PAD-MPFN: Dynamic Fusion with Popularity Decay for News Recommendation
Abstract
1. Introduction
- We introduce a novel fusion framework that jointly models user interests, social influences, and temporal popularity patterns through adaptive subspace projection. This integrated approach achieves notable improvements in both recommendation accuracy and content diversity, effectively capturing the complex interplay between personal preferences and collective behaviors compared to existing methods.
- We develop a logarithmic time-decay mechanism that dynamically adjusts the recommendation weights between trending and long-tail content. This innovation significantly reduces popularity bias while maintaining recommendation relevance, addressing a critical limitation in current news recommendation systems.
- Comprehensive experiments conducted on the MIND benchmark dataset [17] demonstrate the superior performance of our model, particularly in cold-start scenarios. The results consistently show advantages over state-of-the-art baselines in both standard and cold-start evaluation settings. (The implementation code is publicly available at https://github.com/1dwy1/PAD-MPFN, accessed on 30 July 2025.)
2. Related Work
2.1. Sequence-Based News Recommendation
2.2. Graph-Based News Recommendation
2.3. Popularity-Based News Recommendation
2.4. Summary and Research Gap
3. Problem Formulation for News Recommendation
4. Popularity-Aware Dynamic Multi-Perspective Fusion Network
4.1. News Encoder (NE)
4.2. Multi-Perspective User Interest Dynamic Modeling
4.2.1. User Long-Term Interest Encoder (ULIE)
4.2.2. Graph-Based User Potential Interest Encoder (GUPIE)
4.2.3. Synergistic Attention Interest Integration (SAII)
4.2.4. Neighbor-Based User Potential Interest Encoder (NUPIE)
4.3. Popularity-Normalized and Temporal-Aware User Interest Encoder (PNTUIE)
4.4. Dynamic Fusion with Multi-Perspective News Recommendation (DFMPNR)
5. Model Training of PAD-MPFN
Algorithm 1 PAD-MPFN training procedure |
Input: Training set ; hyperparameters E, k, and K; and batch size m Output: Learned model parameters
|
Computational Complexity Analysis
6. Experimental Setup
6.1. Dataset Description
- MIND-Large: It contains complete user interaction logs from Microsoft’s news platform, recording both impression events (shown news with click/non-click status) and historical click behaviors. The data spans six weeks (12 October to 22 November 2019) and includes two primary components: (1) news content (headlines and abstracts) and (2) user interaction records.
- MIND-Small: A stratified sample of MIND-Large containing behaviors from 50,000 randomly selected users, maintaining the original data distribution.
6.2. Experiment Settings
6.3. Baselines
- Sequence-based method:
- 1.
- LSTUR [1] constructs a dynamic user interest representation by capturing changes in short-term user interest through a GRU network and utilizing an embedding vector of user IDs to represent the user’s long-term interest.
- 2.
- NAML [19] captures multifaceted features of news and user sequential interests through multi-view learning and attention mechanisms.
- 3.
- HieRec [6] captures diverse and multi-granular user sequential interests using hierarchical interest trees.
- 4.
- MCCM [4] utilizes a hierarchical interest tree to capture diverse and multi-granular user sequence interests.
- Graph Structure-based method:
- 5.
- KIM [3] models user news interactions using knowledge graphs with common encoders and user interest representations.
- 6.
- DIGAT [2] captures effective feature interactions between the news graph and the user graph through interactive attention mechanisms.
- 7.
- GLORY [24] combines a global click graph with a gated graph neural network to enhance global news representation.
- 8.
- FNRKPL [8] combines knowledge graphs for news recommendation.
- Popularity-based method:
- 9.
- KRED [26] enhances the representation of news documents by utilizing knowledge graphs and employing a multi-task learning framework to encode tasks such as popularity as additional information into the recommendation model.
- 10.
- PENR [27] calculates the number of clicks on each news article as heat and adds popularity as an auxiliary task.
7. Results
7.1. Overall Performance
7.2. Ablation Study
- Full Model: Complete PAD-MPFN implementation;
- w/o NUPIE: Remove neighbor interest aggregation (disable Algorithm 1 @ line 12);
- w/o PNTUIE: Exclude popularity encoding (disable Algorithm 1 @ line 13);
- w/o GUPIE: Use only sequential interests (disable Algorithm 1 @ line 10);
- w/o DFMPNR: Remove dynamic fusion and use only the news encoder for modeling user interests (use only Algorithm 1 @ line 8, disable Algorithm 1 @ line 14, and retain Equation (21)).
7.3. Hyperparameter Analysis
- For sparse histories (0–10 clicks), neighbor count shows minimal impact (0.12% variation), indicating fundamental cold-start challenges.
- Medium-history users (11–30 clicks) benefit most from neighbor integration (0.64% improvement at ).
- Dense histories (>30 clicks) maintain stable performance with but degrade sharply with excessive neighbors.
7.4. Cold-Start Problem
7.5. Saturation Effect Problem
7.6. Case Study
8. Conclusions and Future Work
- Information diffusion modeling: The current framework could be enhanced by incorporating news propagation patterns in social networks and event evolution trajectories, particularly for breaking news scenarios.
- Dynamic model adaptation: Our experiments on static datasets reveal opportunities for developing online learning versions that can adapt to real-time news cycles and shifting user interests.
- Multimodal extension: Future work will investigate incorporating visual and audio features from news videos and images to create richer content representations, potentially improving recommendation quality for multimedia news platforms.
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- An, M.; Wu, F.; Wu, C.; Zhang, K.; Liu, Z.; Xie, X. Neural news recommendation with long-and short-term user representations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 28 July–2 August 2019; pp. 336–345. [Google Scholar]
- Mao, Z.; Li, J.; Wang, H.; Zeng, X.; Wong, K.F. DIGAT: Modeling News Recommendation with Dual-Graph Interaction. In Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, 7–11 December 2022; pp. 6595–6607. [Google Scholar]
- Qi, T.; Wu, F.; Wu, C.; Huang, Y. Personalized news recommendation with knowledge-aware interactive matching. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, 11–15 July 2021; pp. 61–70. [Google Scholar]
- Wang, J.; Jiang, Y.; Li, H.; Zhao, W. Improving news recommendation with channel-wise dynamic representations and contrastive user modeling. In Proceedings of the sixteenth ACM International Conference on Web Search and Data Mining, Singapore, 27 February–3 March 2023; pp. 562–570. [Google Scholar]
- Wang, S.; Guo, S.; Wang, L.; Liu, T.; Xu, H. HDNR: A hyperbolic-based debiased approach for personalized news recommendation. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, Taipei, China, 23–27 July 2023; pp. 259–268. [Google Scholar]
- Qi, T.; Wu, F.; Wu, C.; Yang, P.; Yu, Y.; Xie, X.; Huang, Y. HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Virtual Event, 1–6 August 2021; pp. 5446–5456. [Google Scholar]
- Yang, Z.; Wang, W.; Qi, T.; Zhang, P.; Zhang, T.; Zhang, R.; Liu, J.; Huang, Y. GLoCIM: Global-view Long Chain Interest Modeling for news recommendation. In Proceedings of the 31st International Conference on Computational Linguistics (COLING 2025), Abu Dhabi, United Arab Emirates, 19–24 January 2025; Rambow, O., Wanner, L., Apidianaki, M., Al-Khalifa, H., Eugenio, B.D., Schockaert, S., Eds.; Association for Computational Linguistics: Abu Dhabi, United Arab Emirates, 2025; pp. 6855–6865. [Google Scholar]
- Sun, S.; Pan, X.; Qi, S.; Gao, J. Knowledge Enhanced Prompt Learning Framework for Financial News Recommendation. Pattern Recognit. 2025, 163, 111461. [Google Scholar] [CrossRef]
- Wu, C.; Wu, F.; Ge, S.; Qi, T.; Huang, Y.; Xie, X. Neural news recommendation with multi-head self-attention. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, 3–7 November 2019; pp. 6389–6394. [Google Scholar]
- Zhu, Q.; Zhou, X.; Song, Z.; Tan, J.; Guo, L. Dan: Deep attention neural network for news recommendation. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, Honolulu, HI, USA, 27 January–1 February 2019; pp. 5973–5980. [Google Scholar]
- Zhao, Q.; Chen, X.; Zhang, H.; Li, X. Dynamic Hierarchical Attention Network for news recommendation. Expert Syst. Appl. 2024, 255, 124667. [Google Scholar] [CrossRef]
- Qi, T.; Wu, F.; Wu, C.; Huang, Y. PP-Rec: News Recommendation with Personalized User Interest and Time-aware News Popularity. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Online, 1–6 August 2021; pp. 5457–5467. [Google Scholar]
- Hosseini, D.; Sood, K.; Bacha, V. News popularity prediction with machine learning. In Proceedings of the 2022 IEEE 4th International Conference on Cybernetics, Cognition and Machine Learning Applications (ICCCMLA), Goa, India, 8–9 October 2022; pp. 474–480. [Google Scholar]
- Panda, D.K.; Ray, S. Approaches and algorithms to mitigate cold start problems in recommender systems: A systematic literature review. J. Intell. Inf. Syst. 2022, 59, 341–366. [Google Scholar] [CrossRef]
- Haim, M.; Graefe, A.; Brosius, H.B. Burst of the filter bubble? Effects of personalization on the diversity of Google News. Digit. J. 2018, 6, 330–343. [Google Scholar]
- Song, G.; Wang, Y.; Li, J.; Hu, H. Predicting the Popularity of Online News Based on the Dynamic Fusion of Multiple Features. Comput. Mater. Contin. 2023, 76, 1621–1641. [Google Scholar] [CrossRef]
- Wu, F.; Qiao, Y.; Chen, J.H.; Wu, C.; Qi, T.; Lian, J.; Liu, D.; Xie, X.; Gao, J.; Wu, W.; et al. Mind: A large-scale dataset for news recommendation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online, 5–10 July 2020; pp. 3597–3606. [Google Scholar]
- Cho, K.; van Merriënboer, B.; Gulcehre, C.; Bahdanau, D.; Bougares, F.; Schwenk, H.; Bengio, Y. Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, 25–29 October 2014; pp. 1724–1734. [Google Scholar]
- Wu, C.; Wu, F.; An, M.; Huang, J.; Huang, Y.; Xie, X. Neural news recommendation with attentive multi-view learning. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China, 10–16 August 2019; pp. 3863–3869. [Google Scholar]
- Gu, J.; Wang, Z.; Kuen, J.; Ma, L.; Shahroudy, A.; Shuai, B.; Liu, T.; Wang, X.; Wang, G.; Cai, J.; et al. Recent advances in convolutional neural networks. Pattern Recognit. 2018, 77, 354–377. [Google Scholar] [CrossRef]
- Yuan, Y.; Zhou, Y.; Chen, X.; Xiong, Q.; Okere, H.C. Enhancing Recommendation Diversity and Novelty with Bi-LSTM and Mean Shift Clustering. Electronics 2024, 13, 3841. [Google Scholar] [CrossRef]
- Zhang, S.; Zheng, D.; Hu, X.; Yang, M. Bidirectional long short-term memory networks for relation classification. In Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation, Shanghai, China, 30 October–1 November 2015; pp. 73–78. [Google Scholar]
- Jiang, S.; Song, H.; Lu, Y.; Zhang, Z. News Recommendation Method Based on Candidate-Aware Long- and Short-Term Preference Modeling. Appl. Sci. 2025, 15, 300. [Google Scholar] [CrossRef]
- Yang, B.; Liu, D.; Suzumura, T.; Dong, R.; Li, I. Going Beyond Local: Global Graph-Enhanced Personalized News Recommendations. In Proceedings of the RecSys’23: 17th ACM Conference on Recommender Systems, Singapore, 18–22 September 2023; pp. 24–34. [Google Scholar]
- Li, H.; Wang, Y.; Xiao, Z.; Yang, J.; Zhou, C.; Zhang, M.; Ju, W. DisCo: Graph-based disentangled contrastive learning for cold-start cross-domain recommendation. In Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA, 25 February–4 March 2025; Number 11. pp. 12049–12057. [Google Scholar]
- Liu, D.; Lian, J.; Wang, S.; Qiao, Y.; Chen, J.H.; Sun, G.; Xie, X. KRED: Knowledge-aware document representation for news recommendations. In Proceedings of the 14th ACM Conference on Recommender Systems, Virtual Event, 22–26 September 2020; pp. 200–209. [Google Scholar]
- Wang, J.; Chen, Y.; Wang, Z.; Zhao, W. Popularity-enhanced news recommendation with multi-view interest representation. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, Virtual Event, 1–5 November 2021; pp. 1949–1958. [Google Scholar]
- Wu, Y.; Wen, Z.; Liang, S. Predicting Question Popularity for Community Question Answering. Electronics 2024, 13, 3260. [Google Scholar] [CrossRef]
- Ding, Y.; Wang, B.; Cui, X.; Xu, M. Popularity prediction with semantic retrieval for news recommendation. Expert Syst. Appl. 2024, 247, 123308. [Google Scholar] [CrossRef]
- Pennington, J.; Socher, R.; Manning, C.D. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, 25–29 October 2014; pp. 1532–1543. [Google Scholar]
- Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, Ł.; Polosukhin, I. Attention is all you need. Adv. Neural Inf. Process. Syst. 2017, 30, 6000–6010. [Google Scholar]
- Li, Y.; Zemel, R.; Brockschmidt, M.; Tarlow, D. Gated Graph Sequence Neural Networks. In Proceedings of the 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, 2–4 May 2016; pp. 1–20. [Google Scholar]
- Graves, A.; Schmidhuber, J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Adv. Neural Inf. Process. Syst. 2005, 18, 601–610. [Google Scholar] [CrossRef] [PubMed]
- Clauset, A.; Shalizi, C.R.; Newman, M.E. Power-law distributions in empirical data. SIAM Rev. 2009, 51, 661–703. [Google Scholar] [CrossRef]
- Cohen Tenoudji, F. First and Second Order Systems. In Analog and Digital Signal Analysis: From Basics to Applications; Springer International Publishing: Berlin/Heidelberg, Germany, 2016; pp. 11–34. [Google Scholar]
- Wu, C.; Wu, F.; Huang, Y.; Xie, X. Neural news recommendation with negative feedback. CCF Trans. Pervasive Comput. Interact. 2020, 2, 178–188. [Google Scholar] [CrossRef]
- Hochreiter, S.; Schmidhuber, J. Long short-term memory. Neural Comput. 1997, 9, 1735–1780. [Google Scholar] [CrossRef] [PubMed]
- Bottou, L.; Curtis, F.E.; Nocedal, J. Optimization Methods for Large-Scale Machine Learning. SIAM Rev. 2018, 60, 223–311. [Google Scholar] [CrossRef]
- Kingma, D.P.; Ba, J. Adam: A Method for Stochastic Optimization. In Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015; pp. 1–15. [Google Scholar]
- Kaminskas, M.; Bridge, D. Diversity, serendipity, novelty, and coverage: A survey and empirical analysis of beyond-accuracy objectives in recommender systems. ACM Trans. Interact. Intell. Syst. (TiiS) 2016, 7, 1–42. [Google Scholar] [CrossRef]
- Liu, S.; Zheng, Y. Long-tail session-based recommendation. In Proceedings of the 14th ACM Conference on Recommender Systems, Virtual Event, 22–26 September 2020; pp. 509–514. [Google Scholar]
Symbol | Description | Symbol | Description |
---|---|---|---|
n | news articles | the embedding of user graph interest | |
c | candidate news articles | user representation embedding | |
w | a word | neighboring representation embedding | |
k | the number of most similar neighbor interests | popularity representation embedding | |
K | the number of negative samples | word embedding matrix | |
the number of clicks per news article | news embedding matrix of the user | ||
the time saturation factor | trainable parameter matrix | ||
news popularity | the set of news articles | ||
personal interest | the set of candidate news articles | ||
social influence | the associated word sequence in the article | ||
popularity trends | a user subgraph | ||
the final recommendation score | the set of user embeddings | ||
attention weights between words | the tanh activation function | ||
the user history news sequential attention weight | the exponential function | ||
the user history news node attention weight | the softmax activation function | ||
a learned weight that determines the contribution of , , and | calculate the cosine similarity vector between and | ||
a learned weight that determines the contribution of and | logarithm with base e | ||
an embedding that refers to a word | the concatenation of and | ||
a word embedding with contextual relationships | vector norm | ||
a query vector | initial word embeddings [30] | ||
the embedding of news | coded word embedding [31] | ||
the updated news node embedding | generates sequence interest representations [10] | ||
the hidden state | generates graph interest representations [32] | ||
the embedding of user sequence interest |
Dataset | News | Users | Clicks | Impressions |
---|---|---|---|---|
MIND-large | 1,000,000 | 161,013 | 24,155,470 | 15,777,377 |
MIND-small | 50,000 | 65,238 | 347,727 | 230,117 |
Method | MIND-Small | MIND-Large | ||||||
---|---|---|---|---|---|---|---|---|
AUC | MRR | nDCG@5 | nDCG@10 | AUC | MRR | nDCG@5 | nDCG@10 | |
LSTUR | 65.87 | 30.78 | 35.15 | 40.15 | 67.08 | 32.36 | 35.15 | 40.93 |
NAML | 66.12 | 31.53 | 34.88 | 41.09 | 66.46 | 32.75 | 35.66 | 41.40 |
HieRec | 67.95 | 32.87 | 36.36 | 42.53 | 69.03 | 33.89 | 37.08 | 43.01 |
MCCM | 67.95 | 32.76 | 36.62 | 42.66 | 69.45 | 34.41 | 37.62 | 43.31 |
KIM | 67.07 | 31.83 | 35.23 | 41.58 | 68.45 | 33.74 | 36.76 | 42.47 |
DIGAT | 67.82 | 32.65 | 36.25 | 42.49 | - | - | - | - |
GLORY ⋆ | 67.68 | 32.45 | 35.78 | 42.10 | 69.04 | 33.83 | 37.53 | 43.69 |
FNRKPL ⋆ | 67.81 | 32.46 | 35.95 | 42.86 | - | - | - | - |
KRED | 65.89 | 30.80 | 33.78 | 40.23 | 68.52 | 33.78 | 36.76 | 42.45 |
PENR ⋆ | 67.16 | 31.75 | 34.36 | 40.82 | 69.25 | 34.16 | 37.31 | 43.04 |
PAD-MPFN | 68.03 | 32.90 | 36.67 | 42.77 | 69.40 | 34.37 | 37.66 | 43.79 |
Group | Count |
---|---|
0–10 | 24,802 |
11–20 | 11,498 |
21–30 | 5372 |
31–40 | 2895 |
41–50 | 5433 |
Method | ILMD@5 | Tail-Coverage@5 | ILMD@10 | Tail-Coverage@10 |
---|---|---|---|---|
PENR | 20.73% | 12.13% | 15.70% | 26.81% |
PAD-MPFN | 21.36% | 18.10% | 17.68% | 32.25% |
User Historical Clicked News | |||
---|---|---|---|
News ID | Title | ||
N45729 | Former Deadliest Catch Star Jerod Sechrist Arrested, Charged with Heroin Possession | 2214 | 8 |
N44007 | Where have Cape Town’s great whites gone? | 779 | 6 |
N306 | Kevin Spacey Won’t Be Charged in Sexual Assault Case After Accuser Dies | 9733 | 9 |
N47953 | Mom who popularized gender reveals it now | 410 | 6 |
N13138 | Amelia Bambridge: Body of missing backpacker found in sea | 3726 | 8 |
N48697 | The ice used to protect them. Now their island is crumbling into the sea. | 721 | 7 |
N38961 | Penn State launches new investigation into Sandusky sexual abuse allegation | 338 | 6 |
N36530 | Property Brothers’ J.D. Scott Marries Annalee Belle in Vintage Theatre-Themed Wedding | 3329 | 8 |
N15288 | Ex-manager sues Starbucks for firing after arrest of 2 black men | 475 | 6 |
N8148 | Holocaust survivor under guard amid death threats | 3756 | 8 |
Candidate News | |||
---|---|---|---|
News ID | Title | Whether to Click ? | Rank |
N20036 | 30 Best Black Friday Deals from Costco | △ | 9 |
N60939 | Russia lands forces at former U.S. air base in northern Syria | △ | 7 |
N30290 | The Real Reason McDonald’s Keeps the Filet-O-Fish on Their Menu | ◯ | 4 |
N32536 | High tides surge through Venice, locals rush to protect art | △ | 8 |
N31958 | Opinion: Colin Kaepernick is about to get what he deserves: a chance | △ | 3 |
N5940 | Meghan Markle and Hillary Clinton Secretly Spent the Afternoon Together at Frogmore Cottage | △ | 6 |
N17807 | The Coolest Car Lamborghini Never Made Is Up For Sale | △ | 10 |
N46917 | Judge agrees Alabama Islamic State recruit is not US citizen | △ | 5 |
N42767 | FDA issues warning to Dollar Tree about selling ’potentially unsafe drugs’ | ◯ | 2 |
N36779 | South Carolina teen gets life in prison for deadly elementary school shooting | △ | 1 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ma, B.; Deng, Y.; Gao, H. PAD-MPFN: Dynamic Fusion with Popularity Decay for News Recommendation. Electronics 2025, 14, 3057. https://doi.org/10.3390/electronics14153057
Ma B, Deng Y, Gao H. PAD-MPFN: Dynamic Fusion with Popularity Decay for News Recommendation. Electronics. 2025; 14(15):3057. https://doi.org/10.3390/electronics14153057
Chicago/Turabian StyleMa, Biyang, Yiwei Deng, and Huifan Gao. 2025. "PAD-MPFN: Dynamic Fusion with Popularity Decay for News Recommendation" Electronics 14, no. 15: 3057. https://doi.org/10.3390/electronics14153057
APA StyleMa, B., Deng, Y., & Gao, H. (2025). PAD-MPFN: Dynamic Fusion with Popularity Decay for News Recommendation. Electronics, 14(15), 3057. https://doi.org/10.3390/electronics14153057