pith. sign in

arxiv: 2508.13663 · v5 · pith:5ZJDXDQPnew · submitted 2025-08-19 · 💻 cs.AI · cs.LG

Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints

Daniel Daza , Alberto Bernardi , Luca Costabello , Christophe Gueret , Masoud Mansoury , Michael Cochez , Martijn Schut This is my paper

Pith reviewed 2026-05-25 08:26 UTC · model grok-4.3

classification 💻 cs.AI cs.LG
keywords knowledge graphsquery answeringsoft constraintsentity constraintsinteractive queriesneural network adjustment
0
0 comments X

The pith

Two lightweight methods allow knowledge graph queries to incorporate soft constraints by adjusting answer scores.

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

The paper formalizes query answering on knowledge graphs with soft constraints, which capture vague or context-dependent preferences not expressible in first-order logic. It presents two methods that adjust scores from existing query answering systems: one using two tunable parameters and another using a small neural network. These adjustments incorporate the soft constraints while preserving the original ranking structure of answers. The methods are evaluated on extended versions of existing benchmarks that include generated soft constraints. Results indicate that the approaches capture the intended constraints with minimal impact on performance and low computational overhead, enabling interactive preference specification via examples.

Core claim

Query answering with soft entity constraints is achieved through efficient score adjustment methods that integrate user preferences without altering the answers produced by standard query systems on incomplete knowledge graphs.

What carries the argument

Score adjustment via two parameters or a small neural network trained to capture soft constraints.

If this is right

  • Real-world queries with vague preferences can be handled in knowledge graph databases.
  • Users can interactively specify preferences by providing examples.
  • Existing query answering systems can be extended with minimal changes.
  • Performance remains robust with very little added overhead.

Where Pith is reading between the lines

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

  • Similar score adjustment techniques might extend to other types of graph-based reasoning tasks.
  • The generated datasets with soft constraints could serve as a starting point for developing more realistic evaluation benchmarks.
  • Interactive querying could change how non-expert users interact with large knowledge graphs.
  • If the neural network method generalizes well, it might reduce the need for manual parameter tuning in similar applications.

Load-bearing premise

That soft constraints can be incorporated by adjusting scores from an existing query system without disrupting the original answers to the query.

What would settle it

A test where the adjusted ranking significantly changes the top answers from the original query or fails to prefer entities that match the provided soft constraint examples on held-out data.

Figures

Figures reproduced from arXiv: 2508.13663 by Alberto Bernardi, Christophe Gueret, Daniel Daza, Luca Costabello, Martijn Schut, Masoud Mansoury, Michael Cochez.

Figure 1
Figure 1. Figure 1: A query over a KG can be written in a logical form that specifies [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Example illustrating the architecture of NQR, consisting of two modules: preference [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Example dendro￾gram used to generate pref￾erence sets. Highlighted in green are preferred enti￾ties, other entities are non￾preferred. Prior work on query answering on KGs has relied on datasets con￾taining query-answer pairs (q, A), where q is a query and A ⊂ V is the set of answers computed over a KG. We extend these by deriving preference data from observable clusters of entities in the set A. This proc… view at source ↗
Figure 4
Figure 4. Figure 4: Results on interactive query answering with soft preferences, on FB15k237 ( 4a) and [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Tradeoff between pairwise accuracy and MRR, across the baselines (shown in cross [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Types of complex queries used in our experiments. [PITH_FULL_IMAGE:figures/full_fig_p015_6.png] view at source ↗
read the original abstract

Methods for query answering over incomplete knowledge graphs retrieve entities that are likely to be answers, which is particularly useful when such answers cannot be reached by direct graph traversal due to missing edges. However, existing approaches have focused on queries formalized using first-order-logic. In practice, many real-world queries involve constraints that are inherently vague or context-dependent, such as preferences for attributes or related categories. Addressing this gap, we introduce the problem of query answering with soft constraints. We formalize the problem and introduce two efficient methods designed to adjust query answer scores by incorporating soft constraints without disrupting the original answers to a query. These methods are lightweight, requiring tuning only two parameters or a small neural network trained to capture soft constraints while maintaining the original ranking structure. To evaluate the task, we extend existing QA benchmarks by generating datasets with soft constraints. Our experiments demonstrate that our methods can capture soft constraints while maintaining robust query answering performance and adding very little overhead. With our work, we explore a new and flexible way to interact with graph databases that allows users to specify their preferences by providing examples interactively.

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

3 major / 1 minor

Summary. The paper introduces the problem of query answering over incomplete knowledge graphs with soft (vague or context-dependent) entity constraints, formalizes the task, and proposes two lightweight methods to adjust scores from existing QA systems: one using two tunable parameters and one using a small neural network. Both are designed to incorporate soft constraints while preserving the original ranking structure and without disrupting answers to the base query. The authors extend existing QA benchmarks by synthetically generating datasets with soft constraints, and report experiments showing that the methods capture the constraints while maintaining robust performance and adding very little overhead. The work positions this as enabling interactive preference specification via user-provided examples.

Significance. If the central claim holds beyond the synthetic setting, the contribution would be a practical extension of KG query answering that handles real-world vague preferences without requiring full retraining or heavy computation. The emphasis on lightweight adjustment (two parameters or small NN) and preservation of existing QA rankings is a strength for deployability. However, the significance is tempered by the reliance on synthetically generated soft constraints whose construction details are not provided in the abstract and whose independence from the adjustment mechanisms is not demonstrated.

major comments (3)
  1. [Abstract] Abstract: The central claim that the methods 'maintain robust query answering performance and add very little overhead' is stated without any experimental numbers, formal definitions of the adjustment functions, or derivation showing how the two-parameter or NN adjustment preserves the original ranking structure. This makes the claim impossible to assess from the provided information.
  2. [Evaluation] Evaluation (synthetic dataset construction): The soft constraints are generated by extending existing QA benchmarks, but the generation procedure is not described. If the synthetic soft scores are defined additively or linearly in the same space used by the score-adjustment methods (as the skeptic concern notes), the reported robustness and low overhead may be an artifact of the data construction rather than evidence that the methods work for independently elicited user preferences that conflict with the KG.
  3. [Methods] Methods section (score adjustment): The claim that the adjustments 'do not disrupt the original answers to a query' is load-bearing for the interactive-use case, yet no formal condition, proof sketch, or counter-example analysis is referenced showing that the two-parameter or NN adjustment leaves the base ranking invariant when soft constraints are in conflict.
minor comments (1)
  1. [Abstract] The abstract mentions 'providing examples interactively' but does not clarify how user examples are turned into the soft-constraint parameters or NN training signal.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the detailed and constructive review. We address each major comment below and commit to revisions that strengthen the presentation of our contributions on query answering with soft entity constraints.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The central claim that the methods 'maintain robust query answering performance and add very little overhead' is stated without any experimental numbers, formal definitions of the adjustment functions, or derivation showing how the two-parameter or NN adjustment preserves the original ranking structure. This makes the claim impossible to assess from the provided information.

    Authors: The abstract is intended as a concise overview; the experimental numbers, formal definitions of the two-parameter and neural adjustment functions, and analysis of ranking preservation appear in Sections 3 and 4 of the manuscript. To improve accessibility, we will revise the abstract to include one or two key quantitative results (e.g., overhead percentages and ranking preservation metrics) while remaining within length limits. revision: yes

  2. Referee: [Evaluation] Evaluation (synthetic dataset construction): The soft constraints are generated by extending existing QA benchmarks, but the generation procedure is not described. If the synthetic soft scores are defined additively or linearly in the same space used by the score-adjustment methods (as the skeptic concern notes), the reported robustness and low overhead may be an artifact of the data construction rather than evidence that the methods work for independently elicited user preferences that conflict with the KG.

    Authors: We agree that the synthetic data generation procedure requires explicit description. In the revision we will add a dedicated subsection detailing the exact procedure used to extend the QA benchmarks with soft constraints, including how soft scores were assigned and any independence checks performed. We will also include an analysis comparing the synthetic scores against the adjustment mechanisms to demonstrate that performance gains are not artifacts of linear dependence. revision: yes

  3. Referee: [Methods] Methods section (score adjustment): The claim that the adjustments 'do not disrupt the original answers to a query' is load-bearing for the interactive-use case, yet no formal condition, proof sketch, or counter-example analysis is referenced showing that the two-parameter or NN adjustment leaves the base ranking invariant when soft constraints are in conflict.

    Authors: The manuscript describes the adjustments as monotonic transformations that preserve relative order when soft constraints are neutral, but we acknowledge the absence of an explicit formal statement or proof sketch. We will add a short lemma in Section 3 establishing the invariance condition under which the base ranking is preserved, together with a brief counter-example analysis for cases of strong conflict. revision: yes

Circularity Check

0 steps flagged

No circularity; methods and evaluation are independent of self-referential reductions

full rationale

The provided abstract and context contain no equations, derivations, or load-bearing self-citations. The two methods (two-parameter adjustment or small NN) are described as lightweight tunings that preserve original rankings, but no specific reduction to fitted inputs or self-definitional steps is quoted or exhibited. Evaluation on synthetically extended benchmarks is an empirical choice, not a derivation that collapses by construction to the inputs. This matches the default expectation of no significant circularity (score 0-2).

Axiom & Free-Parameter Ledger

1 free parameters · 0 axioms · 0 invented entities

The approach rests on the premise that soft constraints are adjustable via lightweight mechanisms without breaking existing query rankings, but no explicit axioms or invented entities are stated.

free parameters (1)
  • two parameters for score adjustment
    The first method requires tuning only two parameters to incorporate soft constraints.

pith-pipeline@v0.9.0 · 5737 in / 1162 out tokens · 32050 ms · 2026-05-25T08:26:43.914437+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

56 extracted references · 56 canonical work pages · 2 internal anchors

  1. [1]

    Knowledge Graphs - Method- ology, Tools and Selected Use Cases

    Dieter Fensel, Umutcan Simsek, Kevin Angele, Elwin Huaman, Elias Kärle, Oleksandra Pana- siuk, Ioan Toma, Jürgen Umbrich, and Alexander Wahler. Knowledge Graphs - Method- ology, Tools and Selected Use Cases . Springer, 2020. ISBN 978-3-030-37438-9. doi: 10.1007/978-3-030-37439-6

    work page doi:10.1007/978-3-030-37439-6 2020

  2. [2]

    Rashid, Anisa Rula, Lukas Schmelzeisen, Juan F

    Aidan Hogan, Eva Blomqvist, Michael Cochez, Claudia d’Amato, Gerard de Melo, Claudio Gutiérrez, Sabrina Kirrane, José Emilio Labra Gayo, Roberto Navigli, Sebastian Neumaier, Axel-Cyrille Ngonga Ngomo, Axel Polleres, Sabbir M. Rashid, Anisa Rula, Lukas Schmelzeisen, Juan F. Sequeda, Steffen Staab, and Antoine Zimmermann. Knowledge Graphs. Number 22 in Synt...

    work page doi:10.2200/s01125ed1v01y202109dsk022 2021

  3. [3]

    Suchanek

    Luis Antonio Galárraga, Christina Teflioudi, Katja Hose, and Fabian M. Suchanek. AMIE: association rule mining under incomplete evidence in ontological knowledge bases. In Daniel Schwabe, Virgílio A. F. Almeida, Hartmut Glaser, Ricardo Baeza-Yates, and Sue B. Moon, editors, 22nd International World Wide Web Conference, WWW ’13, Rio de Janeiro, Brazil, May...

    work page doi:10.1145/2488388.2488425 2013

  4. [4]

    Fine-Grained Evaluation of Rule- and Embedding-Based Systems for Knowl- edge Graph Completion

    Christian Meilicke, Manuel Fink, Yanjie Wang, Daniel Ruffinelli, Rainer Gemulla, and Heiner Stuckenschmidt. Fine-Grained Evaluation of Rule- and Embedding-Based Systems for Knowl- edge Graph Completion. In Denny Vrandecic, Kalina Bontcheva, Mari Carmen Suárez-Figueroa, Valentina Presutti, Irene Celino, Marta Sabou, Lucie-Aimée Kaffee, and Elena Simperl, e...

    work page doi:10.1007/978-3-030-00671-6_1 2018

  5. [5]

    Anytime Bottom-Up Rule Learning for Knowledge Graph Completion

    Christian Meilicke, Melisachew Wudage Chekol, Daniel Ruffinelli, and Heiner Stuckenschmidt. Anytime Bottom-Up Rule Learning for Knowledge Graph Completion. In Sarit Kraus, editor, Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China, August 10-16, 2019 , pages 3137–3143. ijcai.org, 2019. doi:...

    work page doi:10.24963/ijcai.2019/435 2019

  6. [6]

    RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs

    Meng Qu, Junkun Chen, Louis-Pascal Xhonneux, Yoshua Bengio, and Jian Tang. RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs. arXiv, October 2020. URL http://arxiv.org/abs/2010.04029. arXiv: 2010.04029 Publisher: arXiv

    work page arXiv 2020

  7. [7]

    A review of relational machine learning for knowledge graphs

    Maximilian Nickel, Kevin Murphy, V olker Tresp, and Evgeniy Gabrilovich. A review of relational machine learning for knowledge graphs. Proc. IEEE, 104(1):11–33, 2016. doi: 10.1109/JPROC.2015.2483592. URL https://doi.org/10.1109/JPROC.2015.2483592

    work page doi:10.1109/jproc.2015.2483592 2016

  8. [8]

    Shaoxiong Ji, Shirui Pan, Erik Cambria, Pekka Marttinen, and Philip S. Yu. A survey on knowledge graphs: Representation, acquisition, and applications. IEEE Trans. Neural Networks Learn. Syst., 33(2):494–514, 2022. URL https://doi.org/10.1109/TNNLS.2021.3070843

    work page doi:10.1109/tnnls.2021.3070843 2022

  9. [9]

    Hamilton, Payal Bajaj, Marinka Zitnik, Dan Jurafsky, and Jure Leskovec

    William L. Hamilton, Payal Bajaj, Marinka Zitnik, Dan Jurafsky, and Jure Leskovec. Embedding logical queries on knowledge graphs. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS’18, page 2030–2041, Red Hook, NY , USA, 2018. Curran Associates Inc

    work page 2030

  10. [10]

    Message passing query embedding

    Daniel Daza and Michael Cochez. Message passing query embedding. In ICML Workshop - Graph Representation Learning and Beyond, 2020. URL https://arxiv.org/abs/2002. 02406

    work page 2020

  11. [11]

    Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings

    Hongyu Ren, Weihua Hu, and Jure Leskovec. Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings. In 8th International Conference on Learning Repre- sentations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, 2020. URL https://openreview.net/forum?id=BJgr4kSFDS. 10

    work page 2020

  12. [12]

    Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs

    Hongyu Ren and Jure Leskovec. Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs. In Hugo Larochelle, Marc’Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin, editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 202...

    work page 2020

  13. [13]

    Complex query answering with neural link predictors

    Erik Arakelyan, Daniel Daza, Pasquale Minervini, and Michael Cochez. Complex query answering with neural link predictors. In International Conference on Learning Representations,

    work page

  14. [14]

    URL https://openreview.net/forum?id=Mos9F9kDwkz

    work page

  15. [15]

    Adapting neural link predictors for data-efficient complex query answering

    Erik Arakelyan, Pasquale Minervini, Daniel Daza, Michael Cochez, and Isabelle Augenstein. Adapting neural link predictors for data-efficient complex query answering. In Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS ’23, Red Hook, NY , USA, 2023. Curran Associates Inc

    work page 2023

  16. [16]

    Answering complex logical queries on knowl- edge graphs via query computation tree optimization

    Yushi Bai, Xin Lv, Juanzi Li, and Lei Hou. Answering complex logical queries on knowl- edge graphs via query computation tree optimization. In Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett, editors, Interna- tional Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, vo...

    work page 2023

  17. [17]

    Neural-Symbolic Mod- els for Logical Queries on Knowledge Graphs

    Zhaocheng Zhu, Mikhail Galkin, Zuobai Zhang, and Jian Tang. Neural-Symbolic Mod- els for Logical Queries on Knowledge Graphs. In Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvári, Gang Niu, and Sivan Sabato, editors, International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, volume 162 of Proceedings ...

    work page 2022

  18. [18]

    Neural graph reasoning: A survey on complex logical query answering

    Hongyu Ren, Mikhail Galkin, Zhaocheng Zhu, Jure Leskovec, and Michael Cochez. Neural graph reasoning: A survey on complex logical query answering. Transactions on Machine Learning Research, 2024. ISSN 2835-8856. URL https://openreview.net/forum?id= xG8un9ZbqT

    work page 2024

  19. [19]

    A three-way model for collective learning on multi-relational data

    Maximilian Nickel, V olker Tresp, and Hans-Peter Kriegel. A three-way model for collective learning on multi-relational data. In Proceedings of the 28th International Conference on International Conference on Machine Learning, ICML’11, page 809–816, Madison, WI, USA,

    work page

  20. [20]

    ISBN 9781450306195

    Omnipress. ISBN 9781450306195

    work page

  21. [21]

    Translating embeddings for modeling multi-relational data

    Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Ok- sana Yakhnenko. Translating embeddings for modeling multi-relational data. In C.J. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger, editors, Advances in Neural Information Processing Systems , volume 26. Curran Associates, Inc., 2013. URL https://proceedings.neu...

    work page 2013

  22. [22]

    Complex embeddings for simple link prediction

    Théo Trouillon, Johannes Welbl, Sebastian Riedel, Éric Gaussier, and Guillaume Bouchard. Complex embeddings for simple link prediction. In Maria-Florina Balcan and Kilian Q. Weinberger, editors,Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016, volume 48 of JMLR Workshop and Conferenc...

    work page 2016

  23. [23]

    Canonical tensor decomposition for knowledge base completion

    Timothée Lacroix, Nicolas Usunier, and Guillaume Obozinski. Canonical tensor decomposition for knowledge base completion. In Jennifer G. Dy and Andreas Krause, editors, Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, volume 80 of Proceedings of Machine Learning Researc...

    work page 2018

  24. [24]

    Rotate: Knowledge graph em- bedding by relational rotation in complex space

    Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, and Jian Tang. Rotate: Knowledge graph em- bedding by relational rotation in complex space. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net, 2019. URL https://openreview.net/forum?id=HkgEQnRqYQ

    work page 2019

  25. [25]

    UnRavL: A Neuro-Symbolic Framework for Answering Graph Pattern Queries in Knowledge Graphs

    Tamara Cucumides, Daniel Daza, Pablo Barcelo, Michael Cochez, Floris Geerts, Juan L Reutter, and Miguel Romero Orth. UnRavL: A Neuro-Symbolic Framework for Answering Graph Pattern Queries in Knowledge Graphs. In The Third Learning on Graphs Conference, 2024. URL https://openreview.net/forum?id=183XrFqaHN

    work page 2024

  26. [26]

    Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors

    Hang Yin, Zihao Wang, and Yangqiu Song. Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net, 2024. URL https://openreview.net/forum?id=1BmveEMNbG

    work page 2024

  27. [27]

    A survey on instance selection for active learning

    Yifan Fu, Xingquan Zhu, and Bin Li. A survey on instance selection for active learning. Knowl. Inf. Syst. , 35(2):249–283, 2013. doi: 10.1007/S10115-012-0507-8. URL https: //doi.org/10.1007/s10115-012-0507-8

    work page doi:10.1007/s10115-012-0507-8 2013

  28. [28]

    Gupta, Xiaojiang Chen, and Xin Wang

    Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Brij B. Gupta, Xiaojiang Chen, and Xin Wang. A Survey of Deep Active Learning. ACM Comput. Surv., 54(9):180:1– 180:40, 2022. doi: 10.1145/3472291

    work page doi:10.1145/3472291 2022

  29. [29]

    ActiveLink: Deep Active Learning for Link Prediction in Knowledge Graphs

    Natalia Ostapuk, Jie Yang, and Philippe Cudre-Mauroux. ActiveLink: Deep Active Learning for Link Prediction in Knowledge Graphs. In The World Wide Web Conference, WWW ’19, pages 1398–1408, New York, NY , USA, May 2019. Association for Computing Machinery. ISBN 978-1-4503-6674-8. doi: 10.1145/3308558.3313620. URL https://dl.acm.org/doi/ 10.1145/3308558.3313620

    work page doi:10.1145/3308558.3313620 2019

  30. [30]

    Active Ensemble Learning for Knowledge Graph Error Detection

    Junnan Dong, Qinggang Zhang, Xiao Huang, Qiaoyu Tan, Daochen Zha, and Zhao Zihao. Active Ensemble Learning for Knowledge Graph Error Detection. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, WSDM ’23, pages 877–885, New York, NY , USA, February 2023. Association for Computing Machinery. ISBN 978-1-4503-9407-9. ...

    work page doi:10.1145/3539597.3570368 2023

  31. [31]

    Deep Active Alignment of Knowledge Graph Entities and Schemata

    Jiacheng Huang, Zequn Sun, Qijin Chen, Xiaozhou Xu, Weijun Ren, and Wei Hu. Deep Active Alignment of Knowledge Graph Entities and Schemata. Proc. ACM Manag. Data, 1(2): 159:1–159:26, June 2023. doi: 10.1145/3589304. URL https://dl.acm.org/doi/10.1145/ 3589304

    work page doi:10.1145/3589304 2023

  32. [32]

    Introduction to information retrieval, volume 39

    Hinrich Schütze, Christopher D Manning, and Prabhakar Raghavan. Introduction to information retrieval, volume 39. Cambridge University Press Cambridge, 2008

    work page 2008

  33. [33]

    BERT: pre-training of deep bidirectional transformers for language understanding

    Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT: pre-training of deep bidirectional transformers for language understanding. In Jill Burstein, Christy Doran, and Thamar Solorio, editors, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAA...

    work page 2019

  34. [34]

    Christopher J. C. Burges, Tal Shaked, Erin Renshaw, Ari Lazier, Matt Deeds, Nicole Hamilton, and Gregory N. Hullender. Learning to rank using gradient descent. In Luc De Raedt and Stefan Wrobel, editors, Machine Learning, Proceedings of the Twenty-Second International Conference (ICML 2005), Bonn, Germany, August 7-11, 2005, volume 119 ofACM International...

    work page doi:10.1145/1102351.1102363 2005

  35. [35]

    Christopher J. C. Burges, Robert Ragno, and Quoc Viet Le. Learning to Rank with Nonsmooth Cost Functions. In Bernhard Schölkopf, John C. Platt, and Thomas Hofmann, editors, Advances in Neural Information Processing Systems 19, Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, Dece...

    work page 2006

  36. [36]

    Christopher J.C. Burges. From ranknet to lambdarank to lambdamart: An overview. Technical Report MSR-TR-2010-82, Microsoft Research,

    work page 2010

  37. [37]

    URL https://www.microsoft.com/en-us/research/publication/ from-ranknet-to-lambdarank-to-lambdamart-an-overview/

    work page

  38. [38]

    Learning to rank: from pairwise approach to listwise approach

    Zhe Cao, Tao Qin, Tie-Yan Liu, Ming-Feng Tsai, and Hang Li. Learning to rank: from pairwise approach to listwise approach. In Zoubin Ghahramani, editor, Machine Learning, Proceedings of the Twenty-Fourth International Conference (ICML 2007), Corvallis, Oregon, USA, June 20-24, 2007, volume 227 of ACM International Conference Proceeding Series, pages 129–1...

    work page doi:10.1145/1273496.1273513 2007

  39. [39]

    Listwise approach to learning to rank: theory and algorithm

    Fen Xia, Tie-Yan Liu, Jue Wang, Wensheng Zhang, and Hang Li. Listwise approach to learning to rank: theory and algorithm. In William W. Cohen, Andrew McCallum, and Sam T. Roweis, editors, Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), Helsinki, Finland, June 5-9, 2008, volume 307 of ACM International Conference Pro...

    work page doi:10.1145/1390156.1390306 2008

  40. [40]

    Listwise Learning to Rank by Exploring Unique Ratings

    Xiaofeng Zhu and Diego Klabjan. Listwise Learning to Rank by Exploring Unique Ratings. In James Caverlee, Xia (Ben) Hu, Mounia Lalmas, and Wei Wang, editors, WSDM ’20: The Thirteenth ACM International Conference on Web Search and Data Mining, Houston, TX, USA, February 3-7, 2020, pages 798–806. ACM, 2020. doi: 10.1145/3336191.3371814

    work page doi:10.1145/3336191.3371814 2020

  41. [41]

    Advances in collaborative filtering

    Yehuda Koren, Steffen Rendle, and Robert Bell. Advances in collaborative filtering. Recom- mender systems handbook, pages 91–142, 2021

    work page 2021

  42. [42]

    Slim: Sparse linear methods for top-n recommender systems

    Xia Ning and George Karypis. Slim: Sparse linear methods for top-n recommender systems. In 2011 IEEE 11th international conference on data mining, pages 497–506. IEEE, 2011

    work page 2011

  43. [43]

    Negative interactions for improved collaborative filtering: Don’t go deeper, go higher

    Harald Steck and Dawen Liang. Negative interactions for improved collaborative filtering: Don’t go deeper, go higher. In Proceedings of the 15th ACM Conference on Recommender Systems, pages 34–43, 2021

    work page 2021

  44. [44]

    Matrix factorization techniques for recom- mender systems

    Yehuda Koren, Robert Bell, and Chris V olinsky. Matrix factorization techniques for recom- mender systems. Computer, 42(8):30–37, 2009

    work page 2009

  45. [45]

    BPR: Bayesian Personalized Ranking from Implicit Feedback

    Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. Bpr: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618, 2012

    work page internal anchor Pith review Pith/arXiv arXiv 2012

  46. [46]

    Neural collaborative filtering

    Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. Neural collaborative filtering. In Proceedings of the 26th international conference on world wide web, pages 173–182, 2017

    work page 2017

  47. [47]

    Blockbusters and wallflowers: Accurate, diverse, and scalable recommendations with random walks

    Fabian Christoffel, Bibek Paudel, Chris Newell, and Abraham Bernstein. Blockbusters and wallflowers: Accurate, diverse, and scalable recommendations with random walks. In Proceed- ings of the 9th ACM Conference on Recommender Systems, pages 163–170, 2015

    work page 2015

  48. [48]

    Attention is all you need

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

    work page 2017

  49. [49]

    Hruschka Jr, and Tom M

    Andrew Carlson, Justin Betteridge, Bryan Kisiel, Burr Settles, Estevam R. Hruschka Jr, and Tom M. Mitchell. Toward an Architecture for Never-Ending Language Learning. In Maria Fox and David Poole, editors, Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2010, Atlanta, Georgia, USA, July 11-15, 2010, pages 1306–1313. AAAI ...

    work page doi:10.1609/aaai.v24i1.7519 2010

  50. [50]

    Bollacker, Colin Evans, Praveen K

    Kurt D. Bollacker, Colin Evans, Praveen K. Paritosh, Tim Sturge, and Jamie Taylor. Freebase: a collaboratively created graph database for structuring human knowledge. In Jason Tsong-Li Wang, editor, Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2008, Vancouver, BC, Canada, June 10-12, 2008, pages 1247–1250. ACM,

    work page 2008

  51. [51]

    doi: 10.1145/1376616.1376746. 13

    work page doi:10.1145/1376616.1376746

  52. [52]

    Observed versus latent features for knowledge base and text inference

    Kristina Toutanova and Danqi Chen. Observed versus latent features for knowledge base and text inference. In Alexandre Allauzen, Edward Grefenstette, Karl Moritz Hermann, Hugo Larochelle, and Scott Wen-tau Yih, editors,Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality, CVSC 2015, Beijing, China, July 26-31, 2015,...

    work page doi:10.18653/v1/w15-4007 2015

  53. [53]

    Systematic integration of biomedical knowledge prioritizes drugs for repurposing

    Daniel Scott Himmelstein, Antoine Lizee, Christine Hessler, Leo Brueggeman, Sabrina L Chen, Dexter Hadley, Ari Green, Pouya Khankhanian, and Sergio E Baranzini. Systematic integration of biomedical knowledge prioritizes drugs for repurposing. eLife, 6:e26726, September 2017. ISSN 2050-084X. doi: 10.7554/eLife.26726. URL https://doi.org/10.7554/eLife.26726...

    work page doi:10.7554/elife.26726 2017

  54. [54]

    Adam: A Method for Stochastic Optimization

    Diederik P. Kingma and Jimmy Ba. Adam: A Method for Stochastic Optimization. In Yoshua Bengio and Yann LeCun, editors, 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2015. URL http://arxiv.org/abs/1412.6980

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  55. [55]

    Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chil- amkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala

    Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Köpf, Edward Z. Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chil- amkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. PyTorch: An Im- perative Style, Hig...

    work page 2019

  56. [56]

    Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations

    Yihong Chen, Pasquale Minervini, Sebastian Riedel, and Pontus Stenetorp. Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations. In Danqi Chen, Jonathan Berant, Andrew McCallum, and Sameer Singh, editors, 3rd Conference on Automated Knowledge Base Construction, AKBC 2021, Virtual, October 4-8, 2021, 202...

    work page doi:10.24432/c54k5w 2021