nextrec 0.4.8__py3-none-any.whl → 0.4.9__py3-none-any.whl

nextrec/loss/__init__.py

@@ -5,6 +5,7 @@ from nextrec.loss.listwise import (
     ListNetLoss,
     SampledSoftmaxLoss,
 )
+from nextrec.loss.loss_utils import VALID_TASK_TYPES, get_loss_fn, get_loss_kwargs
 from nextrec.loss.pairwise import BPRLoss, HingeLoss, TripletLoss
 from nextrec.loss.pointwise import (
     ClassBalancedFocalLoss,
@@ -12,11 +13,6 @@ from nextrec.loss.pointwise import (
     FocalLoss,
     WeightedBCELoss,
 )
-from nextrec.loss.loss_utils import (
-    get_loss_fn,
-    get_loss_kwargs,
-    VALID_TASK_TYPES,
-)
 
 __all__ = [
     # Pointwise

nextrec/loss/loss_utils.py

@@ -2,7 +2,7 @@
 Loss utilities for NextRec.
 
 Date: create on 27/10/2025
-Checkpoint: edit on 17/12/2025
+Checkpoint: edit on 19/12/2025
 Author: Yang Zhou, zyaztec@gmail.com
 """
 
@@ -18,16 +18,10 @@ from nextrec.loss.listwise import (
     SampledSoftmaxLoss,
 )
 from nextrec.loss.pairwise import BPRLoss, HingeLoss, TripletLoss
-from nextrec.loss.pointwise import (
-    ClassBalancedFocalLoss,
-    FocalLoss,
-    WeightedBCELoss,
-)
-
+from nextrec.loss.pointwise import ClassBalancedFocalLoss, FocalLoss, WeightedBCELoss
 
 VALID_TASK_TYPES = [
     "binary",
-    "multiclass",
     "multilabel",
     "regression",
 ]

nextrec/models/generative/__init__.py

@@ -5,12 +5,5 @@ This module contains generative models for recommendation tasks.
 """
 
 from nextrec.models.generative.hstu import HSTU
-from nextrec.models.generative.rqvae import (
-    RQVAE,
-    RQ,
-    VQEmbedding,
-    BalancedKmeans,
-    kmeans,
-)
 
-__all__ = ["HSTU", "RQVAE", "RQ", "VQEmbedding", "BalancedKmeans", "kmeans"]
+__all__ = ["HSTU"]

nextrec/models/generative/hstu.py

@@ -54,10 +54,9 @@ import torch
 import torch.nn as nn
 import torch.nn.functional as F
 
-from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import RMSNorm, EmbeddingLayer
 from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
-
+from nextrec.basic.layers import EmbeddingLayer, RMSNorm
+from nextrec.basic.model import BaseModel
 from nextrec.utils.model import select_features
 
 
@@ -302,7 +301,7 @@ class HSTU(BaseModel):
 
     @property
     def default_task(self) -> str:
-        return "multiclass"
+        return "binary"
 
     def __init__(
         self,
@@ -336,6 +335,9 @@ class HSTU(BaseModel):
         device: str = "cpu",
         **kwargs,
     ):
+        raise NotImplementedError(
+            "[HSTU Error] NextRec no longer supports multiclass tasks; HSTU is disabled."
+        )
         if not sequence_features:
             raise ValueError(
                 "[HSTU Error] HSTU requires at least one SequenceFeature (user behavior history)."

nextrec/models/multi_task/esmm.py

@@ -44,9 +44,9 @@ CVR 预测 P(conversion|click)，二者相乘得到 CTCVR 并在曝光标签上
 import torch
 import torch.nn as nn
 
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import MLP, EmbeddingLayer, PredictionLayer
 from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import EmbeddingLayer, MLP, PredictionLayer
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
 
 
 class ESMM(BaseModel):

nextrec/models/multi_task/mmoe.py

@@ -45,9 +45,9 @@ MMoE（Multi-gate Mixture-of-Experts）是多任务学习框架，通过多个
 import torch
 import torch.nn as nn
 
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import MLP, EmbeddingLayer, PredictionLayer
 from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import EmbeddingLayer, MLP, PredictionLayer
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
 
 
 class MMOE(BaseModel):

nextrec/models/multi_task/ple.py

@@ -48,9 +48,9 @@ PLE（Progressive Layered Extraction）通过堆叠 CGC 模块，联合共享与
 import torch
 import torch.nn as nn
 
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import MLP, EmbeddingLayer, PredictionLayer
 from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import EmbeddingLayer, MLP, PredictionLayer
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
 from nextrec.utils.model import get_mlp_output_dim
 
 

nextrec/models/multi_task/poso.py

@@ -42,11 +42,10 @@ import torch
 import torch.nn as nn
 import torch.nn.functional as F
 
-from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
-from nextrec.basic.layers import EmbeddingLayer, MLP, PredictionLayer
 from nextrec.basic.activation import activation_layer
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import MLP, EmbeddingLayer, PredictionLayer
 from nextrec.basic.model import BaseModel
-
 from nextrec.utils.model import select_features
 
 

nextrec/models/multi_task/share_bottom.py

@@ -42,9 +42,9 @@ Share-Bottom（硬共享底层）是多任务学习的经典基线：所有任
 import torch
 import torch.nn as nn
 
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import MLP, EmbeddingLayer, PredictionLayer
 from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import EmbeddingLayer, MLP, PredictionLayer
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
 
 
 class ShareBottom(BaseModel):

nextrec/models/ranking/afm.py

@@ -39,9 +39,9 @@ AFM 在 FM 的二阶交互上引入注意力，为每个特征对学习重要性
 import torch
 import torch.nn as nn
 
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import EmbeddingLayer, InputMask, PredictionLayer
 from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import EmbeddingLayer, PredictionLayer, InputMask
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
 
 
 class AFM(BaseModel):

nextrec/models/ranking/autoint.py

@@ -57,9 +57,9 @@ AutoInt 通过对所有特征 embedding 进行注意力计算，捕捉特征之
 import torch
 import torch.nn as nn
 
-from nextrec.basic.model import BaseModel
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import EmbeddingLayer, MultiHeadSelfAttention, PredictionLayer
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
+from nextrec.basic.model import BaseModel
 
 
 class AutoInt(BaseModel):

nextrec/models/ranking/dcn.py

@@ -53,9 +53,9 @@ Deep 分支提升表达能力；最终将 Cross（及 Deep）结果送入线性
 import torch
 import torch.nn as nn
 
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import MLP, EmbeddingLayer, PredictionLayer
 from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import EmbeddingLayer, MLP, PredictionLayer
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
 
 
 class CrossNetwork(nn.Module):

nextrec/models/ranking/dcn_v2.py

@@ -46,9 +46,9 @@ DCN v2 在原始 DCN 基础上，将标量交叉权重升级为向量/矩阵参
 import torch
 import torch.nn as nn
 
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import MLP, EmbeddingLayer, PredictionLayer
 from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import EmbeddingLayer, MLP, PredictionLayer
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
 
 
 class CrossNetV2(nn.Module):

nextrec/models/ranking/deepfm.py

@@ -45,9 +45,9 @@ embedding，无需手工构造交叉特征即可端到端训练，常用于 CTR/
 
 import torch.nn as nn
 
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import FM, LR, MLP, EmbeddingLayer, PredictionLayer
 from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import FM, LR, EmbeddingLayer, MLP, PredictionLayer
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
 
 
 class DeepFM(BaseModel):

nextrec/models/ranking/dien.py

@@ -50,14 +50,14 @@ import torch
 import torch.nn as nn
 import torch.nn.functional as F
 
-from nextrec.basic.model import BaseModel
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import (
-    EmbeddingLayer,
     MLP,
     AttentionPoolingLayer,
+    EmbeddingLayer,
     PredictionLayer,
 )
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
+from nextrec.basic.model import BaseModel
 
 
 class AUGRU(nn.Module):

nextrec/models/ranking/din.py

@@ -50,14 +50,14 @@ DIN 是一个 CTR 预估模型，通过对用户历史行为序列进行目标
 import torch
 import torch.nn as nn
 
-from nextrec.basic.model import BaseModel
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import (
-    EmbeddingLayer,
     MLP,
     AttentionPoolingLayer,
+    EmbeddingLayer,
     PredictionLayer,
 )
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
+from nextrec.basic.model import BaseModel
 
 
 class DIN(BaseModel):

nextrec/models/ranking/fibinet.py

@@ -43,17 +43,17 @@ FiBiNET 是一个 CTR 预估模型，通过 SENET 重新分配特征字段的重
 import torch
 import torch.nn as nn
 
-from nextrec.basic.model import BaseModel
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import (
-    BiLinearInteractionLayer,
-    HadamardInteractionLayer,
-    EmbeddingLayer,
     LR,
     MLP,
+    BiLinearInteractionLayer,
+    EmbeddingLayer,
+    HadamardInteractionLayer,
     PredictionLayer,
     SENETLayer,
 )
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
+from nextrec.basic.model import BaseModel
 
 
 class FiBiNET(BaseModel):

nextrec/models/ranking/fm.py

@@ -40,14 +40,10 @@ FM 是一种通过分解二阶特征交互矩阵、以线性复杂度建模特
 
 import torch.nn as nn
 
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import FM as FMInteraction
+from nextrec.basic.layers import LR, EmbeddingLayer, PredictionLayer
 from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import (
-    EmbeddingLayer,
-    FM as FMInteraction,
-    LR,
-    PredictionLayer,
-)
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
 
 
 class FM(BaseModel):

nextrec/models/ranking/masknet.py

@@ -57,9 +57,9 @@ import torch
 import torch.nn as nn
 import torch.nn.functional as F
 
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import MLP, EmbeddingLayer, PredictionLayer
 from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import EmbeddingLayer, MLP, PredictionLayer
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
 
 
 class InstanceGuidedMask(nn.Module):

nextrec/models/ranking/pnn.py

@@ -37,9 +37,9 @@ PNN 是一种 CTR 预估模型，通过将线性信号与乘积信号结合，
 import torch
 import torch.nn as nn
 
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import MLP, EmbeddingLayer, PredictionLayer
 from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import EmbeddingLayer, MLP, PredictionLayer
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
 
 
 class PNN(BaseModel):

nextrec/models/ranking/widedeep.py

@@ -41,9 +41,9 @@ Wide & Deep 同时使用宽线性部分（记忆共现/手工交叉）与深网
 
 import torch.nn as nn
 
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import LR, MLP, EmbeddingLayer, PredictionLayer
 from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import LR, EmbeddingLayer, MLP, PredictionLayer
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
 
 
 class WideDeep(BaseModel):

nextrec/models/ranking/xdeepfm.py

@@ -55,9 +55,9 @@ import torch
 import torch.nn as nn
 import torch.nn.functional as F
 
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
+from nextrec.basic.layers import LR, MLP, EmbeddingLayer, PredictionLayer
 from nextrec.basic.model import BaseModel
-from nextrec.basic.layers import LR, EmbeddingLayer, MLP, PredictionLayer
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
 
 
 class CIN(nn.Module):

nextrec/models/representation/__init__.py

@@ -0,0 +1,9 @@
+from nextrec.models.representation.rqvae import (
+    RQ,
+    RQVAE,
+    BalancedKmeans,
+    VQEmbedding,
+    kmeans,
+)
+
+__all__ = ["RQVAE", "RQ", "VQEmbedding", "BalancedKmeans", "kmeans"]

nextrec/models/{generative → representation}/rqvae.py

@@ -46,21 +46,21 @@ RQ-VAE 通过残差量化学习分层离散表示，将连续嵌入（如物品/
 
 from __future__ import annotations
 
+import logging
 import math
+from typing import cast
+
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
 from sklearn.cluster import KMeans
-from typing import cast
-import logging
-import tqdm
-
 from torch.utils.data import DataLoader
 
 from nextrec.basic.features import DenseFeature
+from nextrec.basic.loggers import colorize, setup_logger
 from nextrec.basic.model import BaseModel
 from nextrec.data.batch_utils import batch_to_dict
-from nextrec.basic.loggers import colorize, setup_logger
+from nextrec.utils.console import progress
 
 
 def kmeans(
@@ -729,9 +729,9 @@ class RQVAE(BaseModel):
             else:
                 tqdm_disable = not self.is_main_process
                 batch_iter = enumerate(
-                    tqdm.tqdm(
+                    progress(
                         train_loader,
-                        desc=f"Epoch {epoch + 1}/{epochs}",
+                        description=f"Epoch {epoch + 1}/{epochs}",
                         total=steps_per_epoch,
                         disable=tqdm_disable,
                     )
@@ -777,9 +777,9 @@ class RQVAE(BaseModel):
                 logging.info(colorize(train_log))
 
         if self.is_main_process:
-            logging.info(" ")
+            logging.info("")
             logging.info(colorize("Training finished.", bold=True))
-            logging.info(" ")
+            logging.info("")
         return self
 
     def predict(

nextrec/models/{match → retrieval}/dssm.py

@@ -7,13 +7,14 @@ Reference:
 //Proceedings of the 22nd ACM international conference on Information & Knowledge Management. 2013: 2333-2338.
 """
 
+from typing import Literal
+
 import torch
 import torch.nn as nn
-from typing import Literal
 
-from nextrec.basic.model import BaseMatchModel
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import MLP, EmbeddingLayer
+from nextrec.basic.model import BaseMatchModel
 
 
 class DSSM(BaseMatchModel):
@@ -28,6 +29,10 @@ class DSSM(BaseMatchModel):
     def model_name(self) -> str:
         return "DSSM"
 
+    @property
+    def support_training_modes(self) -> list[str]:
+        return ["pointwise", "pairwise", "listwise"]
+
     def __init__(
         self,
         user_dense_features: list[DenseFeature] | None = None,

nextrec/models/{match → retrieval}/dssm_v2.py

@@ -6,13 +6,14 @@ Reference:
 DSSM v2 - DSSM with pairwise training using BPR loss
 """
 
+from typing import Literal
+
 import torch
 import torch.nn as nn
-from typing import Literal
 
-from nextrec.basic.model import BaseMatchModel
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import MLP, EmbeddingLayer
+from nextrec.basic.model import BaseMatchModel
 
 
 class DSSM_v2(BaseMatchModel):
@@ -24,6 +25,10 @@ class DSSM_v2(BaseMatchModel):
     def model_name(self) -> str:
         return "DSSM_v2"
 
+    @property
+    def support_training_modes(self) -> list[str]:
+        return ["pointwise", "pairwise", "listwise"]
+
     def __init__(
         self,
         user_dense_features: list[DenseFeature] | None = None,

nextrec/models/{match → retrieval}/mind.py

@@ -7,14 +7,15 @@ Reference:
 //Proceedings of the 28th ACM international conference on information and knowledge management. 2019: 2615-2623.
 """
 
+from typing import Literal
+
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
-from typing import Literal
 
-from nextrec.basic.model import BaseMatchModel
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import MLP, EmbeddingLayer
+from nextrec.basic.model import BaseMatchModel
 
 
 class MultiInterestSA(nn.Module):

nextrec/models/{match → retrieval}/sdm.py

@@ -7,14 +7,15 @@ Reference:
 //IJCAI. 2018: 3926-3932.
 """
 
+from typing import Literal
+
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
-from typing import Literal
 
-from nextrec.basic.model import BaseMatchModel
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import MLP, EmbeddingLayer
+from nextrec.basic.model import BaseMatchModel
 
 
 class SDM(BaseMatchModel):

nextrec/models/{match → retrieval}/youtube_dnn.py

@@ -7,13 +7,14 @@ Reference:
 //Proceedings of the 10th ACM conference on recommender systems. 2016: 191-198.
 """
 
+from typing import Literal
+
 import torch
 import torch.nn as nn
-from typing import Literal
 
-from nextrec.basic.model import BaseMatchModel
-from nextrec.basic.features import DenseFeature, SparseFeature, SequenceFeature
+from nextrec.basic.features import DenseFeature, SequenceFeature, SparseFeature
 from nextrec.basic.layers import MLP, EmbeddingLayer
+from nextrec.basic.model import BaseMatchModel
 
 
 class YoutubeDNN(BaseMatchModel):
@@ -28,6 +29,10 @@ class YoutubeDNN(BaseMatchModel):
     def model_name(self) -> str:
         return "YouTubeDNN"
 
+    @property
+    def support_training_modes(self) -> list[str]:
+        return ["pointwise", "pairwise", "listwise"]
+
     def __init__(
         self,
         user_dense_features: list[DenseFeature] | None = None,