pith. sign in

arxiv: 1907.06853 · v1 · pith:63IDTRHCnew · submitted 2019-07-16 · 💻 cs.IR · cs.SI

Deep Social Collaborative Filtering

Wenqi Fan , Yao Ma , Dawei Yin , Jianping Wang , Jiliang Tang , Qing Li This is my paper

Pith reviewed 2026-05-24 20:55 UTC · model grok-4.3

classification 💻 cs.IR cs.SI
keywords recommender systemscollaborative filteringsocial networksdeep learningsocial recommendationsuser-item interactionshomophilyinfluence
0
0 comments X

The pith

DSCF framework uses deep networks to capture distant social neighbors and item-specific opinions for recommendations.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Recommender systems often incorporate social network data alongside user-item interactions to predict preferences. Existing deep models for social recommendations are limited because they only consider direct neighbors, apply the same weight to all neighbor data, and fail to model explicit opinions about particular items. The paper proposes DSCF to overcome these by exploiting social relations in multiple aspects via deep neural networks. This would matter because it promises more accurate recommendations by using a fuller picture of social influence. Experiments on two real-world datasets confirm that the framework outperforms previous methods.

Core claim

To address the challenges of only using direct neighbors, treating neighbor information equally, and not capturing neighbors' opinions explicitly, the paper proposes DSCF, a Deep Social Collaborative Filtering framework, which can exploit the social relations with various aspects for recommender systems.

What carries the argument

DSCF, a deep neural network framework that integrates social relations from various aspects including distant neighbors and item-specific opinions.

If this is right

  • Distant neighbors in social networks provide helpful information for recommendations.
  • Item-specific information from neighbors improves the relevance of recommendations.
  • Explicitly capturing neighbors' opinions to items affects user preferences differently.
  • The framework shows effectiveness through experiments on two real-world datasets.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Extending the model to dynamic social networks where relations change over time could be a natural next step.
  • The idea of multi-aspect social exploitation might apply to other graph-structured data in machine learning.
  • Investigating which aspects contribute most could lead to more efficient variants of the model.

Load-bearing premise

The additional social information from distant neighbors and item-specific opinions improves recommendation performance beyond models that only use direct neighbors.

What would settle it

If experiments show that DSCF does not outperform baselines that only use direct neighbors on the two real-world datasets, the claim of effectiveness would be disproven.

Figures

Figures reproduced from arXiv: 1907.06853 by Dawei Yin, Jianping Wang, Jiliang Tang, Qing Li, Wenqi Fan, Yao Ma.

Figure 1
Figure 1. Figure 1: An overview of the proposed framework. Before introducing the details of each layer, we first introduce definitions and notations that are used through the paper. Let U = {u1,u2, ...,uN } and V = {v1,v2, ...,vM } denote the sets of users and items respectively, where N is the number of users, and M is the number of items. Let R ∈ R N ×M be the rating matrix (or the user-item interaction matrix), where the … view at source ↗
Figure 2
Figure 2. Figure 2: An illustration example of generating item-aware [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Component Analysis on Ciao dataset. DSCF-* [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Effect of Bi-LSTM model on Ciao dataset. [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Performances w.r.t. the length of sequence. [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Performance w.r.t the number of sequences. [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
read the original abstract

Recommender systems are crucial to alleviate the information overload problem in online worlds. Most of the modern recommender systems capture users' preference towards items via their interactions based on collaborative filtering techniques. In addition to the user-item interactions, social networks can also provide useful information to understand users' preference as suggested by the social theories such as homophily and influence. Recently, deep neural networks have been utilized for social recommendations, which facilitate both the user-item interactions and the social network information. However, most of these models cannot take full advantage of the social network information. They only use information from direct neighbors, but distant neighbors can also provide helpful information. Meanwhile, most of these models treat neighbors' information equally without considering the specific recommendations. However, for a specific recommendation case, the information relevant to the specific item would be helpful. Besides, most of these models do not explicitly capture the neighbor's opinions to items for social recommendations, while different opinions could affect the user differently. In this paper, to address the aforementioned challenges, we propose DSCF, a Deep Social Collaborative Filtering framework, which can exploit the social relations with various aspects for recommender systems. Comprehensive experiments on two-real world datasets show the effectiveness of the proposed framework.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 2 minor

Summary. The manuscript proposes DSCF, a deep neural network framework for social collaborative filtering that addresses three stated limitations of prior models: restriction to direct neighbors (instead incorporating distant neighbors), uniform neighbor weighting (instead using item-specific relevance), and absence of explicit neighbor opinion modeling. The central claim is that these mechanisms together yield improved recommendation performance, supported by experiments on two real-world datasets.

Significance. If the empirical results hold under proper controls, the work would offer a concrete advance in social recommender systems by operationalizing homophily and influence theories through multiple social aspects within a single deep architecture. The explicit separation of opinion modeling from neighbor aggregation is a useful modeling distinction that prior graph-based social recommenders often conflate.

minor comments (2)
  1. Abstract, line 8: 'two-real world datasets' contains a hyphenation error and should read 'two real-world datasets'.
  2. The abstract provides no quantitative results, baseline names, or dataset identifiers. While the full manuscript presumably supplies these in the experimental section, the abstract should at minimum name the datasets and report the primary metric improvement to allow readers to assess the strength of the effectiveness claim.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the careful reading and positive assessment of our manuscript on DSCF. We are pleased that the contribution is viewed as a concrete advance in social recommender systems and that the modeling distinction between opinion modeling and neighbor aggregation is recognized as useful. We are happy to prepare a revised version incorporating any minor points.

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper proposes the DSCF framework to address limitations in prior social recommenders (direct-neighbor restriction, uniform weighting, missing opinion modeling) and supports its claims solely via empirical experiments on two real-world datasets. No equations, derivations, or first-principles predictions appear in the provided text; the central effectiveness claim is presented as an empirical outcome rather than reducing to any fitted parameter, self-definition, or self-citation chain by construction. The model architecture and social theories (homophily, influence) function as independent design choices tested externally, with no load-bearing step that collapses to its own inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The framework rests on standard assumptions of neural network training and social homophily theory; no free parameters, axioms, or invented entities are specified in the abstract.

axioms (1)
  • domain assumption Social theories such as homophily and influence provide useful signals for user preferences
    Invoked in the second sentence of the abstract to justify using social networks.

pith-pipeline@v0.9.0 · 5751 in / 1181 out tokens · 26335 ms · 2026-05-24T20:55:02.685957+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

50 extracted references · 50 canonical work pages · 1 internal anchor

  1. [1]

    Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate.In International Conference on Learning Representations (ICLR)

    work page 2015

  2. [2]

    Ting Bai, Ji-Rong Wen, Jun Zhang, and Wayne Xin Zhao. 2017. A neural collaborative filtering model with interaction-based neighborhood. InProceedings of the 2017 ACM on Conference on Information and Knowledge Management . ACM, 1979–1982

    work page 2017

  3. [3]

    Eytan Bakshy, Itamar Rosenn, Cameron Marlow, and Lada Adamic. 2012. The role of social networks in information diffusion. In World Wide Web conference. 519–528

    work page 2012

  4. [4]

    Rianne van den Berg, Thomas N Kipf, and Max Welling. 2017. Graph convolutional matrix completion. arXiv preprint arXiv:1706.02263 (2017)

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  5. [5]

    Chong Chen, Min Zhang, Yiqun Liu, and Shaoping Ma. 2018. Neural attentional rating regression with review-level explanations. In Proceedings of the 2018 World Wide Web Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 1583–1592

    work page 2018

  6. [6]

    Shuiguang Deng, Longtao Huang, Guandong Xu, Xindong Wu, and Zhaohui Wu

    work page

  7. [7]

    IEEE transactions on neural networks and learning systems 28, 5 (2017), 1164–1177

    On deep learning for trust-aware recommendations in social networks. IEEE transactions on neural networks and learning systems 28, 5 (2017), 1164–1177

    work page 2017

  8. [8]

    Jimmy Ba Diederik P. Kingma. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR)

    work page 2015

  9. [9]

    Wenqi Fan, Tyler Derr, Yao Ma, Jianping Wang, Jiliang Tang, and Qing Li. 2019. Deep Adversarial Social Recommendation. InProceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI-19

    work page 2019

  10. [10]

    Wenqi Fan, Qing Li, and Min Cheng. 2018. Deep Modeling of Social Relations for Recommendation. In AAAI

    work page 2018

  11. [11]

    Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, and Dawei Yin

    work page

  12. [12]

    In The World Wide Web Conference

    Graph Neural Networks for Social Recommendation. In The World Wide Web Conference. ACM, 417–426

    work page

  13. [13]

    David Goldberg, David Nichols, Brian M Oki, and Douglas Terry. 1992. Using collaborative filtering to weave an information tapestry. Commun. ACM 35, 12 (1992), 61–70

    work page 1992

  14. [14]

    Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining . ACM, 855–864

    work page 2016

  15. [15]

    Guibing Guo, Jie Zhang, and Neil Yorke-Smith. 2015. TrustSVD: collaborative filtering with both the explicit and implicit influence of user trust and of item ratings. In Twenty-Ninth AAAI Conference on Artificial Intelligence

    work page 2015

  16. [16]

    Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural collaborative filtering. In Proceedings of the 26th International Conference on World Wide Web . International World Wide Web Conferences Steering Committee, 173–182

    work page 2017

  17. [17]

    Geoffrey Hinton, Li Deng, Dong Yu, George E Dahl, Abdel-rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara N Sainath, et al . 2012. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal processing magazine 29, 6 (2012), 82–97

    work page 2012

  18. [18]

    Mohsen Jamali and Martin Ester. 2010. A matrix factorization technique with trust propagation for recommendation in social networks. In Proceedings of the fourth ACM conference on Recommender systems . ACM, 135–142

    work page 2010

  19. [19]

    Nal Kalchbrenner, Edward Grefenstette, and Phil Blunsom. 2014. A convolutional neural network for modelling sentences. InProceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

    work page 2014

  20. [20]

    Donghyun Kim, Chanyoung Park, Jinoh Oh, Sungyoung Lee, and Hwanjo Yu. 2016. Convolutional matrix factorization for document context-aware recommendation. In Proceedings of the 10th ACM Conference on Recommender Systems. ACM, 233–240

    work page 2016

  21. [21]

    Yehuda Koren. 2008. Factorization meets the neighborhood: a multifaceted collaborative filtering model. InProceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining . ACM, 426–434

    work page 2008

  22. [22]

    László Lovász et al. [n. d.]. Random walks on graphs: A survey. ([n. d.])

    work page

  23. [23]

    Hao Ma, Haixuan Yang, Michael R Lyu, and Irwin King. 2008. Sorec: social recommendation using probabilistic matrix factorization. In Proceedings of the 17th ACM conference on Information and Knowledge Management. ACM, 931–940

    work page 2008

  24. [24]

    Hao Ma, Dengyong Zhou, Chao Liu, Michael R Lyu, and Irwin King. 2011. Recommender systems with social regularization. In Proceedings of the fourth ACM international conference on Web Search and Data Mining . ACM, 287–296

    work page 2011

  25. [25]

    Daniel J O’keefe. 2002. Persuasion: Theory and research . Vol. 2. Sage

    work page 2002

  26. [26]

    Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining . ACM, 701–710

    work page 2014

  27. [27]

    Sanjay Purushotham, Yan Liu, and C-C Jay Kuo. 2012. Collaborative topic regression with social matrix factorization for recommendation systems. In Proceedings of the 24th International Conference on Machine Learning

    work page 2012

  28. [28]

    Ruslan Salakhutdinov and Andriy Mnih. 2007. Probabilistic Matrix Factorization. In 21th Conference on Neural Information Processing Systems , Vol. 1. 2–1

    work page 2007

  29. [29]

    Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl. 2001. Item- based collaborative filtering recommendation algorithms. In World Wide Web Conference. ACM, 285–295

    work page 2001

  30. [30]

    Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research 15, 1 (2014), 1929–1958

    work page 2014

  31. [31]

    Peijie Sun, Le Wu, and Meng Wang. 2018. Attentive Recurrent Social Recommendation. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval . ACM, 185–194

    work page 2018

  32. [32]

    Bosiljka Tadić. 2003. Exploring complex graphs by random walks. In AIP Conference Proceedings, Vol. 661. AIP, 24–27

    work page 2003

  33. [33]

    Jiliang Tang, Xia Hu, Huiji Gao, and Huan Liu. 2013. Exploiting local and global social context for recommendation.. In IJCAI, Vol. 13. 2712–2718

    work page 2013

  34. [34]

    Jiliang Tang, Xia Hu, and Huan Liu. 2013. Social recommendation: a review. Social Network Analysis and Mining 3, 4 (2013), 1113–1133

    work page 2013

  35. [35]

    Jiliang Tang, Suhang Wang, Xia Hu, Dawei Yin, Yingzhou Bi, Yi Chang, and Huan Liu. 2016. Recommendation with Social Dimensions. In AAAI. 251–257

    work page 2016

  36. [36]

    Aaron Van den Oord, Sander Dieleman, and Benjamin Schrauwen. 2013. Deep content-based music recommendation. In Advances in neural information processing systems. 2643–2651

    work page 2013

  37. [37]

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems . 5998–6008

    work page 2017

  38. [38]

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30 . 5998–6008

    work page 2017

  39. [39]

    Hao Wang, Naiyan Wang, and Dit-Yan Yeung. 2015. Collaborative deep learning for recommender systems. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . ACM, 1235–1244

    work page 2015

  40. [40]

    Jun Wang, Lantao Yu, Weinan Zhang, Yu Gong, Yinghui Xu, Benyou Wang, Peng Zhang, and Dell Zhang. 2017. Irgan: A minimax game for unifying generative and discriminative information retrieval models. In Proceedings of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval. ACM, 515–524

    work page 2017

  41. [41]

    Naiyan Wang and Dit-Yan Yeung. 2013. Learning a deep compact image representation for visual tracking. In Advances in neural information processing systems. 809–817

    work page 2013

  42. [42]

    Xiang Wang, Xiangnan He, Liqiang Nie, and Tat-Seng Chua. 2017. Item silk road: Recommending items from information domains to social users. In Proceedings of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval. ACM, 185–194

    work page 2017

  43. [43]

    Xin Wang, Wei Lu, Martin Ester, Can Wang, and Chun Chen. 2016. Social Recommendation with Strong and Weak Ties. In Proceedings of the 25th ACM International on Conference on Information and Knowledge Management . ACM, 5–14

    work page 2016

  44. [44]

    Xinxi Wang and Ye Wang. 2014. Improving content-based and hybrid music recommendation using deep learning. In Proceedings of the 22nd ACM International Conference on Multimedia . ACM, 627–636

    work page 2014

  45. [45]

    Bo Yang, Yu Lei, Jiming Liu, and Wenjie Li. 2017. Social collaborative filtering by trust. IEEE transactions on pattern analysis and machine intelligence 39, 8 (2017), 1633–1647

    work page 2017

  46. [46]

    Zichao Yang, Diyi Yang, Chris Dyer, Xiaodong He, Alex Smola, and Eduard Hovy. 2016. Hierarchical attention networks for document classification. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies . 1480–1489

    work page 2016

  47. [47]

    Lili Zhao, Zhongqi Lu, Sinno Jialin Pan, and Qiang Yang. 2016. Matrix Factorization+ for Movie Recommendation. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence . 3945–3951

    work page 2016

  48. [48]

    Tong Zhao, Julian McAuley, and Irwin King. 2014. Leveraging social connections to improve personalized ranking for collaborative filtering. In Proceedings of the 23rd ACM international conference on conference on information and knowledge management. ACM, 261–270

    work page 2014

  49. [49]

    Yu Zhu, Hao Li, Yikang Liao, Beidou Wang, Ziyu Guan, Haifeng Liu, and Deng Cai

    work page

  50. [50]

    In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17

    What to do next: Modeling user behaviors by time-lstm. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17 . 3602–3608

    work page