The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
"Attribute Weighting by Forward Selection"
christian1983
Member Posts: 11 
Contributor II
Hello everybody,
I am doing an attribute weighting by using a forward selection algorithm. The inner cross validation of the FS shows an accuracy of 49,26%. When i start a new process with the scaled input data and the identic cross validation operator containing the same learner as in the FS Process, i get an accuracy of 47,61%. How can this difference be explained?
Here the Forward Selection Process:
Here the Test Process:
Best regards
I am doing an attribute weighting by using a forward selection algorithm. The inner cross validation of the FS shows an accuracy of 49,26%. When i start a new process with the scaled input data and the identic cross validation operator containing the same learner as in the FS Process, i get an accuracy of 47,61%. How can this difference be explained?
Here the Forward Selection Process:
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.0.10" expanded="true" name="Process">
<process expanded="true" height="444" width="435">
<operator activated="true" class="retrieve" compatibility="5.0.10" expanded="true" height="60" name="Retrieve" width="90" x="45" y="30">
<parameter key="repository_entry" value="../../../../../Data/C15_QST 32-3_Label_Umformgrad"/>
</operator>
<operator activated="true" class="discretize_by_frequency" compatibility="5.0.10" expanded="true" height="94" name="Discretize" width="90" x="180" y="30">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="Total Equivalent Plastic Strain (Umformgrad)"/>
<parameter key="include_special_attributes" value="true"/>
<parameter key="use_sqrt_of_examples" value="true"/>
</operator>
<operator activated="true" class="optimize_selection_forward" compatibility="5.0.10" expanded="true" height="94" name="Forward Selection" width="90" x="315" y="30">
<process expanded="true" height="444" width="280">
<operator activated="true" class="x_validation" compatibility="5.0.10" expanded="true" height="112" name="Validation" width="90" x="45" y="30">
<process expanded="true" height="444" width="165">
<operator activated="true" class="decision_tree" compatibility="5.0.10" expanded="true" height="76" name="Decision Tree" width="90" x="45" y="30"/>
<connect from_port="training" to_op="Decision Tree" to_port="training set"/>
<connect from_op="Decision Tree" from_port="model" to_port="model"/>
<portSpacing port="source_training" spacing="0"/>
<portSpacing port="sink_model" spacing="0"/>
<portSpacing port="sink_through 1" spacing="0"/>
</process>
<process expanded="true" height="444" width="300">
<operator activated="true" class="apply_model" compatibility="5.0.10" expanded="true" height="76" name="Apply Model" width="90" x="45" y="30">
<list key="application_parameters"/>
</operator>
<operator activated="true" class="performance" compatibility="5.0.10" expanded="true" height="76" name="Performance" width="90" x="180" y="30"/>
<connect from_port="model" to_op="Apply Model" to_port="model"/>
<connect from_port="test set" to_op="Apply Model" to_port="unlabelled data"/>
<connect from_op="Apply Model" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
<connect from_op="Performance" from_port="performance" to_port="averagable 1"/>
<portSpacing port="source_model" spacing="0"/>
<portSpacing port="source_test set" spacing="0"/>
<portSpacing port="source_through 1" spacing="0"/>
<portSpacing port="sink_averagable 1" spacing="0"/>
<portSpacing port="sink_averagable 2" spacing="0"/>
</process>
</operator>
<connect from_port="example set" to_op="Validation" to_port="training"/>
<connect from_op="Validation" from_port="averagable 1" to_port="performance"/>
<portSpacing port="source_example set" spacing="0"/>
<portSpacing port="sink_performance" spacing="0"/>
</process>
</operator>
<connect from_op="Retrieve" from_port="output" to_op="Discretize" to_port="example set input"/>
<connect from_op="Discretize" from_port="example set output" to_op="Forward Selection" to_port="example set"/>
<connect from_op="Forward Selection" from_port="attribute weights" to_port="result 1"/>
<connect from_op="Forward Selection" from_port="performance" to_port="result 2"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="0"/>
<portSpacing port="sink_result 3" spacing="0"/>
</process>
</operator>
</process>
Here the Test Process:
<?xml version="1.0" encoding="UTF-8" standalone="no"?>I hope someone could explain this difference.
<process version="5.0">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.0.10" expanded="true" name="Process">
<process expanded="true" height="444" width="685">
<operator activated="true" class="retrieve" compatibility="5.0.10" expanded="true" height="60" name="Retrieve (2)" width="90" x="112" y="165">
<parameter key="repository_entry" value="../../../Data/C15_QST 32-3_Label_Umformgrad"/>
</operator>
<operator activated="true" class="discretize_by_frequency" compatibility="5.0.10" expanded="true" height="94" name="Discretize (2)" width="90" x="246" y="165">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="Total Equivalent Plastic Strain (Umformgrad)"/>
<parameter key="include_special_attributes" value="true"/>
<parameter key="use_sqrt_of_examples" value="true"/>
</operator>
<operator activated="true" class="retrieve" compatibility="5.0.10" expanded="true" height="60" name="Retrieve" width="90" x="126" y="57">
<parameter key="repository_entry" value="../../../Results/DecisionTrees/Attribute Weighting/Gain Ratio/Forward Selection/AttributeWeights"/>
</operator>
<operator activated="true" class="scale_by_weights" compatibility="5.0.10" expanded="true" height="76" name="Scale by Weights" width="90" x="380" y="75"/>
<operator activated="true" class="x_validation" compatibility="5.0.10" expanded="true" height="112" name="Validation (2)" width="90" x="514" y="75">
<parameter key="local_random_seed" value="1"/>
<process expanded="true" height="444" width="314">
<operator activated="true" class="decision_tree" compatibility="5.0.10" expanded="true" height="76" name="Decision Tree (2)" width="90" x="84" y="37"/>
<connect from_port="training" to_op="Decision Tree (2)" to_port="training set"/>
<connect from_op="Decision Tree (2)" from_port="model" to_port="model"/>
<portSpacing port="source_training" spacing="0"/>
<portSpacing port="sink_model" spacing="0"/>
<portSpacing port="sink_through 1" spacing="0"/>
</process>
<process expanded="true" height="444" width="346">
<operator activated="true" class="apply_model" compatibility="5.0.10" expanded="true" height="76" name="Apply Model (2)" width="90" x="81" y="34">
<list key="application_parameters"/>
</operator>
<operator activated="true" class="performance" compatibility="5.0.10" expanded="true" height="76" name="Performance (2)" width="90" x="179" y="120"/>
<connect from_port="model" to_op="Apply Model (2)" to_port="model"/>
<connect from_port="test set" to_op="Apply Model (2)" to_port="unlabelled data"/>
<connect from_op="Apply Model (2)" from_port="labelled data" to_op="Performance (2)" to_port="labelled data"/>
<connect from_op="Performance (2)" from_port="performance" to_port="averagable 1"/>
<portSpacing port="source_model" spacing="0"/>
<portSpacing port="source_test set" spacing="0"/>
<portSpacing port="source_through 1" spacing="0"/>
<portSpacing port="sink_averagable 1" spacing="0"/>
<portSpacing port="sink_averagable 2" spacing="0"/>
</process>
</operator>
<connect from_op="Retrieve (2)" from_port="output" to_op="Discretize (2)" to_port="example set input"/>
<connect from_op="Discretize (2)" from_port="example set output" to_op="Scale by Weights" to_port="example set"/>
<connect from_op="Retrieve" from_port="output" to_op="Scale by Weights" to_port="weights"/>
<connect from_op="Scale by Weights" from_port="example set" to_op="Validation (2)" to_port="training"/>
<connect from_op="Validation (2)" from_port="averagable 1" to_port="result 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="0"/>
</process>
</operator>
</process>
Best regards
Tagged:
0
Answers
actually this is a problem of overfitting. If you make a forward selection on a cross validation, the selection will base on all data. But in fact this might be random. We had a very good paper on this topic during our RCOMM last month. So I would suggest taking a look there:
http://rapid-i.com/component/page,shop.product_details/flypage,flypage.tpl/product_id,68/category_id,5/option,com_virtuemart/Itemid,180/
Greetings,
Sebastian