35 | 0.02 | asserted 0.96 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Submodular functions are a special class of set functions which naturally model the notion of representativeness, diversity, coverage etc. and have been shown to be computationally very efficient. A lot of past work has applied submodular optimization to find optimal subsets in various contexts. Some examples include data summarization for efficient human consumption, finding effective smaller subsets of training data to reduce the model development time (training, hyper parameter tuning), finding effective subsets of unlabeled data to reduce the labeling costs, etc. A recent work has also leveraged submodular functions to propose submodular information measures which have been found to be very useful in solving the problems of guided subset selection and guided summarization. In this work, we present Submodlib which is an open-source, easy-to-use, efficient and scalable Python library for submodular optimization with a C++ optimization engine. Submodlib finds its application in summarization, data subset selection, hyper parameter tuning, efficient training and more. Through a rich API, it offers a great deal of flexibility in the way it can be used. Source of Submodlib is available at https://github.com/decile-team/submodlib.
Human review
How the literature uses it
5 arXiv papers cite this in 6 sentences
Papers citing it
Uses its method or tool 4 papers
-
To boost accuracies, we utilize subset selection method [ref] to select the most diverse images of the Dermatofibroma class present in the training set.
One Shot GANs for Long Tail Problem in Skin Lesion Dataset using novel content space assessment metric · Subset Selection and One-Shot GANs · 1.00
-
For this, we employed the library [ref] . * [ref] : Again this bears similarity to but with a difference.
Speeding up NAS with Adaptive Subset Selection · Experiments · 0.99
-
We use SUBMODLIB [ref] , which has the necessary algorithms implemented, to obtain the weighted task subsets (Section [ref]) and the instances (Section [ref]).
SMART: Submodular Data Mixture Strategy for Instruction Tuning · Finetuning Data · 1.00
Cites it as background 1 paper
-
Classical results on submodular functions and multilinear relaxations [ref] established the importance of diminishing-returns structure in discrete and continuous optimization, and subsequent studies have used this structure for budget allocation, data summarization, and representative selection [ref] .
Toward Trustworthy AI: Multi-Target Adversarial Attacks and Robust Defenses for Continuous Data Summarization · Introduction · 0.98
What it cites · 1 sentence without a confident label
Cites as background 4 papers
-
Some of the ways past work has tried to address one or more of these challenges are through novel network architecture modifications [ref] , transfer learning [ref] , zero-shot learning [ref] , one-shot learning [ref] , activelearning [ref] , core sets [ref] and, in the context of this work, submodular functions [ref] .
Distilling the Knowledge in a Neural Network · Introduction · 0.93
-
Some of the ways past work has tried to address one or more of these challenges are through novel network architecture modifications [ref] , transfer learning [ref] , zero-shot learning [ref] , one-shot learning [ref] , activelearning [ref] , core sets [ref] and, in the context of this work, submodular functions [ref] .
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size · Introduction · 0.93
-
Submodularity is a rich yet tractable sub-field of non-linear combinatorial optimization which ensures tractable algorithms and nice connections to convexity and concavity [ref] .
Learning with Submodular Functions: A Convex Optimization Perspective · Submodular Functions and Submodular Optimization · 0.91
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.