diff --git a/doc/ensemble.rst b/doc/ensemble.rst
index 0700ea0aa..159a23b76 100644
--- a/doc/ensemble.rst
+++ b/doc/ensemble.rst
@@ -59,7 +59,7 @@ random under-sampler::
   BalancedBaggingClassifier(...)
   >>> y_pred = bbc.predict(X_test)
   >>> balanced_accuracy_score(y_test, y_pred)  # doctest: +ELLIPSIS
-  0.80...
+  0.8...
 
 .. _forest:
 
diff --git a/examples/model_selection/plot_validation_curve.py b/examples/model_selection/plot_validation_curve.py
index 7e6ffdb68..5d83e7497 100644
--- a/examples/model_selection/plot_validation_curve.py
+++ b/examples/model_selection/plot_validation_curve.py
@@ -39,7 +39,7 @@
 param_range = range(1, 11)
 train_scores, test_scores = ms.validation_curve(
     pipeline, X, y, param_name="smote__k_neighbors", param_range=param_range,
-    cv=3, scoring=scorer, n_jobs=1)
+    cv=3, scoring=scorer)
 train_scores_mean = np.mean(train_scores, axis=1)
 train_scores_std = np.std(train_scores, axis=1)
 test_scores_mean = np.mean(test_scores, axis=1)
diff --git a/imblearn/combine/_smote_enn.py b/imblearn/combine/_smote_enn.py
index 10d423ddd..657e2a222 100644
--- a/imblearn/combine/_smote_enn.py
+++ b/imblearn/combine/_smote_enn.py
@@ -45,9 +45,12 @@ class SMOTEENN(BaseSampler):
         :class:`imblearn.under_sampling.EditedNearestNeighbours` object with
         sampling strategy='all' will be given.
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
-        Will not apply to smote and enn given by the user.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Notes
     -----
@@ -93,7 +96,7 @@ def __init__(
         random_state=None,
         smote=None,
         enn=None,
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__()
         self.sampling_strategy = sampling_strategy
diff --git a/imblearn/combine/_smote_tomek.py b/imblearn/combine/_smote_tomek.py
index af99d002d..595b208be 100644
--- a/imblearn/combine/_smote_tomek.py
+++ b/imblearn/combine/_smote_tomek.py
@@ -45,9 +45,12 @@ class SMOTETomek(BaseSampler):
         given, a :class:`imblearn.under_sampling.TomekLinks` object with
         sampling strategy='all' will be given.
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
-        Will not apply to smote and tomek given by the user.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Notes
     -----
@@ -93,7 +96,7 @@ def __init__(
         random_state=None,
         smote=None,
         tomek=None,
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__()
         self.sampling_strategy = sampling_strategy
diff --git a/imblearn/ensemble/_bagging.py b/imblearn/ensemble/_bagging.py
index e77ab892d..26bb2b4b1 100644
--- a/imblearn/ensemble/_bagging.py
+++ b/imblearn/ensemble/_bagging.py
@@ -73,9 +73,12 @@ class BalancedBaggingClassifier(BaggingClassifier):
     replacement : bool, optional (default=False)
         Whether or not to sample randomly with replacement or not.
 
-    n_jobs : int, optional (default=1)
-        The number of jobs to run in parallel for both `fit` and `predict`.
-        If -1, then the number of jobs is set to the number of cores.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     {random_state}
 
@@ -178,7 +181,7 @@ def __init__(
         warm_start=False,
         sampling_strategy="auto",
         replacement=False,
-        n_jobs=1,
+        n_jobs=None,
         random_state=None,
         verbose=0,
     ):
diff --git a/imblearn/ensemble/_easy_ensemble.py b/imblearn/ensemble/_easy_ensemble.py
index 808d36b97..2c02d6c59 100644
--- a/imblearn/ensemble/_easy_ensemble.py
+++ b/imblearn/ensemble/_easy_ensemble.py
@@ -53,9 +53,12 @@ class EasyEnsembleClassifier(BaggingClassifier):
     replacement : bool, optional (default=False)
         Whether or not to sample randomly with replacement or not.
 
-    n_jobs : int, optional (default=1)
-        The number of jobs to run in parallel for both `fit` and `predict`.
-        If -1, then the number of jobs is set to the number of cores.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     {random_state}
 
@@ -126,7 +129,7 @@ def __init__(
         warm_start=False,
         sampling_strategy="auto",
         replacement=False,
-        n_jobs=1,
+        n_jobs=None,
         random_state=None,
         verbose=0,
     ):
diff --git a/imblearn/ensemble/_forest.py b/imblearn/ensemble/_forest.py
index 68769d12e..db17c4a11 100644
--- a/imblearn/ensemble/_forest.py
+++ b/imblearn/ensemble/_forest.py
@@ -161,9 +161,12 @@ class BalancedRandomForestClassifier(RandomForestClassifier):
     replacement : bool, optional (default=False)
         Whether or not to sample randomly with replacement or not.
 
-    n_jobs : int, optional (default=1)
-        The number of jobs to run in parallel for both `fit` and `predict`.
-        If -1, then the number of jobs is set to the number of cores.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     {random_state}
 
@@ -299,7 +302,7 @@ def __init__(
         oob_score=False,
         sampling_strategy="auto",
         replacement=False,
-        n_jobs=1,
+        n_jobs=None,
         random_state=None,
         verbose=0,
         warm_start=False,
diff --git a/imblearn/over_sampling/_adasyn.py b/imblearn/over_sampling/_adasyn.py
index 507ddfd25..a7ea9104b 100644
--- a/imblearn/over_sampling/_adasyn.py
+++ b/imblearn/over_sampling/_adasyn.py
@@ -38,8 +38,12 @@ class ADASYN(BaseOverSampler):
         :class:`sklearn.neighbors.base.KNeighborsMixin` that will be used to
         find the k_neighbors.
 
-    n_jobs : int, optional (default=1)
-        Number of threads to run the algorithm when it is possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Notes
     -----
@@ -83,7 +87,7 @@ def __init__(
         sampling_strategy="auto",
         random_state=None,
         n_neighbors=5,
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__(sampling_strategy=sampling_strategy)
         self.random_state = random_state
diff --git a/imblearn/over_sampling/_smote.py b/imblearn/over_sampling/_smote.py
index 4798efadf..a81c492bf 100644
--- a/imblearn/over_sampling/_smote.py
+++ b/imblearn/over_sampling/_smote.py
@@ -40,7 +40,7 @@ def __init__(
         sampling_strategy="auto",
         random_state=None,
         k_neighbors=5,
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__(sampling_strategy=sampling_strategy)
         self.random_state = random_state
@@ -252,8 +252,12 @@ class BorderlineSMOTE(BaseSMOTE):
         :class:`sklearn.neighbors.base.KNeighborsMixin` that will be used to
         find the k_neighbors.
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     m_neighbors : int or object, optional (default=10)
         If int, number of nearest neighbours to use to determine if a minority
@@ -316,7 +320,7 @@ def __init__(
         sampling_strategy="auto",
         random_state=None,
         k_neighbors=5,
-        n_jobs=1,
+        n_jobs=None,
         m_neighbors=10,
         kind="borderline-1",
     ):
@@ -446,8 +450,12 @@ class SVMSMOTE(BaseSMOTE):
         :class:`sklearn.neighbors.base.KNeighborsMixin` that will be used to
         find the k_neighbors.
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     m_neighbors : int or object, optional (default=10)
         If int, number of nearest neighbours to use to determine if a minority
@@ -512,7 +520,7 @@ def __init__(
         sampling_strategy="auto",
         random_state=None,
         k_neighbors=5,
-        n_jobs=1,
+        n_jobs=None,
         m_neighbors=10,
         svm_estimator=None,
         out_step=0.5,
@@ -661,8 +669,12 @@ class SMOTE(BaseSMOTE):
         :class:`sklearn.neighbors.base.KNeighborsMixin` that will be used to
         find the k_neighbors.
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Notes
     -----
@@ -711,7 +723,7 @@ def __init__(
         sampling_strategy="auto",
         random_state=None,
         k_neighbors=5,
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__(
             sampling_strategy=sampling_strategy,
@@ -822,8 +834,12 @@ class SMOTENC(SMOTE):
         :class:`sklearn.neighbors.base.KNeighborsMixin` that will be used to
         find the k_neighbors.
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Notes
     -----
@@ -881,7 +897,7 @@ def __init__(
         sampling_strategy="auto",
         random_state=None,
         k_neighbors=5,
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__(
             sampling_strategy=sampling_strategy,
@@ -1068,8 +1084,12 @@ class KMeansSMOTE(BaseSMOTE):
         :class:`sklearn.neighbors.base.KNeighborsMixin` that will be used to
         find the k_neighbors.
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     kmeans_estimator : int or object, optional (default=MiniBatchKMeans())
         A KMeans instance or the number of clusters to be used. By default,
@@ -1134,7 +1154,7 @@ def __init__(
         sampling_strategy="auto",
         random_state=None,
         k_neighbors=2,
-        n_jobs=1,
+        n_jobs=None,
         kmeans_estimator=None,
         cluster_balance_threshold="auto",
         density_exponent="auto",
diff --git a/imblearn/under_sampling/_prototype_generation/_cluster_centroids.py b/imblearn/under_sampling/_prototype_generation/_cluster_centroids.py
index 98054e4fa..1c079d1a6 100644
--- a/imblearn/under_sampling/_prototype_generation/_cluster_centroids.py
+++ b/imblearn/under_sampling/_prototype_generation/_cluster_centroids.py
@@ -59,8 +59,12 @@ class ClusterCentroids(BaseUnderSampler):
 
         .. versionadded:: 0.3.0
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Notes
     -----
@@ -92,7 +96,7 @@ def __init__(
         random_state=None,
         estimator=None,
         voting="auto",
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__(sampling_strategy=sampling_strategy)
         self.random_state = random_state
diff --git a/imblearn/under_sampling/_prototype_selection/_condensed_nearest_neighbour.py b/imblearn/under_sampling/_prototype_selection/_condensed_nearest_neighbour.py
index 9b0bea3c8..c47adbcac 100644
--- a/imblearn/under_sampling/_prototype_selection/_condensed_nearest_neighbour.py
+++ b/imblearn/under_sampling/_prototype_selection/_condensed_nearest_neighbour.py
@@ -46,8 +46,12 @@ class CondensedNearestNeighbour(BaseCleaningSampler):
     n_seeds_S : int, optional (default=1)
         Number of samples to extract in order to build the set S.
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Attributes
     ----------
@@ -97,7 +101,7 @@ def __init__(
         random_state=None,
         n_neighbors=None,
         n_seeds_S=1,
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__(sampling_strategy=sampling_strategy)
         self.random_state = random_state
diff --git a/imblearn/under_sampling/_prototype_selection/_edited_nearest_neighbours.py b/imblearn/under_sampling/_prototype_selection/_edited_nearest_neighbours.py
index 94aef0268..fc14524a3 100644
--- a/imblearn/under_sampling/_prototype_selection/_edited_nearest_neighbours.py
+++ b/imblearn/under_sampling/_prototype_selection/_edited_nearest_neighbours.py
@@ -47,8 +47,12 @@ class EditedNearestNeighbours(BaseCleaningSampler):
         - If ``'mode'``, the majority vote of the neighbours will be used in
           order to exclude a sample.
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Attributes
     ----------
@@ -94,7 +98,7 @@ class EditedNearestNeighbours(BaseCleaningSampler):
     """
 
     def __init__(
-        self, sampling_strategy="auto", n_neighbors=3, kind_sel="all", n_jobs=1
+        self, sampling_strategy="auto", n_neighbors=3, kind_sel="all", n_jobs=None
     ):
         super().__init__(sampling_strategy=sampling_strategy)
         self.n_neighbors = n_neighbors
@@ -184,8 +188,12 @@ class RepeatedEditedNearestNeighbours(BaseCleaningSampler):
         - If ``'mode'``, the majority vote of the neighbours will be used in
           order to exclude a sample.
 
-    n_jobs : int, optional (default=1)
-        The number of thread to open when it is possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Attributes
     ----------
@@ -236,7 +244,7 @@ def __init__(
         n_neighbors=3,
         max_iter=100,
         kind_sel="all",
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__(sampling_strategy=sampling_strategy)
         self.n_neighbors = n_neighbors
@@ -354,8 +362,12 @@ class without early stopping.
 
         .. versionadded:: 0.3
 
-    n_jobs : int, optional (default=1)
-        The number of thread to open when it is possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Attributes
     ----------
@@ -407,7 +419,7 @@ def __init__(
         n_neighbors=3,
         kind_sel="all",
         allow_minority=False,
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__(sampling_strategy=sampling_strategy)
         self.n_neighbors = n_neighbors
diff --git a/imblearn/under_sampling/_prototype_selection/_instance_hardness_threshold.py b/imblearn/under_sampling/_prototype_selection/_instance_hardness_threshold.py
index 16d69056b..2bdd1c914 100644
--- a/imblearn/under_sampling/_prototype_selection/_instance_hardness_threshold.py
+++ b/imblearn/under_sampling/_prototype_selection/_instance_hardness_threshold.py
@@ -48,8 +48,12 @@ class InstanceHardnessThreshold(BaseUnderSampler):
     cv : int, optional (default=5)
         Number of folds to be used when estimating samples' instance hardness.
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Attributes
     ----------
@@ -95,7 +99,7 @@ def __init__(
         sampling_strategy="auto",
         random_state=None,
         cv=5,
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__(sampling_strategy=sampling_strategy)
         self.random_state = random_state
diff --git a/imblearn/under_sampling/_prototype_selection/_nearmiss.py b/imblearn/under_sampling/_prototype_selection/_nearmiss.py
index 5f76a34cf..b8ccb91b7 100644
--- a/imblearn/under_sampling/_prototype_selection/_nearmiss.py
+++ b/imblearn/under_sampling/_prototype_selection/_nearmiss.py
@@ -44,8 +44,12 @@ class NearMiss(BaseUnderSampler):
         :class:`sklearn.neighbors.base.KNeighborsMixin` that will be used to
         find the k_neighbors.
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Attributes
     ----------
@@ -91,7 +95,7 @@ def __init__(
         version=1,
         n_neighbors=3,
         n_neighbors_ver3=3,
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__(sampling_strategy=sampling_strategy)
         self.version = version
diff --git a/imblearn/under_sampling/_prototype_selection/_neighbourhood_cleaning_rule.py b/imblearn/under_sampling/_prototype_selection/_neighbourhood_cleaning_rule.py
index 0cd6daea4..05e077c38 100644
--- a/imblearn/under_sampling/_prototype_selection/_neighbourhood_cleaning_rule.py
+++ b/imblearn/under_sampling/_prototype_selection/_neighbourhood_cleaning_rule.py
@@ -47,8 +47,12 @@ class NeighbourhoodCleaningRule(BaseCleaningSampler):
         where Ci and C is the number of samples in the class and the data set,
         respectively and theta is the threshold.
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Attributes
     ----------
@@ -94,7 +98,7 @@ def __init__(
         n_neighbors=3,
         kind_sel="all",
         threshold_cleaning=0.5,
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__(sampling_strategy=sampling_strategy)
         self.n_neighbors = n_neighbors
diff --git a/imblearn/under_sampling/_prototype_selection/_one_sided_selection.py b/imblearn/under_sampling/_prototype_selection/_one_sided_selection.py
index aa37c0337..6bf093c56 100644
--- a/imblearn/under_sampling/_prototype_selection/_one_sided_selection.py
+++ b/imblearn/under_sampling/_prototype_selection/_one_sided_selection.py
@@ -43,8 +43,12 @@ class OneSidedSelection(BaseCleaningSampler):
     n_seeds_S : int, optional (default=1)
         Number of samples to extract in order to build the set S.
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Attributes
     ----------
@@ -91,7 +95,7 @@ def __init__(
         random_state=None,
         n_neighbors=None,
         n_seeds_S=1,
-        n_jobs=1,
+        n_jobs=None,
     ):
         super().__init__(sampling_strategy=sampling_strategy)
         self.random_state = random_state
diff --git a/imblearn/under_sampling/_prototype_selection/_tomek_links.py b/imblearn/under_sampling/_prototype_selection/_tomek_links.py
index 603930050..9eacf0367 100644
--- a/imblearn/under_sampling/_prototype_selection/_tomek_links.py
+++ b/imblearn/under_sampling/_prototype_selection/_tomek_links.py
@@ -25,8 +25,12 @@ class TomekLinks(BaseCleaningSampler):
     ----------
     {sampling_strategy}
 
-    n_jobs : int, optional (default=1)
-        The number of threads to open if possible.
+    n_jobs : int or None, optional (default=None)
+        Number of CPU cores used during the cross-validation loop.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See
+        `Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
+        for more details.
 
     Attributes
     ----------
@@ -66,7 +70,7 @@ class TomekLinks(BaseCleaningSampler):
 
     """
 
-    def __init__(self, sampling_strategy="auto", n_jobs=1):
+    def __init__(self, sampling_strategy="auto", n_jobs=None):
         super().__init__(sampling_strategy=sampling_strategy)
         self.n_jobs = n_jobs