diff --git a/examples/erniesage/models/erniesage_v2.py b/examples/erniesage/models/erniesage_v2.py
index 78fed26cc56b31c0e1e604e5d01b51657ee48fd2..7ad9a26caf87d7ed79fe55584f21fe8d4f46dd2d 100644
--- a/examples/erniesage/models/erniesage_v2.py
+++ b/examples/erniesage/models/erniesage_v2.py
@@ -81,14 +81,16 @@ class ErnieSageV2(BaseNet):
             self_feature = L.fc(self_feature,
                                            hidden_size,
                                            act=act,
-                                           param_attr=F.ParamAttr(name=name + "_l",
+                                           param_attr=F.ParamAttr(name=name + "_l.w_0",
                                            learning_rate=learning_rate),
+                                           bias_attr=name+"_l.b_0"
                                            )
             neigh_feature = L.fc(neigh_feature,
                                             hidden_size,
                                             act=act,
-                                            param_attr=F.ParamAttr(name=name + "_r",
-                                           learning_rate=learning_rate),
+                                            param_attr=F.ParamAttr(name=name + "_r.w_0",
+                                            learning_rate=learning_rate),
+                                            bias_attr=name+"_r.b_0"
                                             )
             output = L.concat([self_feature, neigh_feature], axis=1)
             output = L.l2_normalize(output, axis=1)
diff --git a/examples/erniesage/models/message_passing.py b/examples/erniesage/models/message_passing.py
index 4567bd694b123841c6b71b61a88e8dcbae8957b7..f45e4be000a17348664486f627f74934c81add1a 100644
--- a/examples/erniesage/models/message_passing.py
+++ b/examples/erniesage/models/message_passing.py
@@ -57,14 +57,16 @@ def graphsage_sum(gw, feature, hidden_size, act, initializer, learning_rate, nam
     self_feature = fluid.layers.fc(self_feature,
                                    hidden_size,
                                    act=act,
-                                   param_attr=fluid.ParamAttr(name=name + "_l", initializer=initializer,
+                                   param_attr=fluid.ParamAttr(name=name + "_l.w_0", initializer=initializer,
                                    learning_rate=learning_rate),
+                                    bias_attr=name+"_l.b_0"
                                    )
     neigh_feature = fluid.layers.fc(neigh_feature,
                                     hidden_size,
                                     act=act,
-                                    param_attr=fluid.ParamAttr(name=name + "_r", initializer=initializer,
+                                    param_attr=fluid.ParamAttr(name=name + "_r.w_0", initializer=initializer,
                                    learning_rate=learning_rate),
+                                    bias_attr=name+"_r.b_0"
                                     )
     output = fluid.layers.concat([self_feature, neigh_feature], axis=1)
     output = fluid.layers.l2_normalize(output, axis=1)
@@ -79,14 +81,16 @@ def graphsage_mean(gw, feature, hidden_size, act, initializer, learning_rate, na
     self_feature = fluid.layers.fc(self_feature,
                                    hidden_size,
                                    act=act,
-                                   param_attr=fluid.ParamAttr(name=name + "_l", initializer=initializer,
+                                   param_attr=fluid.ParamAttr(name=name + "_l.w_0", initializer=initializer,
                                    learning_rate=learning_rate),
+                                    bias_attr=name+"_l.b_0"
                                    )
     neigh_feature = fluid.layers.fc(neigh_feature,
                                     hidden_size,
                                     act=act,
-                                    param_attr=fluid.ParamAttr(name=name + "_r", initializer=initializer,
+                                    param_attr=fluid.ParamAttr(name=name + "_r.w_0", initializer=initializer,
                                    learning_rate=learning_rate),
+                                    bias_attr=name+"_r.b_0"
                                     )
     output = fluid.layers.concat([self_feature, neigh_feature], axis=1)
     output = fluid.layers.l2_normalize(output, axis=1)
@@ -101,14 +105,16 @@ def pinsage_mean(gw, feature, hidden_size, act, initializer, learning_rate, name
     self_feature = fluid.layers.fc(self_feature,
                                    hidden_size,
                                    act=act,
-                                   param_attr=fluid.ParamAttr(name=name + "_l", initializer=initializer,
+                                   param_attr=fluid.ParamAttr(name=name + "_l.w_0", initializer=initializer,
                                    learning_rate=learning_rate),
+                                    bias_attr=name+"_l.b_0"
                                    )
     neigh_feature = fluid.layers.fc(neigh_feature,
                                     hidden_size,
                                     act=act,
-                                    param_attr=fluid.ParamAttr(name=name + "_r", initializer=initializer,
+                                    param_attr=fluid.ParamAttr(name=name + "_r.w_0", initializer=initializer,
                                    learning_rate=learning_rate),
+                                    bias_attr=name+"_r.b_0"
                                     )
     output = fluid.layers.concat([self_feature, neigh_feature], axis=1)
     output = fluid.layers.l2_normalize(output, axis=1)
@@ -123,14 +129,16 @@ def pinsage_sum(gw, feature, hidden_size, act, initializer, learning_rate, name)
     self_feature = fluid.layers.fc(self_feature,
                                    hidden_size,
                                    act=act,
-                                   param_attr=fluid.ParamAttr(name=name + "_l", initializer=initializer,
+                                   param_attr=fluid.ParamAttr(name=name + "_l.w_0", initializer=initializer,
                                    learning_rate=learning_rate),
+                                    bias_attr=name+"_l.b_0"
                                    )
     neigh_feature = fluid.layers.fc(neigh_feature,
                                     hidden_size,
                                     act=act,
-                                    param_attr=fluid.ParamAttr(name=name + "_r", initializer=initializer,
+                                    param_attr=fluid.ParamAttr(name=name + "_r.w_0", initializer=initializer,
                                    learning_rate=learning_rate),
+                                    bias_attr=name+"_r.b_0"
                                     )
     output = fluid.layers.concat([self_feature, neigh_feature], axis=1)
     output = fluid.layers.l2_normalize(output, axis=1)
diff --git a/pgl/utils/mp_reader.py b/pgl/utils/mp_reader.py
index b7aec4d268e13d282c8420d80628f975e5472499..a7962830031c3aeede2b780104dacf936d62a120 100644
--- a/pgl/utils/mp_reader.py
+++ b/pgl/utils/mp_reader.py
@@ -25,7 +25,7 @@ except:
 import numpy as np
 import time
 import paddle.fluid as fluid
-from queue import Queue
+from multiprocessing import Queue
 import threading