Collaborative Metric Learning with Memory Network for Multi-Relational Recommender Systems

Danyang Liu; Jianxun Lian; Xiao Zhou; Xing Xie

arxiv: 1906.09882 · v1 · pith:F2KETPBGnew · submitted 2019-06-24 · 💻 cs.LG · cs.IR· stat.ML

Collaborative Metric Learning with Memory Network for Multi-Relational Recommender Systems

Xiao Zhou , Danyang Liu , Jianxun Lian , Xing Xie This is my paper

Pith reviewed 2026-05-25 17:18 UTC · model grok-4.3

classification 💻 cs.LG cs.IRstat.ML

keywords multi-relational recommender systemscollaborative metric learningmemory networkuser feedback typespersonalized recommendationsmetric spaceneural models

0 comments

The pith

The Multi-Relational Memory Network improves recommendations by modeling multiple user feedback types together in metric space.

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

Most recommender systems rely on a single interaction type such as purchases, yet users leave many signals including browsing and sharing that reflect different preference strengths. The paper argues these signals form a spectrum of preferences that can be jointly learned through relational metric learning. It introduces the Multi-Relational Memory Network (MRMN) to capture fine-grained user-item relations while distinguishing feedback by strength and diversity. Experiments across e-commerce, local services, and job recommendation tasks show gains over competitive baselines that use only one feedback type. If correct, platforms could extract more value from the varied interaction logs they already collect.

Core claim

Based on the observation that the underlying spectrum of user preferences is reflected in various types of interactions with items and can be uncovered by latent relational learning in metric space, we propose a unified neural learning framework, named Multi-Relational Memory Network (MRMN). It can not only model fine-grained user-item relations but also enable us to discriminate between feedback types in terms of the strength and diversity of user preferences. Extensive experiments show that the proposed MRMN model outperforms competitive state-of-the-art algorithms in a wide range of scenarios, including e-commerce, local services, and job recommendations.

What carries the argument

Multi-Relational Memory Network (MRMN), a memory-network architecture for collaborative metric learning that jointly embeds multiple user-item relation types.

If this is right

Recommender systems gain accuracy by using all available interaction types rather than one.
Feedback types can be automatically ranked by inferred preference strength and diversity.
The same framework produces gains in e-commerce, local services, and job recommendation domains.
Latent relational learning in metric space extracts finer preference distinctions than single-relation models.

Where Pith is reading between the lines

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

The memory component may allow easier inspection of which interaction types drive each recommendation.
The approach could be tested on platforms with even richer logs such as video or music streaming.
If the relational embeddings prove stable across domains, they might serve as transferable user representations for cold-start scenarios.

Load-bearing premise

The spectrum of user preferences is reflected in various types of interactions with items and can be uncovered by latent relational learning in metric space.

What would settle it

Re-running the reported experiments on the same datasets and finding that MRMN shows no consistent improvement over single-feedback metric-learning baselines.

Figures

Figures reproduced from arXiv: 1906.09882 by Danyang Liu, Jianxun Lian, Xiao Zhou, Xing Xie.

**Figure 2.** Figure 2: The architecture of MRMN. 4.2 User and Item Embedding For a training set consisting of triplets (user, item, τ ), the identities of a user and an item, represented as two binary sparse vectors via one-hot encoding, are employed as input features initially. Then the two vectors are projected to lowdimensional dense vectors to generate a pair of user and item embeddings, denoted as (u, i). After that, Hadam… view at source ↗

**Figure 3.** Figure 3: Performance of MRMN and selected baselines w.r.t. the number of iterations on Tmall and Xing. [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗

**Figure 4.** Figure 4: Attention weights over memory slices for feedback types. [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗

read the original abstract

The success of recommender systems in modern online platforms is inseparable from the accurate capture of users' personal tastes. In everyday life, large amounts of user feedback data are created along with user-item online interactions in a variety of ways, such as browsing, purchasing, and sharing. These multiple types of user feedback provide us with tremendous opportunities to detect individuals' fine-grained preferences. Different from most existing recommender systems that rely on a single type of feedback, we advocate incorporating multiple types of user-item interactions for better recommendations. Based on the observation that the underlying spectrum of user preferences is reflected in various types of interactions with items and can be uncovered by latent relational learning in metric space, we propose a unified neural learning framework, named Multi-Relational Memory Network (MRMN). It can not only model fine-grained user-item relations but also enable us to discriminate between feedback types in terms of the strength and diversity of user preferences. Extensive experiments show that the proposed MRMN model outperforms competitive state-of-the-art algorithms in a wide range of scenarios, including e-commerce, local services, and job recommendations.

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.

Desk Editor's Note private letter to a colleague

MRMN combines memory networks with metric learning for multi-relational feedback in recommenders, but the abstract supplies zero experimental details to support its outperformance claims.

read the letter

The paper's key contribution is MRMN, a neural framework that uses memory networks within a collaborative metric learning setup to handle multi-relational user feedback in recommenders. It aims to model fine-grained relations from different interaction types and distinguish their preference strengths. This approach has some merit in recognizing the value of diverse feedback data, which most single-relation models ignore. The memory network allows for better handling of the variety in user preferences across feedback types, which is a practical concern for real platforms. The novelty lies in the specific integration for multi-relational data, as the abstract positions it as a unified framework not matching prior single-feedback methods. On the downside, the abstract asserts outperformance over competitive algorithms in e-commerce, local services, and job recommendations without any supporting numbers, metrics, or experimental setup details. This leaves the central empirical claim ungrounded and hard to evaluate. The assumption that the preference spectrum can be uncovered by latent relational learning in metric space is a standard modeling choice and doesn't show obvious internal problems, but it requires the experiments to back it up. The paper targets the recommender systems community, especially those dealing with implicit multi-behavior data. Readers who work on improving recommendation accuracy using multiple signals could find it relevant if the full experiments are robust. Given that, I think it deserves a serious referee to examine the methods and results in detail.

Referee Report

1 major / 0 minor

Summary. The paper proposes the Multi-Relational Memory Network (MRMN), a unified neural framework for multi-relational recommender systems. It models multiple types of user-item interactions (browsing, purchasing, sharing) to uncover fine-grained preferences via latent relational learning in metric space, claiming that MRMN outperforms competitive state-of-the-art algorithms across e-commerce, local services, and job recommendation scenarios.

Significance. If the empirical outperformance is substantiated, the work would contribute a memory-network-based approach to handling diverse feedback types in metric space, extending beyond single-relation recommenders and potentially improving personalization in multi-relational settings.

major comments (1)

[Abstract] Abstract: the central claim that 'the proposed MRMN model outperforms competitive state-of-the-art algorithms in a wide range of scenarios' supplies no quantitative results, baselines, metrics, dataset sizes, or ablation details, rendering it impossible to assess whether the data support the claim.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback. We address the single major comment below and will revise the manuscript accordingly.

read point-by-point responses

Referee: [Abstract] Abstract: the central claim that 'the proposed MRMN model outperforms competitive state-of-the-art algorithms in a wide range of scenarios' supplies no quantitative results, baselines, metrics, dataset sizes, or ablation details, rendering it impossible to assess whether the data support the claim.

Authors: We agree that the abstract, as a high-level summary, does not include quantitative details and that adding such information would make the central claim easier to evaluate at a glance. In the revised version we will update the abstract to incorporate key quantitative highlights drawn from the experimental results (e.g., relative improvements on the primary metrics across the reported datasets and scenarios). All supporting details—baselines, metrics, dataset sizes, and ablation studies—already appear in Sections 4 and 5; the abstract revision will simply surface the most salient numbers without altering the technical content. revision: yes

Circularity Check

0 steps flagged

No derivation chain or equations present to analyze for circularity

full rationale

The provided abstract and context contain no equations, loss functions, derivation steps, or mathematical claims. The paper's central assertion is an empirical statement of outperformance on recommendation tasks, which rests on experimental results rather than any internal derivation that could reduce to its own inputs by construction. No self-citations, ansatzes, or fitted predictions are visible in the text supplied. This is the expected honest non-finding when no load-bearing derivation exists.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no explicit free parameters, axioms, or invented entities are stated or derivable from the given text.

pith-pipeline@v0.9.0 · 5730 in / 1017 out tokens · 29075 ms · 2026-05-25T17:18:22.639235+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

scoring function s(u,i,τ) = ||u + r_τ - i||₂² ... pairwise ranking loss L = Σ_τ Σ ... φ(s(u,i,τ) + λ_τ - s(u,j,τ))
IndisputableMonolith/Foundation/RealityFromDistinction.lean reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

memory matrix M ∈ R^{N×d} ... attention ω_τ_i = v^T k_τ_i ... r_τ = Σ ω_τ_i m_i

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

24 extracted references · 24 canonical work pages · 2 internal anchors

[1]

Translating embeddings for modeling multi-relational data

Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. Translating embeddings for modeling multi-relational data. In Advances in neural information processing systems , pages 2787--2795, 2013

work page 2013
[2]

Sequential recommendation with user memory networks

Xu Chen, Hongteng Xu, Yongfeng Zhang, Jiaxi Tang, Yixin Cao, Zheng Qin, and Hongyuan Zha. Sequential recommendation with user memory networks. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining , pages 108--116. ACM, 2018

work page 2018
[3]

An improved sampler for bayesian personalized ranking by leveraging view data

Jingtao Ding, Fuli Feng, Xiangnan He, Guanghui Yu, Yong Li, and Depeng Jin. An improved sampler for bayesian personalized ranking by leveraging view data. In Companion of the The Web Conference 2018 on The Web Conference 2018 , pages 13--14. International World Wide Web Conferences Steering Committee, 2018

work page 2018
[4]

Improving implicit recommender systems with view data

Jingtao Ding, Guanghui Yu, Xiangnan He, Yuhan Quan, Yong Li, Tat-Seng Chua, Depeng Jin, and Jiajie Yu. Improving implicit recommender systems with view data. In IJCAI , pages 3343--3349, 2018

work page 2018
[5]

Collaborative Memory Network for Recommendation Systems

Travis Ebesu, Bin Shen, and Yi Fang. Collaborative memory network for recommendation systems. arXiv preprint arXiv:1804.10862 , 2018

work page internal anchor Pith review Pith/arXiv arXiv 2018
[6]

Collaborative filtering recommender systems

Michael D Ekstrand, John T Riedl, Joseph A Konstan, et al. Collaborative filtering recommender systems. Foundations and Trends in Human--Computer Interaction , 4(2):81--173, 2011

work page 2011
[7]

Vbpr: Visual bayesian personalized ranking from implicit feedback

Ruining He and Julian McAuley. Vbpr: Visual bayesian personalized ranking from implicit feedback. In AAAI , pages 144--150, 2016

work page 2016
[8]

Collaborative metric learning

Cheng-Kang Hsieh, Longqi Yang, Yin Cui, Tsung-Yi Lin, Serge Belongie, and Deborah Estrin. Collaborative metric learning. In Proceedings of the 26th International Conference on World Wide Web , pages 193--201. International World Wide Web Conferences Steering Committee, 2017

work page 2017
[9]

Collaborative filtering for implicit feedback datasets

Yifan Hu, Yehuda Koren, and Chris Volinsky. Collaborative filtering for implicit feedback datasets. In Data Mining, 2008. ICDM'08. Eighth IEEE International Conference on , pages 263--272. Ieee, 2008

work page 2008
[10]

Mention recommendation for twitter with end-to-end memory network

Haoran Huang, Qi Zhang, Xuanjing Huang, et al. Mention recommendation for twitter with end-to-end memory network. In Proc. IJCAI , volume 17, pages 1872--1878, 2017

work page 2017
[11]

Factorization meets the neighborhood: a multifaceted collaborative filtering model

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

work page 2008
[12]

Learning from history and present: next-item recommendation via discriminatively exploiting user behaviors

Zhi Li, Hongke Zhao, Qi Liu, Zhenya Huang, Tao Mei, and Enhong Chen. Learning from history and present: next-item recommendation via discriminatively exploiting user behaviors. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , pages 1734--1743. ACM, 2018

work page 2018
[13]

xdeepfm: Combining explicit and implicit feature interactions for recommender systems

Jianxun Lian, Xiaohuan Zhou, Fuzheng Zhang, Zhongxia Chen, Xing Xie, and Guangzhong Sun. xdeepfm: Combining explicit and implicit feature interactions for recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , pages 1754--1763. ACM, 2018

work page 2018
[14]

Personalized ranking recommendation via integrating multiple feedbacks

Jian Liu, Chuan Shi, Binbin Hu, Shenghua Liu, and S Yu Philip. Personalized ranking recommendation via integrating multiple feedbacks. In Pacific-Asia Conference on Knowledge Discovery and Data Mining , pages 131--143. Springer, 2017

work page 2017
[15]

Bayesian personalized ranking with multi-channel user feedback

Babak Loni, Roberto Pagano, Martha Larson, and Alan Hanjalic. Bayesian personalized ranking with multi-channel user feedback. In Proceedings of the 10th ACM Conference on Recommender Systems , pages 361--364. ACM, 2016

work page 2016
[16]

Transfer learning in collaborative filtering for sparsity reduction

Weike Pan, Evan Wei Xiang, Nathan Nan Liu, and Qiang Yang. Transfer learning in collaborative filtering for sparsity reduction. In AAAI , volume 10, pages 230--235, 2010

work page 2010
[17]

Content-based recommendation systems

Michael J Pazzani and Daniel Billsus. Content-based recommendation systems. In The adaptive web , pages 325--341. Springer, 2007

work page 2007
[18]

Bpr: Bayesian personalized ranking from implicit feedback

Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. Bpr: Bayesian personalized ranking from implicit feedback. In Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence . AUAI Press, 2009

work page 2009
[19]

Singh and Geoffrey J

Ajit P. Singh and Geoffrey J. Gordon. Relational learning via collective matrix factorization. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , pages 650--658. ACM, 2008

work page 2008
[20]

An empirical study on recommendation with multiple types of feedback

Liang Tang, Bo Long, Bee-Chung Chen, and Deepak Agarwal. An empirical study on recommendation with multiple types of feedback. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , pages 283--292. ACM, 2016

work page 2016
[21]

Latent relational metric learning via memory-based attention for collaborative ranking

Yi Tay, Luu Anh Tuan, and Siu Cheung Hui. Latent relational metric learning via memory-based attention for collaborative ranking. In Proceedings of the 2018 World Wide Web Conference on World Wide Web , pages 729--739. International World Wide Web Conferences Steering Committee, 2018

work page 2018
[22]

Memory networks

Jason Weston, Sumit Chopra, and Antoine Bordesm. Memory networks. In ICLR , 2015

work page 2015
[23]

Topic-Enhanced Memory Networks for Personalised Point-of-Interest Recommendation

Xiao Zhou, Cecilia Mascolo, and Zhongxiang Zhao. Topic-enhanced memory networks for personalised point-of-interest recommendation. arXiv preprint arXiv:1905.13127 , 2019

work page internal anchor Pith review Pith/arXiv arXiv 1905
[24]

write newline

" write newline "" before.all 'output.state := FUNCTION fin.entry add.period write newline FUNCTION new.block output.state before.all = 'skip after.block 'output.state := if FUNCTION new.sentence output.state after.block = 'skip output.state before.all = 'skip after.sentence 'output.state := if if FUNCTION not #0 #1 if FUNCTION and 'skip pop #0 if FUNCTIO...

work page

[1] [1]

Translating embeddings for modeling multi-relational data

Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. Translating embeddings for modeling multi-relational data. In Advances in neural information processing systems , pages 2787--2795, 2013

work page 2013

[2] [2]

Sequential recommendation with user memory networks

Xu Chen, Hongteng Xu, Yongfeng Zhang, Jiaxi Tang, Yixin Cao, Zheng Qin, and Hongyuan Zha. Sequential recommendation with user memory networks. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining , pages 108--116. ACM, 2018

work page 2018

[3] [3]

An improved sampler for bayesian personalized ranking by leveraging view data

Jingtao Ding, Fuli Feng, Xiangnan He, Guanghui Yu, Yong Li, and Depeng Jin. An improved sampler for bayesian personalized ranking by leveraging view data. In Companion of the The Web Conference 2018 on The Web Conference 2018 , pages 13--14. International World Wide Web Conferences Steering Committee, 2018

work page 2018

[4] [4]

Improving implicit recommender systems with view data

Jingtao Ding, Guanghui Yu, Xiangnan He, Yuhan Quan, Yong Li, Tat-Seng Chua, Depeng Jin, and Jiajie Yu. Improving implicit recommender systems with view data. In IJCAI , pages 3343--3349, 2018

work page 2018

[5] [5]

Collaborative Memory Network for Recommendation Systems

Travis Ebesu, Bin Shen, and Yi Fang. Collaborative memory network for recommendation systems. arXiv preprint arXiv:1804.10862 , 2018

work page internal anchor Pith review Pith/arXiv arXiv 2018

[6] [6]

Collaborative filtering recommender systems

Michael D Ekstrand, John T Riedl, Joseph A Konstan, et al. Collaborative filtering recommender systems. Foundations and Trends in Human--Computer Interaction , 4(2):81--173, 2011

work page 2011

[7] [7]

Vbpr: Visual bayesian personalized ranking from implicit feedback

Ruining He and Julian McAuley. Vbpr: Visual bayesian personalized ranking from implicit feedback. In AAAI , pages 144--150, 2016

work page 2016

[8] [8]

Collaborative metric learning

Cheng-Kang Hsieh, Longqi Yang, Yin Cui, Tsung-Yi Lin, Serge Belongie, and Deborah Estrin. Collaborative metric learning. In Proceedings of the 26th International Conference on World Wide Web , pages 193--201. International World Wide Web Conferences Steering Committee, 2017

work page 2017

[9] [9]

Collaborative filtering for implicit feedback datasets

Yifan Hu, Yehuda Koren, and Chris Volinsky. Collaborative filtering for implicit feedback datasets. In Data Mining, 2008. ICDM'08. Eighth IEEE International Conference on , pages 263--272. Ieee, 2008

work page 2008

[10] [10]

Mention recommendation for twitter with end-to-end memory network

Haoran Huang, Qi Zhang, Xuanjing Huang, et al. Mention recommendation for twitter with end-to-end memory network. In Proc. IJCAI , volume 17, pages 1872--1878, 2017

work page 2017

[11] [11]

Factorization meets the neighborhood: a multifaceted collaborative filtering model

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

work page 2008

[12] [12]

Learning from history and present: next-item recommendation via discriminatively exploiting user behaviors

Zhi Li, Hongke Zhao, Qi Liu, Zhenya Huang, Tao Mei, and Enhong Chen. Learning from history and present: next-item recommendation via discriminatively exploiting user behaviors. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , pages 1734--1743. ACM, 2018

work page 2018

[13] [13]

xdeepfm: Combining explicit and implicit feature interactions for recommender systems

Jianxun Lian, Xiaohuan Zhou, Fuzheng Zhang, Zhongxia Chen, Xing Xie, and Guangzhong Sun. xdeepfm: Combining explicit and implicit feature interactions for recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , pages 1754--1763. ACM, 2018

work page 2018

[14] [14]

Personalized ranking recommendation via integrating multiple feedbacks

Jian Liu, Chuan Shi, Binbin Hu, Shenghua Liu, and S Yu Philip. Personalized ranking recommendation via integrating multiple feedbacks. In Pacific-Asia Conference on Knowledge Discovery and Data Mining , pages 131--143. Springer, 2017

work page 2017

[15] [15]

Bayesian personalized ranking with multi-channel user feedback

Babak Loni, Roberto Pagano, Martha Larson, and Alan Hanjalic. Bayesian personalized ranking with multi-channel user feedback. In Proceedings of the 10th ACM Conference on Recommender Systems , pages 361--364. ACM, 2016

work page 2016

[16] [16]

Transfer learning in collaborative filtering for sparsity reduction

Weike Pan, Evan Wei Xiang, Nathan Nan Liu, and Qiang Yang. Transfer learning in collaborative filtering for sparsity reduction. In AAAI , volume 10, pages 230--235, 2010

work page 2010

[17] [17]

Content-based recommendation systems

Michael J Pazzani and Daniel Billsus. Content-based recommendation systems. In The adaptive web , pages 325--341. Springer, 2007

work page 2007

[18] [18]

Bpr: Bayesian personalized ranking from implicit feedback

Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. Bpr: Bayesian personalized ranking from implicit feedback. In Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence . AUAI Press, 2009

work page 2009

[19] [19]

Singh and Geoffrey J

Ajit P. Singh and Geoffrey J. Gordon. Relational learning via collective matrix factorization. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , pages 650--658. ACM, 2008

work page 2008

[20] [20]

An empirical study on recommendation with multiple types of feedback

Liang Tang, Bo Long, Bee-Chung Chen, and Deepak Agarwal. An empirical study on recommendation with multiple types of feedback. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , pages 283--292. ACM, 2016

work page 2016

[21] [21]

Latent relational metric learning via memory-based attention for collaborative ranking

Yi Tay, Luu Anh Tuan, and Siu Cheung Hui. Latent relational metric learning via memory-based attention for collaborative ranking. In Proceedings of the 2018 World Wide Web Conference on World Wide Web , pages 729--739. International World Wide Web Conferences Steering Committee, 2018

work page 2018

[22] [22]

Memory networks

Jason Weston, Sumit Chopra, and Antoine Bordesm. Memory networks. In ICLR , 2015

work page 2015

[23] [23]

Topic-Enhanced Memory Networks for Personalised Point-of-Interest Recommendation

Xiao Zhou, Cecilia Mascolo, and Zhongxiang Zhao. Topic-enhanced memory networks for personalised point-of-interest recommendation. arXiv preprint arXiv:1905.13127 , 2019

work page internal anchor Pith review Pith/arXiv arXiv 1905

[24] [24]

write newline

" write newline "" before.all 'output.state := FUNCTION fin.entry add.period write newline FUNCTION new.block output.state before.all = 'skip after.block 'output.state := if FUNCTION new.sentence output.state after.block = 'skip output.state before.all = 'skip after.sentence 'output.state := if if FUNCTION not #0 #1 if FUNCTION and 'skip pop #0 if FUNCTIO...

work page