Merge pull request #313 from geometric-intelligence/guille/inductive_node

gbg141 · web-flow · commit f905814b3594 · 2026-04-17T17:17:54.000-07:00
Fix bug in node-inductive settings
diff --git a/configs/model/cell/can.yaml b/configs/model/cell/can.yaml
@@ -38,7 +38,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/cell/cccn.yaml b/configs/model/cell/cccn.yaml
@@ -32,7 +32,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/cell/ccxn.yaml b/configs/model/cell/ccxn.yaml
@@ -34,7 +34,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/cell/cwn.yaml b/configs/model/cell/cwn.yaml
@@ -31,7 +31,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/cell/topotune.yaml b/configs/model/cell/topotune.yaml
@@ -47,7 +47,7 @@ readout:
   num_cell_dimensions: ${infer_topotune_num_cell_dimensions:${oc.select:model.backbone.neighborhoods}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/cell/topotune_onehasse.yaml b/configs/model/cell/topotune_onehasse.yaml
@@ -46,7 +46,7 @@ readout:
   num_cell_dimensions: ${infer_topotune_num_cell_dimensions:${oc.select:model.backbone.neighborhoods}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/combinatorial/topotune.yaml b/configs/model/combinatorial/topotune.yaml
@@ -47,7 +47,7 @@ readout:
   num_cell_dimensions: ${infer_topotune_num_cell_dimensions:${oc.select:model.backbone.neighborhoods}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/graph/gat.yaml b/configs/model/graph/gat.yaml
@@ -34,7 +34,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/graph/gcn.yaml b/configs/model/graph/gcn.yaml
@@ -31,7 +31,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/graph/gcn_dgm.yaml b/configs/model/graph/gcn_dgm.yaml
@@ -34,7 +34,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/graph/gin.yaml b/configs/model/graph/gin.yaml
@@ -31,7 +31,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/graph/gps.yaml b/configs/model/graph/gps.yaml
@@ -35,7 +35,7 @@ readout:
   in_channels: ${model.feature_encoder.out_channels}
   hidden_layers: [16]
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
   # Extra MLP params
   dropout: 0.2
diff --git a/configs/model/graph/graph_mlp.yaml b/configs/model/graph/graph_mlp.yaml
@@ -35,7 +35,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 
diff --git a/configs/model/graph/nsd.yaml b/configs/model/graph/nsd.yaml
@@ -35,7 +35,7 @@ readout:
   in_channels: ${model.feature_encoder.out_channels}
   hidden_layers: [16]
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
   # Extra MLP params
   dropout: 0.2
diff --git a/configs/model/hypergraph/alldeepset.yaml b/configs/model/hypergraph/alldeepset.yaml
@@ -39,7 +39,7 @@ readout:
   num_cell_dimensions: 1 # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/hypergraph/allsettransformer.yaml b/configs/model/hypergraph/allsettransformer.yaml
@@ -33,7 +33,7 @@ readout:
   num_cell_dimensions: 1 # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/hypergraph/edgnn.yaml b/configs/model/hypergraph/edgnn.yaml
@@ -34,7 +34,7 @@ readout:
   num_cell_dimensions: 1 # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/hypergraph/unignn.yaml b/configs/model/hypergraph/unignn.yaml
@@ -29,7 +29,7 @@ readout:
   num_cell_dimensions: 1 # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/hypergraph/unignn2.yaml b/configs/model/hypergraph/unignn2.yaml
@@ -33,7 +33,7 @@ readout:
   num_cell_dimensions: 1
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/non_relational/mlp.yaml b/configs/model/non_relational/mlp.yaml
@@ -29,7 +29,7 @@ readout:
   readout_name: NoReadOut
   hidden_dim: ${model.backbone.out_channels}
   out_channels: ${model.backbone.out_channels}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
   logits_linear_layer: false
 
diff --git a/configs/model/pointcloud/deepset.yaml b/configs/model/pointcloud/deepset.yaml
@@ -29,7 +29,7 @@ readout:
   in_channels: ${model.feature_encoder.out_channels}
   hidden_layers: [64,32]
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
   # Extra MLP params
   dropout: 0.0
diff --git a/configs/model/simplicial/san.yaml b/configs/model/simplicial/san.yaml
@@ -35,7 +35,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/simplicial/sccn.yaml b/configs/model/simplicial/sccn.yaml
@@ -30,7 +30,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/simplicial/sccnn.yaml b/configs/model/simplicial/sccnn.yaml
@@ -43,7 +43,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/simplicial/sccnn_custom.yaml b/configs/model/simplicial/sccnn_custom.yaml
@@ -43,7 +43,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/simplicial/scn.yaml b/configs/model/simplicial/scn.yaml
@@ -34,7 +34,7 @@ readout:
   num_cell_dimensions: ${infer_num_cell_dimensions:${oc.select:model.feature_encoder.selected_dimensions,null},${model.feature_encoder.in_channels}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/simplicial/topotune.yaml b/configs/model/simplicial/topotune.yaml
@@ -47,7 +47,7 @@ readout:
   num_cell_dimensions: ${infer_topotune_num_cell_dimensions:${oc.select:model.backbone.neighborhoods}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/model/simplicial/topotune_onehasse.yaml b/configs/model/simplicial/topotune_onehasse.yaml
@@ -46,7 +46,7 @@ readout:
   num_cell_dimensions: ${infer_topotune_num_cell_dimensions:${oc.select:model.backbone.neighborhoods}} # The highest order of cell dimensions to consider
   hidden_dim: ${model.feature_encoder.out_channels}
   out_channels: ${dataset.parameters.num_classes}
-  task_level: ${dataset.parameters.task_level}
+  task_level: ${define_task_level:${dataset.parameters.task_level},${dataset.split_params.learning_setting}} # Handles the edge case of node-inductive task
   pooling_type: sum
 
 # compile model for faster training with pytorch 2.0
diff --git a/configs/run.yaml b/configs/run.yaml
@@ -31,9 +31,6 @@ defaults:
   # debugging config (enable through command line, e.g. `python train.py debug=default)
   - debug: null
 
-# evaluator: ${dataset.parameters.task}
-# callbacks: ${dataset.parameters.task}
-
 # task name, determines output directory path
 task_name: "train"
 
diff --git a/test/model/__init__.py b/test/model/__init__.py
diff --git a/test/model/test_model.py b/test/model/test_model.py
diff --git a/test/utils/test_config_resolvers.py b/test/utils/test_config_resolvers.py
diff --git a/topobench/model/model.py b/topobench/model/model.py
diff --git a/topobench/nn/readouts/base.py b/topobench/nn/readouts/base.py
diff --git a/topobench/run.py b/topobench/run.py
diff --git a/topobench/utils/config_resolvers.py b/topobench/utils/config_resolvers.py
