{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b9424635",
   "metadata": {},
   "source": [
    "# Federated Learning for Image Classification"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "73854d03",
   "metadata": {},
   "source": [
    ">The following codes are demos only. It's **NOT for production** due to system security concerns, please **DO NOT** use it directly in production."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "26887415",
   "metadata": {},
   "source": [
    "In this tutorial, we will use the image classification task to show how to complete the horizontal federated learning task in the `SecretFlow` framework.\n",
    "The `SecretFlow` framework provides a user-friendly API that makes it easy to apply your Keras or PyTorch model to a federated learning scenario as a federated learning model.\n",
    "In the rest of the tutorial we will show you how to turn your existing model into a federated model in `SecretFlow` to complete federated multi-party modeling tasks"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "223044ce",
   "metadata": {},
   "source": [
    "## What is Federated Learning"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5b60fdb5",
   "metadata": {},
   "source": [
    "The federated learning here refers specifically to the federated learning of horizontal scenarios. This mode applies to the situation where each participant has the same business but different customer groups are reached. In this case, samples from various parties can be combined to train a joint model with better performance. For example, in the medical scene, each hospital has its own unique patient group, and hospitals in different regions almost do not overlap each other, but their examination records for medical records (such as images, blood tests, etc.) are of the same type."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "333698af",
   "metadata": {},
   "source": [
    "<img alt=\"federate_learning.png\" src=\"resources/federate_learning.png\" width=\"600\">"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "54c1b11a",
   "metadata": {},
   "source": [
    "Training process:\n",
    "1. Each participant downloads the latest model from the server.\n",
    "2. Each participant uses its own local data to train the model, and uploads gradient encryption (or parameter encryption) to the server, which obtains the encryption gradient (encryption parameter) uploaded by all parties for security aggregation at the server, and updates model parameters with the aggregated gradient.\n",
    "3. The server returns the updated model to each participant.\n",
    "4. Each participant updates their local model, and prepare next training."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "65430f78",
   "metadata": {},
   "source": [
    "## Federated learning on SecretFlow"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "59774353",
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c5253753",
   "metadata": {},
   "source": [
    "Create 3 entities in the Secretflow environment [Alice, Bob, Charlie]\n",
    "Alice, Bob and Charlie are the three PYUs.\n",
    "Alice and Bob to be the clients and Charlie to be the server"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "93f79d14",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-08-18 17:13:51.247907: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /opt/rh/devtoolset-10/root/usr/lib64:/opt/rh/devtoolset-10/root/usr/lib:/opt/rh/devtoolset-10/root/usr/lib64/dyninst:/opt/rh/devtoolset-10/root/usr/lib/dyninst:/opt/rh/devtoolset-10/root/usr/lib64:/opt/rh/devtoolset-10/root/usr/lib\n"
     ]
    }
   ],
   "source": [
    "import secretflow as sf\n",
    "\n",
    "# In case you have a running secretflow runtime already.\n",
    "sf.shutdown()\n",
    "\n",
    "sf.init(['alice', 'bob', 'charlie'], address='local')\n",
    "alice, bob, charlie = sf.PYU('alice'), sf.PYU('bob'), sf.PYU('charlie')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "4bf4e1f6",
   "metadata": {},
   "outputs": [],
   "source": [
    "spu = sf.SPU(sf.utils.testing.cluster_def(['alice', 'bob']))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c53224e0",
   "metadata": {},
   "source": [
    "### Prepare Data\n",
    "\n",
    "Alice and bob each own half the data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "44a81605",
   "metadata": {},
   "outputs": [],
   "source": [
    "from secretflow.data.ndarray import load\n",
    "from secretflow.utils.simulation.datasets import load_mnist\n",
    "\n",
    "(x_train, y_train), (x_test, y_test) = load_mnist(parts=[alice, bob], normalized_x=True, categorical_y=True)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "23fbbbdf",
   "metadata": {},
   "source": [
    "`x_train`, `y_train`, `x_test`, `y_test` are both `FedNdarray`. Let's take a look at the data obtained from `FedNdarray`. FedNdarray is a virtual Ndarray built on a multi-party concept to protect data privacy.\n",
    "The underlying data is stored in each participant. The FedNdarray operation is actually performed by each participant on their own local data. The server or other clients do not touch the original data.\n",
    "For demonstration purposes, we will manually download the data to the driver\n",
    "**This data will be used later in the unilateral model comparison**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "5984479d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from secretflow.utils.simulation.datasets import dataset\n",
    "\n",
    "mnist = np.load(dataset('mnist'), allow_pickle=True)\n",
    "image = mnist['x_train']\n",
    "label = mnist['y_train']"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e01bc559",
   "metadata": {},
   "source": [
    "Let's grab some samples from the data set, and just visually see, what does the data look like for Both Alice and Bob?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "031dbe50",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1440x288 with 40 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "from matplotlib import pyplot as plt\n",
    "\n",
    "figure = plt.figure(figsize=(20, 4))\n",
    "j = 0\n",
    "\n",
    "for example in image[:40]:\n",
    "  plt.subplot(4, 10, j+1)\n",
    "  plt.imshow(example, cmap='gray', aspect='equal')\n",
    "  plt.axis('off')\n",
    "  j += 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "11098cb0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1440x288 with 40 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "figure = plt.figure(figsize=(20, 4))\n",
    "j = 0\n",
    "for example in image[:40]:\n",
    "  plt.subplot(4, 10, j+1)\n",
    "  plt.imshow(example, cmap='gray', aspect='equal')\n",
    "  plt.axis('off')\n",
    "  j += 1"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8ff562fe",
   "metadata": {},
   "source": [
    "It can be seen from the above two examples that the data types and tasks of Alice and Bob are consistent, but the samples are different due to the different user groups they reach."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "806779e1",
   "metadata": {},
   "source": [
    "### Define Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "25fbec5d",
   "metadata": {},
   "outputs": [],
   "source": [
    "def create_conv_model(input_shape, num_classes, name='model'):\n",
    "    def create_model():\n",
    "        from tensorflow import keras\n",
    "        from tensorflow.keras import layers\n",
    "        # Create model\n",
    "        model = keras.Sequential(\n",
    "            [\n",
    "                keras.Input(shape=input_shape),\n",
    "                layers.Conv2D(32, kernel_size=(3, 3), activation=\"relu\"),\n",
    "                layers.MaxPooling2D(pool_size=(2, 2)),\n",
    "                layers.Conv2D(64, kernel_size=(3, 3), activation=\"relu\"),\n",
    "                layers.MaxPooling2D(pool_size=(2, 2)),\n",
    "                layers.Flatten(),\n",
    "                layers.Dropout(0.5),\n",
    "                layers.Dense(num_classes, activation=\"softmax\"),\n",
    "            ]\n",
    "        )\n",
    "        # Compile model\n",
    "        model.compile(loss='categorical_crossentropy',\n",
    "                      optimizer='adam',\n",
    "                      metrics=[\"accuracy\"])\n",
    "        return model\n",
    "\n",
    "    return create_model\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "33fce574",
   "metadata": {},
   "source": [
    "### Training FL Model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ac7e3cb8",
   "metadata": {},
   "source": [
    "1. Import packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "c2c68047",
   "metadata": {},
   "outputs": [],
   "source": [
    "from secretflow.security.aggregation import SPUAggregator, SecureAggregator\n",
    "from secretflow.ml.nn import FLModel"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "37f25ac1",
   "metadata": {},
   "source": [
    "2. Define Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "25a3f788",
   "metadata": {},
   "outputs": [],
   "source": [
    "num_classes = 10\n",
    "input_shape = (28, 28, 1)\n",
    "model = create_conv_model(input_shape, num_classes)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "564ac93b",
   "metadata": {},
   "source": [
    "3. Define the device list for participating training, which is the PYUS of each participant prepared previously"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "a7955558",
   "metadata": {},
   "outputs": [],
   "source": [
    "device_list = [alice, bob]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "95051611",
   "metadata": {},
   "source": [
    "4. Define Aggregator  \n",
    " Secretflow offer a variety of aggregation schemes, `SecureAggregator` and `PPUAggregator`can be used security aggregation, more information about aggregation,see [Secure Aggregator](../developer/algorithm/secure_aggregation.ipynb)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "cfd83d07",
   "metadata": {},
   "outputs": [],
   "source": [
    "secure_aggregator = SecureAggregator(charlie, [alice, bob])\n",
    "spu_aggregator = SPUAggregator(spu)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4bb9c29c",
   "metadata": {},
   "source": [
    "5. Define `FLModel`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "1d4fbc7a",
   "metadata": {},
   "outputs": [],
   "source": [
    "fed_model = FLModel(server=charlie,\n",
    "                    device_list=device_list,\n",
    "                    model=model,\n",
    "                    aggregator=secure_aggregator,\n",
    "                    strategy=\"fed_avg_w\",\n",
    "                    backend = \"tensorflow\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e41f0a4c",
   "metadata": {},
   "source": [
    "6. Lets run model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "e5bcb2d0",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|█████████▉| 234/235 [00:04<00:00, 49.26it/s]2022-08-18 17:14:21.735534: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /opt/rh/devtoolset-10/root/usr/lib64:/opt/rh/devtoolset-10/root/usr/lib:/opt/rh/devtoolset-10/root/usr/lib64/dyninst:/opt/rh/devtoolset-10/root/usr/lib/dyninst:/opt/rh/devtoolset-10/root/usr/lib64:/opt/rh/devtoolset-10/root/usr/lib\n",
      "2022-08-18 17:14:21.735571: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)\n",
      "100%|██████████| 235/235 [00:18<00:00, 12.61it/s, epoch: 1/10 -  loss:0.5259245038032532  accuracy:0.8461666703224182  val_loss:0.14433448016643524  val_accuracy:0.9577999711036682 ]\n",
      "100%|██████████| 40/40 [00:04<00:00,  8.08it/s, epoch: 2/10 -  loss:0.1685342937707901  accuracy:0.9504940509796143  val_loss:0.12423974275588989  val_accuracy:0.964900016784668 ]\n",
      "100%|██████████| 40/40 [00:02<00:00, 13.97it/s, epoch: 3/10 -  loss:0.1499660760164261  accuracy:0.9557806253433228  val_loss:0.11904746294021606  val_accuracy:0.9649999737739563 ]\n",
      "100%|██████████| 40/40 [00:02<00:00, 14.88it/s, epoch: 4/10 -  loss:0.14443494379520416  accuracy:0.9566205739974976  val_loss:0.1067579835653305  val_accuracy:0.9693999886512756 ]\n",
      "100%|██████████| 40/40 [00:02<00:00, 14.78it/s, epoch: 5/10 -  loss:0.1303529143333435  accuracy:0.9610671997070312  val_loss:0.09679792076349258  val_accuracy:0.9718999862670898 ]\n",
      "100%|██████████| 40/40 [00:02<00:00, 14.61it/s, epoch: 6/10 -  loss:0.11564651876688004  accuracy:0.9659584760665894  val_loss:0.09385047107934952  val_accuracy:0.9726999998092651 ]\n",
      "100%|██████████| 40/40 [00:02<00:00, 14.48it/s, epoch: 7/10 -  loss:0.10946863144636154  accuracy:0.9681274890899658  val_loss:0.09159354865550995  val_accuracy:0.972599983215332 ]\n",
      "100%|██████████| 40/40 [00:02<00:00, 14.81it/s, epoch: 8/10 -  loss:0.10932281613349915  accuracy:0.9678359627723694  val_loss:0.08414007723331451  val_accuracy:0.9754999876022339 ]\n",
      "100%|██████████| 40/40 [00:02<00:00, 14.47it/s, epoch: 9/10 -  loss:0.10051391273736954  accuracy:0.9696640372276306  val_loss:0.08173993974924088  val_accuracy:0.9753999710083008 ]\n",
      "100%|██████████| 40/40 [00:02<00:00, 13.60it/s, epoch: 10/10 -  loss:0.10390906035900116  accuracy:0.968478262424469  val_loss:0.07482419162988663  val_accuracy:0.9775000214576721 ]\n"
     ]
    }
   ],
   "source": [
    "history = fed_model.fit(x_train, \n",
    "                        y_train, \n",
    "                        validation_data=(x_test, y_test), \n",
    "                        epochs=10,\n",
    "                        sampler_method=\"batch\",\n",
    "                        batch_size=128, \n",
    "                        aggregate_freq=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "fba7079a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Draw accuracy values for training & validation\n",
    "plt.plot(history.global_history['accuracy'])\n",
    "plt.plot(history.global_history['val_accuracy'])\n",
    "plt.title('FLModel accuracy')\n",
    "plt.ylabel('Accuracy')\n",
    "plt.xlabel('Epoch')\n",
    "plt.legend(['Train', 'Valid'], loc='upper left')\n",
    "plt.show()\n",
    "\n",
    "# Draw loss for training & validation\n",
    "plt.plot(history.global_history['loss'])\n",
    "plt.plot(history.global_history['val_loss'])\n",
    "plt.title('FLModel loss')\n",
    "plt.ylabel('Loss')\n",
    "plt.xlabel('Epoch')\n",
    "plt.legend(['Train', 'Valid'], loc='upper left')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "94aa9e5f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "([Mean(name='loss', total=748.24194, count=10000.0), Mean(name='accuracy', total=9775.0, count=10000.0)], {'alice': [Mean(name='loss', total=527.7763, count=5000.0), Mean(name='accuracy', total=4833.0, count=5000.0)], 'bob': [Mean(name='loss', total=220.46567, count=5000.0), Mean(name='accuracy', total=4942.0, count=5000.0)]})\n"
     ]
    }
   ],
   "source": [
    "global_metric = fed_model.evaluate(x_test, y_test, batch_size=128)\n",
    "print(global_metric)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cb9c64ba",
   "metadata": {},
   "source": [
    "### Contrast experiment to local training"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a1309ed8",
   "metadata": {},
   "source": [
    "#### Model\n",
    "The model structure is consistent with the fl model above\n",
    "#### Data\n",
    "Here, we only used data after a horizontal segmentation, with a total of 20,000 samples for `Alice`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "3a239a07",
   "metadata": {},
   "outputs": [],
   "source": [
    "from tensorflow import keras\n",
    "from tensorflow.keras import layers\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "def create_model():\n",
    "\n",
    "    model = keras.Sequential(\n",
    "        [\n",
    "            keras.Input(shape=input_shape),\n",
    "            layers.Conv2D(32, kernel_size=(3, 3), activation=\"relu\"),\n",
    "            layers.MaxPooling2D(pool_size=(2, 2)),\n",
    "            layers.Conv2D(64, kernel_size=(3, 3), activation=\"relu\"),\n",
    "            layers.MaxPooling2D(pool_size=(2, 2)),\n",
    "            layers.Flatten(),\n",
    "            layers.Dropout(0.5),\n",
    "            layers.Dense(num_classes, activation=\"softmax\"),\n",
    "        ]\n",
    "    )\n",
    "    # Compile model\n",
    "    model.compile(loss='categorical_crossentropy',\n",
    "                  optimizer='adam',\n",
    "                  metrics=[\"accuracy\"])\n",
    "    return model\n",
    "\n",
    "single_model = create_model()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "fbd979bf",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import OneHotEncoder\n",
    "\n",
    "alice_x = image[:10000]\n",
    "alice_y = label[:10000]\n",
    "alice_y = OneHotEncoder(sparse=False).fit_transform(alice_y.reshape(-1, 1))\n",
    "\n",
    "random_seed = 1234\n",
    "alice_X_train, alice_X_test, alice_y_train, alice_y_test = train_test_split(alice_x, \n",
    "    alice_y, test_size=0.33, random_state=random_seed)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "74524f78",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n",
      "53/53 [==============================] - 1s 16ms/step - loss: 8.1856 - accuracy: 0.5194 - val_loss: 0.5021 - val_accuracy: 0.8461\n",
      "Epoch 2/10\n",
      "53/53 [==============================] - 1s 13ms/step - loss: 0.7643 - accuracy: 0.7754 - val_loss: 0.3211 - val_accuracy: 0.9024\n",
      "Epoch 3/10\n",
      "53/53 [==============================] - 1s 13ms/step - loss: 0.5189 - accuracy: 0.8452 - val_loss: 0.2557 - val_accuracy: 0.9233\n",
      "Epoch 4/10\n",
      "53/53 [==============================] - 1s 14ms/step - loss: 0.3795 - accuracy: 0.8899 - val_loss: 0.1997 - val_accuracy: 0.9388\n",
      "Epoch 5/10\n",
      "53/53 [==============================] - 1s 13ms/step - loss: 0.3246 - accuracy: 0.9024 - val_loss: 0.1864 - val_accuracy: 0.9406\n",
      "Epoch 6/10\n",
      "53/53 [==============================] - 1s 13ms/step - loss: 0.2747 - accuracy: 0.9182 - val_loss: 0.1696 - val_accuracy: 0.9464\n",
      "Epoch 7/10\n",
      "53/53 [==============================] - 1s 12ms/step - loss: 0.2245 - accuracy: 0.9324 - val_loss: 0.1484 - val_accuracy: 0.9545\n",
      "Epoch 8/10\n",
      "53/53 [==============================] - 1s 13ms/step - loss: 0.2123 - accuracy: 0.9361 - val_loss: 0.1427 - val_accuracy: 0.9570\n",
      "Epoch 9/10\n",
      "53/53 [==============================] - 1s 13ms/step - loss: 0.1884 - accuracy: 0.9425 - val_loss: 0.1290 - val_accuracy: 0.9633\n",
      "Epoch 10/10\n",
      "53/53 [==============================] - 1s 13ms/step - loss: 0.1775 - accuracy: 0.9451 - val_loss: 0.1179 - val_accuracy: 0.9627\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x7fcd9c53f7c0>"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "single_model.fit(alice_X_train, alice_y_train, validation_data=(alice_X_test, alice_y_test), batch_size=128, epochs=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dbe14068",
   "metadata": {},
   "source": [
    "The two experiments above simulated a training problem in a typical horizontal federation scenario,\n",
    "* Alice and Bob have same type of data\n",
    "* Each side had only a portion of the sample, but the training objectives is the same \n",
    "If Alice only uses her own data to train the model, could only obtain a model with an accuracy of 0.945. However, if Bob's data is combined, a model with an accuracy close to 0.995 can be obtained. In addition, the generalization performance of the model jointly trained with multi-party data will also be better"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c15e286a",
   "metadata": {},
   "source": [
    "## Conclusion\n",
    "* This tutorial introduces what federated learning is and how to perform horizontal federated learning in `secretFlow`  \n",
    "* It can be seen from the experimental data that horizontal federation can improve the model effect by expanding the sample size and combining multi-party training.\n",
    "* This tutorial uses a SecureAggregator to demonstrate, and secretflow provides a variety of aggregation schemes，for more infomation, see [Secure Aggregation](../developer/algorithm/secure_aggregation.ipynb).\n",
    "* next, you can use your data or model to explore how to do federate learning\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.8.13 ('3.8')",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.13"
  },
  "vscode": {
   "interpreter": {
    "hash": "ae1fdd5fd034b7d694352220485921694ff89198520409089b4646721fce11ca"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}