incrementalLearner

Convert multiclass error-correcting output codes (ECOC) model to incremental learner

Since R2022a

Syntax

IncrementalMdl = incrementalLearner(Mdl)

IncrementalMdl = incrementalLearner(Mdl,Name=Value)

Description

IncrementalMdl = incrementalLearner(Mdl) returns a multiclass error-correcting output codes (ECOC) model for incremental learning, IncrementalMdl, using the hyperparameters and parameters of the traditionally trained ECOC model for multiclass classification, Mdl. Because its property values reflect the knowledge gained from Mdl, IncrementalMdl can predict labels given new observations, and it is warm, meaning that its predictive performance is tracked.

IncrementalMdl = incrementalLearner(Mdl,Name=Value) uses additional options specified by one or more name-value arguments. Some options require you to train IncrementalMdl before its predictive performance is tracked. For example, MetricsWarmupPeriod=50,MetricsWindowSize=100 specifies a preliminary incremental training period of 50 observations before performance metrics are tracked, and specifies processing 100 observations before updating the window performance metrics.

Examples

Convert Traditionally Trained Model to Incremental Learner

Train a multiclass ECOC classification model by using fitcecoc, and then convert it to an incremental learner.

Load Data

Load the human activity data set.

load humanactivity

For details on the data set, enter Description at the command line.

Train ECOC Model

Fit a multiclass ECOC classification model to the entire data set.

Mdl = fitcecoc(feat,actid);

Mdl is a ClassificationECOC model object representing a traditionally trained ECOC classification model.

Convert Trained Model

Convert the traditionally trained ECOC classification model to a model for incremental learning.

IncrementalMdl = incrementalLearner(Mdl) 

IncrementalMdl = 
  incrementalClassificationECOC

            IsWarm: 1
           Metrics: [1×2 table]
        ClassNames: [1 2 3 4 5]
    ScoreTransform: 'none'
    BinaryLearners: {10×1 cell}
        CodingName: 'onevsone'
          Decoding: 'lossweighted'


  Properties, Methods

IncrementalMdl is an incrementalClassificationECOC model object prepared for incremental learning.

• The incrementalLearner function initializes the incremental learner by passing the coding design and model parameters for binary learners to it, along with other information Mdl extracts from the training data.

• IncrementalMdl is warm (IsWarm is 1), which means that incremental learning functions can track performance metrics and make predictions.

Predict Responses

An incremental learner created from converting a traditionally trained model can generate predictions without further processing.

Predict classification scores for all observations using both models.

[~,ttscores] = predict(Mdl,feat);
[~,ilcores] = predict(IncrementalMdl,feat);
compareScores = norm(ttscores - ilcores)

compareScores = 0

The difference between the scores generated by the models is 0.

Configure Performance Metric Options

Use a trained ECOC model to initialize an incremental learner. Prepare the incremental learner by specifying a metrics warm-up period and a metrics window size.

Load the human activity data set.

load humanactivity

For details on the data set, enter Description at the command line

Randomly split the data in half: the first half for training a model traditionally, and the second half for incremental learning.

n = numel(actid);

rng(1) % For reproducibility
cvp = cvpartition(n,Holdout=0.5);
idxtt = training(cvp);
idxil = test(cvp);

% First half of data
Xtt = feat(idxtt,:);
Ytt = actid(idxtt);

% Second half of data
Xil = feat(idxil,:);
Yil = actid(idxil);

Fit an ECOC model to the first half of the data.

Mdl = fitcecoc(Xtt,Ytt);

Convert the traditionally trained ECOC model to a model for incremental learning. Specify the following:

• A performance metrics warm-up period of 2000 observations

• A metrics window size of 500 observations

IncrementalMdl = incrementalLearner(Mdl, ...
    MetricsWarmupPeriod=2000,MetricsWindowSize=500);

By default, incrementalClassificationECOC uses classification error loss to measure the performance of the model.

Fit the incremental model to the second half of the data by using the updateMetricsAndFit function. At each iteration:

• Simulate a data stream by processing 20 observations at a time.

• Overwrite the previous incremental model with a new one fitted to the incoming observations.

• Store the first model coefficient of the first binary learner $${\beta }_{11}$$, the cumulative metrics, and the window metrics to see how they evolve during incremental learning.

% Preallocation
nil = numel(Yil);
numObsPerChunk = 20;
nchunk = ceil(nil/numObsPerChunk);
ce = array2table(zeros(nchunk,2),VariableNames=["Cumulative","Window"]);
beta11 = [IncrementalMdl.BinaryLearners{1}.Beta(1); zeros(nchunk+1,1)];  

% Incremental fitting
for j = 1:nchunk
    ibegin = min(nil,numObsPerChunk*(j-1) + 1);
    iend   = min(nil,numObsPerChunk*j);
    idx = ibegin:iend;    
    IncrementalMdl = updateMetricsAndFit(IncrementalMdl,Xil(idx,:),Yil(idx));
    ce{j,:} = IncrementalMdl.Metrics{"ClassificationError",:};
    beta11(j+1) = IncrementalMdl.BinaryLearners{1}.Beta(1);
end

IncrementalMdl is an incrementalClassificationECOC model object trained on all the data in the stream. During incremental learning and after the model is warmed up, updateMetricsAndFit checks the performance of the model on the incoming observations, and then fits the model to those observations.

To see how the performance metrics and $${\beta }_{11}$$ evolve during training, plot them on separate tiles.

t = tiledlayout(2,1);
nexttile
plot(beta11)
ylabel("\beta_{11}")
xlim([0 nchunk]);
xline(IncrementalMdl.MetricsWarmupPeriod/numObsPerChunk,"r-.");
nexttile
plot(ce.Variables);
xlim([0 nchunk]);
ylabel("Classification Error")
xline(IncrementalMdl.MetricsWarmupPeriod/numObsPerChunk,"r-.");
legend(ce.Properties.VariableNames,Location="best")
xlabel(t,"Iteration")

The plots indicate that updateMetricsAndFit performs the following actions:

• Fit $${\beta }_{11}$$ during all incremental learning iterations.

• Compute the performance metrics after the metrics warm-up period (red vertical line) only.

• Compute the cumulative metrics during each iteration.

• Compute the window metrics after processing 500 observations (25 iterations).

Input Arguments

Mdl — Traditionally trained ECOC model for multiclass classification

ClassificationECOC model object | CompactClassificationECOC model object

Traditionally trained ECOC model for multiclass classification, specified as a ClassificationECOC or CompactClassificationECOC model object returned by fitcecoc or compact, respectively.

Note

• When you train Mdl, you must specify the Learners name-value argument of fitcecoc to use support vector machine (SVM) binary learner templates (templateSVM) or linear classification model binary learner templates (templateLinear).

• Incremental learning functions support only numeric input predictor data. If Mdl was trained on categorical data, you must prepare an encoded version of the categorical data to use incremental learning functions. Use dummyvar to convert each categorical variable to a numeric matrix of dummy variables. Then, concatenate all dummy variable matrices and any other numeric predictors, in the same way that the training function encodes categorical data. For more details, see Dummy Variables.

Name-Value Arguments

Specify optional pairs of arguments as Name1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

Example: Decoding="lossbased",MetricsWindowSize=100 specifies to use the loss-based decoding scheme and to process 100 observations before updating the window performance metrics.

ECOC Classifier Options

BinaryLoss — Binary learner loss function

Mdl.BinaryLoss (default) | "hamming" | "linear" | "logit" | "exponential" | "binodeviance" | "hinge" | "quadratic" | function handle

Binary learner loss function, specified as a built-in loss function name or function handle.

• This table describes the built-in functions, where y_j is the class label for a particular binary learner (in the set {–1,1,0}), s_j is the score for observation j, and g(y_j,s_j) is the binary loss formula.

  Value	Description	Score Domain	g(yj,sj)
  "binodeviance"	Binomial deviance	(–∞,∞)	log[1 + exp(–2yjsj)]/[2log(2)]
  "exponential"	Exponential	(–∞,∞)	exp(–yjsj)/2
  "hamming"	Hamming	[0,1] or (–∞,∞)	[1 – sign(yjsj)]/2
  "hinge"	Hinge	(–∞,∞)	max(0,1 – yjsj)/2
  "linear"	Linear	(–∞,∞)	(1 – yjsj)/2
  "logit"	Logistic	(–∞,∞)	log[1 + exp(–yjsj)]/[2log(2)]
  "quadratic"	Quadratic	[0,1]	[1 – yj(2sj – 1)]2/2

  The software normalizes binary losses so that the loss is 0.5 when y_j = 0. Also, the software calculates the mean binary loss for each class [1].

• For a custom binary loss function, for example customFunction, specify its function handle BinaryLoss=@customFunction.

  customFunction has this form:

  bLoss = customFunction(M,s)

  • M is the K-by-B coding matrix stored in Mdl.CodingMatrix.

  • s is the 1-by-B row vector of classification scores.

  • bLoss is the classification loss. This scalar aggregates the binary losses for every learner in a particular class. For example, you can use the mean binary loss to aggregate the loss over the learners for each class.

  • K is the number of classes.

  • B is the number of binary learners.

  For an example of a custom binary loss function, see Predict Test-Sample Labels of ECOC Model Using Custom Binary Loss Function. This example is for a traditionally trained model. You can define a custom loss function for incremental learning as shown in the example.

For more information, see Binary Loss.

Data Types: char | string | function_handle

Decoding — Decoding scheme

"lossweighted" (default) | "lossbased"

Decoding scheme, specified as "lossweighted" or "lossbased".

The decoding scheme of an ECOC model specifies how the software aggregates the binary losses and determines the predicted class for each observation. The software supports two decoding schemes:

• "lossweighted" — The predicted class of an observation corresponds to the class that produces the minimum sum of the binary losses over binary learners.

• "lossbased" — The predicted class of an observation corresponds to the class that produces the minimum average of the binary losses over binary learners.

For more information, see Binary Loss.

Example: Decoding="lossbased"

Data Types: char | string

Performance Metrics Options

Metrics — Model performance metrics to track during incremental learning

"classiferror" (default) | function handle | cell vector | structure array

Model performance metrics to track during incremental learning with the updateMetrics or updateMetricsAndFit function, specified as "classiferror" (classification error, or misclassification error rate), a function handle (for example, @metricName), a structure array of function handles, or a cell vector of names, function handles, or structure arrays.

To specify a custom function that returns a performance metric, use function handle notation. The function must have this form.

metric = customMetric(C,S)

• The output argument metric is an n-by-1 numeric vector, where each element is the loss of the corresponding observation in the data processed by the incremental learning functions during a learning cycle.

• You specify the function name (here, customMetric).

• C is an n-by-K logical matrix with rows indicating the class to which the corresponding observation belongs, where K is the number of classes. The column order corresponds to the class order in the ClassNames property. Create C by setting C(p,q) = 1, if observation p is in class q, for each observation in the specified data. Set the other element in row p to 0.

• S is an n-by-K numeric matrix of predicted classification scores. S is similar to the NegLoss output of predict, where rows correspond to observations in the data and the column order corresponds to the class order in the ClassNames property. S(p,q) is the classification score of observation p being classified in class q.

To specify multiple custom metrics and assign a custom name to each, use a structure array. To specify a combination of built-in and custom metrics, use a cell vector.

updateMetrics and updateMetricsAndFit store specified metrics in a table in the Metrics property. The data type of Metrics determines the row names of the table.

Metrics Value Data Type	Description of Metrics Property Row Name	Example
String or character vector	Name of corresponding built-in metric	Row name for "classiferror" is "ClassificationError"
Structure array	Field name	Row name for struct(Metric1=@customMetric1) is "Metric1"
Function handle to function stored in a program file	Name of function	Row name for @customMetric is "customMetric"
Anonymous function	CustomMetric_j, where j is metric j in Metrics	Row name for @(C,S)customMetric(C,S)... is CustomMetric_1

For more details on performance metrics options, see Performance Metrics.

Example: Metrics=struct(Metric1=@customMetric1,Metric2=@customMetric2)

Example: Metrics={@customMetric1,@customMetric2,"classiferror",struct(Metric3=@customMetric3)}

Data Types: char | string | struct | cell | function_handle

MetricsWarmupPeriod — Number of observations fit before tracking performance metrics

0 (default) | nonnegative integer

Number of observations the incremental model must be fit to before it tracks performance metrics in its Metrics property, specified as a nonnegative integer. The incremental model is warm after incremental fitting functions fit MetricsWarmupPeriod observations to the incremental model.

For more details on performance metrics options, see Performance Metrics.

Example: MetricsWarmupPeriod=50

Data Types: single | double

MetricsWindowSize — Number of observations to use to compute window performance metrics

200 (default) | positive integer

Number of observations to use to compute window performance metrics, specified as a positive integer.

For more details on performance metrics options, see Performance Metrics.

Example: MetricsWindowSize=250

Data Types: single | double

UpdateBinaryLearnerMetrics — Flag for updating metrics of binary learners

false or 0 (default) | true or 1

Flag for updating the metrics of binary learners, specified as logical 0 (false) or 1 (true).

If the value is true, the software tracks the performance metrics of binary learners using the Metrics property of the binary learners, stored in the BinaryLearners property. For an example, see Configure Incremental Model to Track Performance Metrics for Model and Binary Learners.

Example: UpdateBinaryLearnerMetrics=true

Data Types: logical

Output Arguments

IncrementalMdl — ECOC classification model for incremental learning

incrementalClassificationECOC model object

ECOC classification model for incremental learning, returned as an incrementalClassificationECOC model object. IncrementalMdl is also configured to generate predictions given new data (see predict).

To initialize IncrementalMdl for incremental learning, incrementalLearner passes the values of the properties of Mdl in this table to corresponding properties of IncrementalMdl.

Property	Description
BinaryLearners	Trained binary learners, a cell array of model objects. The learners in Mdl are traditionally trained binary learners, and the learners in IncrementalMdl are binary learners for incremental learning converted from the traditionally trained binary learners.
BinaryLoss	Binary learner loss function, a character vector. You can specify a different value by using the BinaryLoss name-value argument.
ClassNames	Class labels for binary classification, a list of names
CodingMatrix	Class assignment codes for the binary learners, a numeric matrix
CodingName	Coding design name, a character vector
NumPredictors	Number of predictors, a positive integer
Prior	Prior class label distribution, a numeric vector

Note that incrementalLearner does not use the Cost property of Mdl because incrementalClassificationECOC does not support it.

More About

Incremental Learning

Incremental learning, or online learning, is a branch of machine learning concerned with processing incoming data from a data stream, possibly given little to no knowledge of the distribution of the predictor variables, aspects of the prediction or objective function (including tuning parameter values), or whether the observations are labeled. Incremental learning differs from traditional machine learning, where enough labeled data is available to fit to a model, perform cross-validation to tune hyperparameters, and infer the predictor distribution.

Given incoming observations, an incremental learning model processes data in any of the following ways, but usually in this order:

• Predict labels.

• Measure the predictive performance.

• Check for structural breaks or drift in the model.

• Fit the model to the incoming observations.

For more details, see Incremental Learning Overview.

Classification Error

The classification error has the form

$$L={\displaystyle \sum _{j=1}^n{w}_j{e}_j},$$

where:

• w_j is the weight for observation j. The software renormalizes the weights to sum to 1.

• e_j = 1 if the predicted class of observation j differs from its true class, and 0 otherwise.

In other words, the classification error is the proportion of observations misclassified by the classifier.

Binary Loss

The binary loss is a function of the class and classification score that determines how well a binary learner classifies an observation into the class. The decoding scheme of an ECOC model specifies how the software aggregates the binary losses and determines the predicted class for each observation.

Assume the following:

• m_kj is element (k,j) of the coding design matrix M—that is, the code corresponding to class k of binary learner j. M is a K-by-B matrix, where K is the number of classes, and B is the number of binary learners.

• s_j is the score of binary learner j for an observation.

• g is the binary loss function.

• $$\widehat{k}$$ is the predicted class for the observation.

The software supports two decoding schemes:

• Loss-based decoding [3] (Decoding is "lossbased") — The predicted class of an observation corresponds to the class that produces the minimum average of the binary losses over all binary learners.

  $$\widehat{k}=\underset{k}{\text{argmin}}\frac{1}{B}{\displaystyle \sum _{j=1}^B\left|m_{kj}\right|g}(m_{kj},s_j).$$

• Loss-weighted decoding [2] (Decoding is "lossweighted") — The predicted class of an observation corresponds to the class that produces the minimum average of the binary losses over the binary learners for the corresponding class.

  $$\widehat{k}=\underset{k}{\text{argmin}}\frac{{\displaystyle \sum _{j=1}^B\left|m_{kj}\right|g}(m_{kj},s_j)}{{\displaystyle \sum }_{j=1}^B\left|m_{kj}\right|}.$$

  The denominator corresponds to the number of binary learners for class k. [1] suggests that loss-weighted decoding improves classification accuracy by keeping loss values for all classes in the same dynamic range.

The predict, resubPredict, and kfoldPredict functions return the negated value of the objective function of argmin as the second output argument (NegLoss) for each observation and class.

This table summarizes the supported binary loss functions, where y_j is a class label for a particular binary learner (in the set {–1,1,0}), s_j is the score for observation j, and g(y_j,s_j) is the binary loss function.

Value	Description	Score Domain	g(yj,sj)
"binodeviance"	Binomial deviance	(–∞,∞)	log[1 + exp(–2yjsj)]/[2log(2)]
"exponential"	Exponential	(–∞,∞)	exp(–yjsj)/2
"hamming"	Hamming	[0,1] or (–∞,∞)	[1 – sign(yjsj)]/2
"hinge"	Hinge	(–∞,∞)	max(0,1 – yjsj)/2
"linear"	Linear	(–∞,∞)	(1 – yjsj)/2
"logit"	Logistic	(–∞,∞)	log[1 + exp(–yjsj)]/[2log(2)]
"quadratic"	Quadratic	[0,1]	[1 – yj(2sj – 1)]2/2

The software normalizes binary losses so that the loss is 0.5 when y_j = 0, and aggregates using the average of the binary learners [1].

Do not confuse the binary loss with the overall classification loss (specified by the LossFun name-value argument of the loss and predict object functions), which measures how well an ECOC classifier performs as a whole.

Algorithms

Performance Metrics

• The updateMetrics and updateMetricsAndFit functions track model performance metrics (Metrics) from new data only when the incremental model is warm (IsWarm property is true).

  • If you create an incremental model by using incrementalLearner and MetricsWarmupPeriod is 0 (default for incrementalLearner), the model is warm at creation.

  • Otherwise, an incremental model becomes warm after fit or updateMetricsAndFit performs both of these actions:

    • Fit the incremental model to MetricsWarmupPeriod observations, which is the metrics warm-up period.

    • Fit the incremental model to all expected classes (see the MaxNumClasses and ClassNames arguments of incrementalClassificationECOC).

• The Metrics property of the incremental model stores two forms of each performance metric as variables (columns) of a table, Cumulative and Window, with individual metrics in rows. When the incremental model is warm, updateMetrics and updateMetricsAndFit update the metrics at the following frequencies:

  • Cumulative — The functions compute cumulative metrics since the start of model performance tracking. The functions update metrics every time you call the functions and base the calculation on the entire supplied data set.

  • Window — The functions compute metrics based on all observations within a window determined by MetricsWindowSize, which also determines the frequency at which the software updates Window metrics. For example, if MetricsWindowSize is 20, the functions compute metrics based on the last 20 observations in the supplied data (X((end – 20 + 1):end,:) and Y((end – 20 + 1):end)).

    Incremental functions that track performance metrics within a window use the following process:

    1. Store a buffer of length MetricsWindowSize for each specified metric, and store a buffer of observation weights.

    2. Populate elements of the metrics buffer with the model performance based on batches of incoming observations, and store corresponding observation weights in the weights buffer.

    3. When the buffer is full, overwrite the Window field of the Metrics property with the weighted average performance in the metrics window. If the buffer overfills when the function processes a batch of observations, the latest incoming MetricsWindowSize observations enter the buffer, and the earliest observations are removed from the buffer. For example, suppose MetricsWindowSize is 20, the metrics buffer has 10 values from a previously processed batch, and 15 values are incoming. To compose the length 20 window, the functions use the measurements from the 15 incoming observations and the latest 5 measurements from the previous batch.

• The software omits an observation with a NaN score when computing the Cumulative and Window performance metric values.

References

[1] Allwein, E., R. Schapire, and Y. Singer. “Reducing multiclass to binary: A unifying approach for margin classifiers.” Journal of Machine Learning Research. Vol. 1, 2000, pp. 113–141.

[2] Escalera, S., O. Pujol, and P. Radeva. “On the decoding process in ternary error-correcting output codes.” IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 32, Issue 7, 2010, pp. 120–134.

[3] Escalera, S., O. Pujol, and P. Radeva. “Separability of ternary codes for sparse designs of error-correcting output codes.” Pattern Recog. Lett. Vol. 30, Issue 3, 2009, pp. 285–297.

Version History

Introduced in R2022a