Adaptive Item-based Collaborative Structures via Noise Rescheduling in Diffusion for Generative Recommendation

Jiaqi Wang; Tianying Liu; Heng Chang; Jihong Guan; Wengen Li; Shuigeng Zhou

cs.IRAug 24, 2026

Adaptive Item-based Collaborative Structures via Noise Rescheduling in Diffusion for Generative Recommendation

Authors: Jiaqi Wang, Tianying Liu, Heng Chang, Jihong Guan, Wengen Li, Shuigeng Zhou

Organizations: Fudan University, Shanghai, China · Tongji University, Shanghai, China

Abstract

Discrete Diffusion Models (DDMs) have recently been introduced to recommendation systems, modeling user history as a token generation process via iterative denoising. However, while effective at capturing user-level sequential patterns, these methods often fail to explicitly integrate item-based collaborative filtering information, a critical component for accurate recommendation. This deficiency manifests in two key aspects: (1) the item representation is often semantic-focused, lacking collaborative priors for diffusion training; and (2) the denoising process employs a uniform noise schedule, treating all tokens indiscriminately and ignoring item-level adaptive structural dependencies. To bridge this gap, we propose ANR-DiffRec, a unified framework designed to encode item-based collaborative structures into discrete diffusion for generative recommendation. First, we explicitly incorporate an item co-occurrence matrix to guide semantic ID generation, providing a structured collaborative prior for discrete diffusion training. Second, we introduce an item-based adaptive noise rescheduling mechanism that dynamically adjusts denoising weights according to both local contextual recoverability and behavior-aware item dependencies. Specifically, the proposed strategy jointly models intra-item structural context and inter-item collaborative signals, enabling structure-aware denoising during diffusion training. Extensive experiments on multiple benchmarks demonstrate that our method consistently outperforms state-of-the-art generative recommendation models. Code: https://github.com/CalmaQi/ANR-DiffRec.

Figures & tables

Figure 1. Illustration of the proposed item-based adaptive noise rescheduling strategy. (a) Existing diffusion-based recommendation models employ a uniform noise schedule, assigning identical denoising weights to masked tokens regardless of their contextual dependencies. (b) Our method dynamically adjusts the denoising weight for each token by jointly considering two complementary signals: (1) local recoverability estimation, and (2) behavior-aware dependency modeling. The final denoising weight is obtained by combining these two signals, enabling structure-aware diffusion training.

Figure 2. The architecture of ANR-DiffRec. (a) SID generation via fusion of semantic and collaborative signals. (b) Discrete diffusion training enhanced by item-based adaptive noise rescheduling, enabling structure-aware denoising to capture collaborative filtering signals. (c) Constrained discrete diffusion inference with validity filtering.

Dataset	#Users	#Items	#Interactions	Sparsity	Avg.Len
Scientific	50,985	25,848	412,947	99.969%	8.10
Instrument	57,439	24,587	511,836	99.964%	8.91
Game	94,762	25,612	814,586	99.966%	8.60
Steam	39,795	9,265	2,949,605	99.200%	74.12
MovieLens	6,040	3,883	1,001,456	95.730%	165.57

Table 1. Statistics of the used datasets. “Avg.Len” indicates the average number of interactions per user.

Category	Model	Scientific					Instrument					Game
Category	Model	R@1	R@5	R@10	N@5	N@10	R@1	R@5	R@10	N@5	N@10	R@1	R@5	R@10	N@5	N@10
Item ID based	GRU4Rec ( 13 )	0.0071	0.0184	0.0272	0.0128	0.0156	0.0094	0.0297	0.0453	0.0196	0.0246	0.0149	0.0461	0.0712	0.0307	0.0387
	SASRec ( 20 )	0.0063	0.0240	0.0379	0.0152	0.0197	0.0089	0.0331	0.0525	0.0211	0.0273	0.0128	0.0516	0.0823	0.0323	0.0421
	BERT4Rec ( 37 )	0.0045	0.0157	0.0264	0.0100	0.0134	0.0065	0.0255	0.0412	0.0160	0.0211	0.0082	0.0315	0.0530	0.0199	0.0267
	FMLP-Rec ( 54 )	0.0046	0.0181	0.0300	0.0113	0.0151	0.0086	0.0299	0.0496	0.0193	0.0257	0.0099	0.0395	0.0649	0.0246	0.0328
	LRURec ( 50 )	0.0049	0.0169	0.0267	0.0110	0.0141	0.0071	0.0272	0.0431	0.0172	0.0223	0.0134	0.0480	0.0753	0.0308	0.0396

Table 2. Performance comparison on three Amazon datasets. R@

K

and N@

K

denote Recall@

K

and NDCG@

K

, respectively. The best results are highlighted in bold , and the second-best results are underlined . The improvements of our model over the best baseline are statistically significant (paired t-test,

p<0.05

Dataset	Model	NDCG@5	NDCG@10	Recall@5	Recall@10
MovieLens	PreferGrow ( 18 )	0.0910	0.1177	0.1409	0.2237
	RPG ( 17 )	0.1197	0.1440	0.1750	0.2503
	DiffGRM ( 28 )	0.1038	0.1260	0.1541	0.2235
	LLaDA-Rec ( 35 )	0.1359	0.1628	0.1980	0.2820
	ANR-DiffRec	0.1468	0.1738	0.2141	0.2977
Steam	PreferGrow ( 18 )	0.0406	0.0508	0.0615	0.0935

Table 3. Performance comparison on MovieLens and Steam. The best results are highlighted in bold , and the second-best results are underlined . The improvements of our model over the best baseline are statistically significant (paired t-test,

p<0.05

Figure 3. Performance comparison across different user interaction sequence length groups on the Scientific and Instrument dataset.

Figure 4. Performance comparison across Head, Mid, and Tail item groups on the Scientific and Instrument dataset.

Dataset	Method	NDCG@1	NDCG@5	NDCG@10	Recall@5	Recall@10
Scientific	RQ-VAE	0.0120	0.0221	0.0269	0.0320	0.0487
	w/o II	0.0109	0.0217	0.0268	0.0314	0.0479
	w/o Schedule	0.0099	0.0205	0.0259	0.0312	0.0477
	w/o Schedule and II	0.0097	0.0203	0.0253	0.0310	0.0474
	Full	0.0122	0.0226	0.0279	0.0327	0.0494
Instrument	RQ-VAE	0.0128	0.0270	0.0341	0.0408	0.0626

Table 4. Ablation study results on three Amazon datasets. “II” denotes item co-occurrence information, and “Schedule” denotes the diffusion adaptive noise rescheduling strategy.

Figure 5. Ablation study on different noise rescheduling strategies.

Figure 6. Ablation study on different forms of collaborative signal construction.

Figure 7. Hyper-parameter study with different dimensionalities for collaborative embedding.

Figure 8. Hyper-parameter study of the sharpness in the geometric distribution.

Stage	Method	Time/Epoch (s)	Total (h)	Cost
Item Tokenization	RQ-VAE	0.648	1.799	1.000 $\times$
Item Tokenization	Ours	–	0.106	0.059 $\times$
Generative Training	LLaDA-Rec	87.402	3.641	1.000 $\times$
Generative Training	ANR-DiffRec	88.351	3.681	1.011 $\times$

Table 5. Training efficiency comparison in Scientific.

Method	Metric	Beam=1	Beam=10	Beam=20	Beam=30	Beam=40	Beam=50
LLaDA-Rec	Total Time (s)	0m 13s	1m 46s	3m 22s	5m 04s	6m 46s	8m 33s
LLaDA-Rec	Time / User (ms)	0.25	2.08	3.96	5.96	7.96	10.06
ANR-DiffRec	Total Time (s)	0m 13s	1m 46s	3m 24s	5m 06s	6m 50s	8m 39s
ANR-DiffRec	Time / User (ms)	0.25	2.08	4.00	6.00	8.04	10.18

Table 6. Inference efficiency comparison with different beam sizes in Scientific.

Item	Metric Space	Co-occur Hits@20			Co-occurring Neighbors (Post-integration)
Item	Metric Space	Pre	Post	Gain ( $\uparrow$ )	Co-occurring Neighbors (Post-integration)
Item #710	Embedding	3	5	+2	{757, 732, 9894, 750, 1104 }
Item #710	SIDs	1	8	+7	{ 732, 719, 750, 1104, 755, 758, 751 , 757}
Item #6278	Embedding	5	9	+4	{9430, 3671, 23939, 2229, 3021, 17400, 24692, 21922 , 17350}
Item #6278	SIDs	4	12	+8	{3671, 3717 , 879 , 2371, 2250, 2230, 1613, 2268, 1169 , 998, 2229, 1774 }
Item #219	Embedding	4	8	+4	{975, 971 , 20665, 977 , 214, 13070, 9644, 6499 }

Table 7. Case study on three sampled items. We compare the number of ground-truth co-occurring items found within the Top-20 nearest neighbors in both the embedding space and the SID space. “Pre” and “Post” denote before and after integrating the item co-occurrence features.

Generative Recommendation

Generative recommendation models user histories and item catalogs to generate personalized items, lists, or queries rather than only scoring candidates.

See all 106 papers

Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation
Jun 1, 2026Bangguo Zhu, Peng Huo, Yuanbo Zhao +3Sequential Recommendation Recommender Systems
Central South University Changsha, China · National Super Computing Center Tianjin, China · Renmin University of China Beijing, China +1
DiffCold: A Diffusion-based Generative Model for Cold-Start Item Recommendation
Jun 10, 2026Kangning Zhang, Yingjie Qin, Weinan Zhang +2Cold-Start Recommendation Recommender Systems
Shanghai Jiao Tong University, Shanghai, China · Xiaohongshu Inc., Shanghai, China
RaDAR: Relation-aware Diffusion-Asymmetric Graph Contrastive Learning for Recommendation
Mar 17, 2026Yixuan Huang, Jiawei Chen, Shengfan Zhang +1Graph Contrastive Learning Collaborative Filtering
National University of Defense Technology, Changsha, China · Ant Group, Chongqing, China · Tsinghua University, Beijing, China

Jun 1, 2026J/K move · Enter open · S save

Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation

Bangguo Zhu, Peng Huo, Yuanbo Zhao, Zhicheng Du+2

Central South University Changsha, China · National Super Computing Center Tianjin, China · Renmin University of China Beijing, China+1

Sequential Recommendation Recommender Systems User Preference Modeling Generative Recommendation

Open paper AskPDF arXiv

Recently, Generative Recommenders (GRs) have emerged as a transformative recommendation paradigm by replacing traditional item IDs with semantic indices (SIDs). Owing to the exceptional generative capabilities of diffusion models, a few pioneering works explore developing GRs with diffusion architectures as the backbone. However, a fatal limitation of existing diffusion-based GRs is that the diffusion process applies uniformly to all items within the historical interactions. In contrast, the user preference is shaped by multifaceted time-evolving factors and thus exhibits a non-stationary distribution in the temporal aspect. To bridge this gap, this study proposes a novel GR framework, named TDPM, by designing the time-aware diffusion on SID tokens. Specifically, TDPM explicitly integrates the impact of time-evolving user preferences into the diffusion process. In detail, the user preference is disentangled into (i) the period preference, which remains consistent over a long time-span, and (ii) the point preference, which is triggered by recent focal events. Extensive experiments on three public real-world datasets demonstrate the significant superiority of TDPM over the state-of-the-art baselines. TDPM achieves average improvements of up to 29.21% and 25.45% in terms of HR@20 and NDCG@20, respectively. The ablation study further underscores the necessity of time-aware token diffusion in diffusion-based GRs.

Abstract

Generative Recommendation

Explore similar work

Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation

DiffCold: A Diffusion-based Generative Model for Cold-Start Item Recommendation

RaDAR: Relation-aware Diffusion-Asymmetric Graph Contrastive Learning for Recommendation