Validate that densityLevel <= dimension

Author: breakanalysis

algo/src/main/java/org/neo4j/gds/embeddings/hashgnn/GenerateFeaturesConfig.java

@@ -26,6 +26,8 @@
 import java.util.Collections;
 import java.util.Map;
 
+import static org.neo4j.gds.utils.StringFormatting.formatWithLocale;
+
 @Configuration
 public interface GenerateFeaturesConfig {
     @Configuration.IntegerRange(min = 1)
@@ -47,4 +49,11 @@ default Map<String, Object> toMap() {
     default Collection<String> configKeys() {
         return Collections.emptyList();
     }
+
+    @Value.Check
+    default void validate() {
+        if (densityLevel() > dimension()) {
+            throw new IllegalArgumentException(formatWithLocale("Generate features requires `densityLevel` to be at most `dimension` but was %d > %d.", densityLevel(), dimension()));
+        }
+    }
 }

algo/src/test/java/org/neo4j/gds/embeddings/hashgnn/HashGNNConfigTest.java

@@ -63,4 +63,16 @@ void requiresFeaturePropertiesIfNoGeneratedFeatures() {
                 .build();
         }).hasMessage("When `generateFeatures` is not given, `featureProperties` must be non-empty.");
     }
+
+    @Test
+    void requiresDensityLevelAtMostDensity() {
+        assertThatThrownBy(() -> {
+            HashGNNConfigImpl
+                .builder()
+                .embeddingDensity(4)
+                .generateFeatures(Map.of("dimension", 4, "densityLevel", 5))
+                .iterations(100)
+                .build();
+        }).hasMessage("Generate features requires `densityLevel` to be at most `dimension` but was 5 > 4.");
+    }
 }

doc/modules/ROOT/partials/machine-learning/node-embeddings/hashgnn/specific-configuration.adoc

@@ -4,6 +4,6 @@
 | heterogeneous                                                                    | Boolean         | false           | yes       | Whether different relationship types should be treated differently.
 | neighborInfluence                                                                | Float           | 1.0             | yes       | Controls how often neighbors' features are sampled in each iteration relative to sampling the node's own features. Must be non-negative.
 | binarizeFeatures                                                                 | Map             | n/a             | yes       | A map with keys `dimension` and `threshold`. If given, features are transformed into `dimension` binary features via hyperplane rounding. Increasing `threshold` makes the output more sparse, and it defaults to `0`. The value of `dimension` must be at least 1.
-| generateFeatures                                                                 | Map             | n/a             | yes       | A map with keys `dimension` and `densityLevel`. Should be given if and only if `featureProperties` is empty. If given, `dimension` binary features are generated with approximately `densityLevel` active features per node. Both must be at least 1.
+| generateFeatures                                                                 | Map             | n/a             | yes       | A map with keys `dimension` and `densityLevel`. Should be given if and only if `featureProperties` is empty. If given, `dimension` binary features are generated with approximately `densityLevel` active features per node. Both must be at least 1 and `densityLevel` at most `density`.
 | outputDimension                                                                  | Integer         | n/a             | yes       | If given, the embeddings are projected randomly into `outputDimension` dense features. Must be at least 1.
 | randomSeed                                                                       | Integer         | n/a             | yes       | A random seed which is used for all randomness in computing the embeddings.