diff --git a/src/Microsoft.ML.Data/Transforms/ColumnConcatenatingTransformer.cs b/src/Microsoft.ML.Data/Transforms/ColumnConcatenatingTransformer.cs
index de4950cfd9..64284a92c1 100644
--- a/src/Microsoft.ML.Data/Transforms/ColumnConcatenatingTransformer.cs
+++ b/src/Microsoft.ML.Data/Transforms/ColumnConcatenatingTransformer.cs
@@ -896,7 +896,6 @@ public void SaveAsOnnx(OnnxContext ctx)
                 Host.CheckValue(ctx, nameof(ctx));
                 Contracts.Assert(CanSaveOnnx(ctx));
 
-                string opType = "Concat";
                 for (int iinfo = 0; iinfo < _columns.Length; ++iinfo)
                 {
                     var colInfo = _parent._columns[iinfo];
@@ -904,7 +903,7 @@ public void SaveAsOnnx(OnnxContext ctx)
 
                     string outName = colInfo.Name;
                     var outColType = boundCol.OutputType;
-                    if (!outColType.IsKnownSize)
+                    if ((!outColType.IsKnownSize) || (!(outColType.GetItemType() is NumberDataViewType)))
                     {
                         ctx.RemoveColumn(outName, false);
                         continue;
@@ -925,10 +924,19 @@ public void SaveAsOnnx(OnnxContext ctx)
                             InputSchema[srcIndex].Type.GetValueCount()));
                     }
 
+                    string opType = "FeatureVectorizer";
+                    int outVectorSize = (int)inputList.Sum(x => x.Value);
+                    var vectorizerOutputType = new VectorDataViewType(NumberDataViewType.Single, outVectorSize);
+                    var vectorizerOutputName = ctx.AddIntermediateVariable(vectorizerOutputType, "VectorFeaturizerOutput");
                     var node = ctx.CreateNode(opType, inputList.Select(t => t.Key),
-                        new[] { ctx.AddIntermediateVariable(outColType, outName) }, ctx.GetNodeName(opType), "");
-
-                    node.AddAttribute("axis", 1);
+                        new[] { vectorizerOutputName }, ctx.GetNodeName(opType));
+                    node.AddAttribute("inputdimensions", inputList.Select(x => x.Value));
+
+                    opType = "Cast";
+                    var dstVectorType = new VectorDataViewType(outColType.GetItemType() as PrimitiveDataViewType, outVectorSize);
+                    var dstVariableName = ctx.AddIntermediateVariable(dstVectorType, outName);
+                    var castNode = ctx.CreateNode(opType, vectorizerOutputName, dstVariableName, ctx.GetNodeName(opType), "");
+                    castNode.AddAttribute("to", outColType.ItemType.RawType);
                 }
             }
         }
diff --git a/test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/ExcludeVariablesInOnnxConversion.txt b/test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/ExcludeVariablesInOnnxConversion.txt
index 6c0545bed8..4e8133d917 100644
--- a/test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/ExcludeVariablesInOnnxConversion.txt
+++ b/test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/ExcludeVariablesInOnnxConversion.txt
@@ -176,14 +176,35 @@
           "F1",
           "F22"
         ],
+        "output": [
+          "VectorFeaturizerOutput"
+        ],
+        "name": "FeatureVectorizer",
+        "opType": "FeatureVectorizer",
+        "attribute": [
+          {
+            "name": "inputdimensions",
+            "ints": [
+              "1",
+              "10"
+            ],
+            "type": "INTS"
+          }
+        ],
+        "domain": "ai.onnx.ml"
+      },
+      {
+        "input": [
+          "VectorFeaturizerOutput"
+        ],
         "output": [
           "Features"
         ],
-        "name": "Concat",
-        "opType": "Concat",
+        "name": "Cast1",
+        "opType": "Cast",
         "attribute": [
           {
-            "name": "axis",
+            "name": "to",
             "i": "1",
             "type": "INT"
           }
@@ -431,7 +452,7 @@
         "output": [
           "PredictedLabel"
         ],
-        "name": "Cast1",
+        "name": "Cast2",
         "opType": "Cast",
         "attribute": [
           {
@@ -638,6 +659,24 @@
           }
         }
       },
+      {
+        "name": "VectorFeaturizerOutput",
+        "type": {
+          "tensorType": {
+            "elemType": 1,
+            "shape": {
+              "dim": [
+                {
+                  "dimValue": "-1"
+                },
+                {
+                  "dimValue": "11"
+                }
+              ]
+            }
+          }
+        }
+      },
       {
         "name": "Features",
         "type": {
diff --git a/test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/ModelWithLessIO.txt b/test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/ModelWithLessIO.txt
index 4bce784b91..1d72cf3487 100644
--- a/test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/ModelWithLessIO.txt
+++ b/test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/ModelWithLessIO.txt
@@ -125,14 +125,35 @@
           "F1",
           "F21"
         ],
+        "output": [
+          "VectorFeaturizerOutput"
+        ],
+        "name": "FeatureVectorizer",
+        "opType": "FeatureVectorizer",
+        "attribute": [
+          {
+            "name": "inputdimensions",
+            "ints": [
+              "8",
+              "9"
+            ],
+            "type": "INTS"
+          }
+        ],
+        "domain": "ai.onnx.ml"
+      },
+      {
+        "input": [
+          "VectorFeaturizerOutput"
+        ],
         "output": [
           "Features"
         ],
-        "name": "Concat",
-        "opType": "Concat",
+        "name": "Cast1",
+        "opType": "Cast",
         "attribute": [
           {
-            "name": "axis",
+            "name": "to",
             "i": "1",
             "type": "INT"
           }
@@ -757,7 +778,7 @@
         "output": [
           "PredictedLabel"
         ],
-        "name": "Cast1",
+        "name": "Cast2",
         "opType": "Cast",
         "attribute": [
           {
@@ -946,6 +967,24 @@
           }
         }
       },
+      {
+        "name": "VectorFeaturizerOutput",
+        "type": {
+          "tensorType": {
+            "elemType": 1,
+            "shape": {
+              "dim": [
+                {
+                  "dimValue": "-1"
+                },
+                {
+                  "dimValue": "17"
+                }
+              ]
+            }
+          }
+        }
+      },
       {
         "name": "Features",
         "type": {
diff --git a/test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/OneHotBagPipeline.txt b/test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/OneHotBagPipeline.txt
index 48945bf310..4158d89aa4 100644
--- a/test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/OneHotBagPipeline.txt
+++ b/test/BaselineOutput/Common/Onnx/BinaryClassification/BreastCancer/OneHotBagPipeline.txt
@@ -176,14 +176,35 @@
           "F1",
           "F22"
         ],
+        "output": [
+          "VectorFeaturizerOutput"
+        ],
+        "name": "FeatureVectorizer",
+        "opType": "FeatureVectorizer",
+        "attribute": [
+          {
+            "name": "inputdimensions",
+            "ints": [
+              "1",
+              "10"
+            ],
+            "type": "INTS"
+          }
+        ],
+        "domain": "ai.onnx.ml"
+      },
+      {
+        "input": [
+          "VectorFeaturizerOutput"
+        ],
         "output": [
           "Features"
         ],
-        "name": "Concat",
-        "opType": "Concat",
+        "name": "Cast1",
+        "opType": "Cast",
         "attribute": [
           {
-            "name": "axis",
+            "name": "to",
             "i": "1",
             "type": "INT"
           }
@@ -384,7 +405,7 @@
         "output": [
           "PredictedLabel"
         ],
-        "name": "Cast1",
+        "name": "Cast2",
         "opType": "Cast",
         "attribute": [
           {
@@ -871,6 +892,24 @@
           }
         }
       },
+      {
+        "name": "VectorFeaturizerOutput",
+        "type": {
+          "tensorType": {
+            "elemType": 1,
+            "shape": {
+              "dim": [
+                {
+                  "dimValue": "-1"
+                },
+                {
+                  "dimValue": "11"
+                }
+              ]
+            }
+          }
+        }
+      },
       {
         "name": "Features",
         "type": {
diff --git a/test/Microsoft.ML.Tests/OnnxConversionTest.cs b/test/Microsoft.ML.Tests/OnnxConversionTest.cs
index ad2bbd0a20..195f8d4634 100644
--- a/test/Microsoft.ML.Tests/OnnxConversionTest.cs
+++ b/test/Microsoft.ML.Tests/OnnxConversionTest.cs
@@ -878,6 +878,36 @@ public void LoadingPredictorModelAndOnnxConversionTest()
             Done();
         }
 
+        [Fact]
+        public void ConcatenateOnnxConversionTest()
+        {
+            var mlContext = new MLContext(seed: 1);
+            string dataPath = GetDataPath("breast-cancer.txt");
+
+            var data = ML.Data.LoadFromTextFile(dataPath, new[] {
+                new TextLoader.Column("VectorDouble2", DataKind.Double, 1),
+                new TextLoader.Column("VectorDouble1", DataKind.Double, 4, 8),
+                new TextLoader.Column("Label", DataKind.Boolean, 0)
+            });
+            var pipeline = mlContext.Transforms.Concatenate("Features", "VectorDouble1", "VectorDouble2");
+            var model = pipeline.Fit(data);
+            var transformedData = model.Transform(data);
+            var onnxModel = mlContext.Model.ConvertToOnnxProtobuf(model, data);
+
+            // Compare results produced by ML.NET and ONNX's runtime.
+            if (IsOnnxRuntimeSupported())
+            {
+                var onnxModelName = "Concatenate.onnx";
+                var onnxModelPath = GetOutputPath(onnxModelName);
+                SaveOnnxModel(onnxModel, onnxModelPath, null);
+                // Evaluate the saved ONNX model using the data used to train the ML.NET pipeline.
+                var onnxEstimator = mlContext.Transforms.ApplyOnnxModel(onnxModelPath);
+                var onnxTransformer = onnxEstimator.Fit(data);
+                var onnxResult = onnxTransformer.Transform(data);
+                CompareSelectedColumns<double>("Features", "Features", transformedData, onnxResult);
+            }
+            Done();
+        }
 
         [Fact]
         public void RemoveVariablesInPipelineTest()