Can graph regularization of tensorflow be also applicable to regression problems?

Roboticist · June 23, 2021, 3:14pm

The official webpage of the Neural Structured Learning has provided three tutorials all of which only focus on classification problems. So, can NSL and its graph regularization be also applicable to regression problems? If so, is there any example representing how that works?

Bhack · June 23, 2021, 9:18pm

Yes check:

github.com/tensorflow/neural-structured-learning

NSL for Regression

opened 10:07AM - 08 Apr 20 UTC

closed 11:44AM - 11 Apr 20 UTC

santhoshkolloju

question

I was able to integrate adversarial loss to my TensorFlow model, My input data h…as combination of categorical and continuous attributes. Is there any way to specify not to perturb categorical data while creating adversarial examples? ``` code: x = tf.placeholder(tf.float32,shape=(None,20)) y = tf.placeholder(tf.float32,shape=(None,1)) #build a sample model def model(x,y,is_training): with tf.variable_scope("regression_model",reuse=tf.AUTO_REUSE) as scope: layer0 = tf.layers.Dense(units=64,activation=tf.nn.relu)(x) layer1 = tf.layers.Dense(units=128,activation=tf.nn.relu)(layer0) output = tf.layers.Dense(units=1)(layer1) error = tf.subtract(y,output) print(error) loss = tf.reduce_mean(error,axis=0) return loss #normal loss mean absolute error regular_loss = model(x,y,True) adv_config = nsl.configs.AdvRegConfig() adv_input,adv_weights = nsl.lib.gen_adv_neighbor(x,regular_loss,config=adv_config.adv_neighbor_config) adv_loss = model(adv_input,y,True) overall_loss = regular_loss + 0.2*adv_loss train_step = optim.minimize(overall_loss) tf.random.set_random_seed(100) sess = tf.Session() init_op = tf.global_variables_initializer() sess.run(init_op) X = np.random.random((32,20))#batch of 32 Y = np.random.random((32,1)) sess.run([train_step,adv_loss,regular_loss,overall_loss],feed_dict={x:X,y:Y}) ```