=Paper=
{{Paper
|id=Vol-3389/ATA75
|storemode=property
|title=Interactions Between Knowledge Graph-Related Tasks and Analogical Reasoning: A Discussion
|pdfUrl=https://ceur-ws.org/Vol-3389/ICCBR_2022_Workshop_paper_75.pdf
|volume=Vol-3389
|authors=Pierre Monnin,Miguel Couceiro
|dblpUrl=https://dblp.org/rec/conf/iccbr/MonninC22
}}
==Interactions Between Knowledge Graph-Related Tasks and Analogical Reasoning: A Discussion==
https://ceur-ws.org/Vol-3389/ICCBR_2022_Workshop_paper_75.pdf
Interactions Between Knowledge Graph-Related
Tasks and Analogical Reasoning: A Discussion
Pierre Monnin1,* , Miguel Couceiro2
1
Orange, Belfort, France
2
Université de Lorraine, CNRS, LORIA, Nancy, France
Abstract
Analogical reasoning has been extensively studied and relies on statements of the form “𝐴 is to 𝐵 as 𝐶 is
to 𝐷” that are called analogical proportions. The motivation of our work is based on the following twofold
observation. On the one hand, recent analogy-based settings relying on character or word embeddings
have achieved state-of-the-art performance on Natural Language Processing tasks. On the other hand,
graph embedding approaches are now mainstream for knowledge graph-related tasks, e.g., knowledge
discovery, knowledge graph refinement, or recommendation. Inspired by these works, we advocate for
the further study of interactions between knowledge graph-related tasks and analogical reasoning. In
particular, we outline how knowledge graph embeddings combined with analogical reasoning could
support semantic table interpretation, knowledge matching, and recommendation.
Keywords
Analogical reasoning, Graph Embedding, Semantic Table Interpretation, Knowledge Matching, Recom-
mendation
1. Introduction
Analogical reasoning is a remarkable capability of the human mind [1]. Analogical proportions or,
simply, analogies, are statements of the form “𝐴 is to 𝐵 as 𝐶 is to 𝐷”‘ which are often written as
𝐴 : 𝐵 :: 𝐶 : 𝐷. A typical example of an analogy would be “Paris is to France as Stockholm is to
Sweden”. Most of the recent works on analogy use the formalization proposed in Lepage [2], and
that subsumes common intuition on analogies viewed as a geometric proportion (Equation (1)),
an arithmetic proportion (Equation (2)), or as a parallelogram in a vector space (Equation (3)):
𝐴 𝐶 →
− →
− →
− →−
= (1) 𝐴−𝐵 =𝐶 −𝐷 (2) 𝐴−𝐵 = 𝐶 −𝐷 (3)
𝐵 𝐷
Traditional tasks related to analogical reasoning include analogy detection (i.e., classifying
a quadruple as a valid or invalid analogy) and analogy solving (i.e., finding an 𝑥 such that
ICCBR Analogies’22: Workshop on Analogies: from Theory to Applications at ICCBR-2022, September, 2022, Nancy,
France
*
Corresponding author.
$ pierre.monnin@orange.com (P. Monnin); miguel.couceiro@loria.fr (M. Couceiro)
https://pmonnin.github.io (P. Monnin); https://members.loria.fr/mcouceiro/ (M. Couceiro)
0000-0002-2017-8426 (P. Monnin); 0000-0003-2316-7623 (M. Couceiro)
© 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
Workshop
Proceedings
http://ceur-ws.org
ISSN 1613-0073
CEUR Workshop Proceedings (CEUR-WS.org)
1
Pierre Monnin et al. ICCBR’22 Workshop Proceedings
𝐴 : 𝐵 :: 𝐶 : 𝑥 constitutes a valid analogy). Analogies have been extensively studied in
Natural Language Processing settings with applications in word morphology [3, 4], machine
translation [5] and semantic tasks [6, 7, 8].
Also, knowledge graphs (KGs) have gained a significant interest from both academic and
industrial actors. A KG can be seen defined as “a graph of data intended to accumulate and
convey knowledge of the real world, whose nodes represent entities of interest and whose edges
represent relations between these entities” [9]. Atomic elements of KGs are triples ⟨𝑠, 𝑝, 𝑜⟩ where
𝑠 is the subject, 𝑝 the predicate, and 𝑜 the object of the triple respectively. An example of a triple
could be ⟨Paris, capitalOf, France⟩, where the predicate (also called property) capitalOf
qualifies the relation holding between Paris and France. KGs support several downstream
applications including offering a consolidated view of knowledge scattered across sources,
fact-checking, search engines, e-commerce, question answering, or recommendation [10, 11,
12, 13, 14]. Various techniques have been developed to build, refine, and use KGs, including
Knowledge Graph Embedding (KGE) techniques which have shown impressive performance [12,
15]. Interestingly, the parallelogram view of an analogy (Equation (3)) can be related to the
translational view adopted by some KGE models. For example, TransE [16] models a triple
−−−−→ −−−−−−−−→ −−−−−→
⟨Paris, capitalOf, France⟩ as a translation Paris + capitalOf = France. Hence, we
would have:
−−−−−→ −−−−→ −−−−−→ −−−−−−−−→ −−−−−−−−→
France − Paris = Sweden − Stockholm = capitalOf
It is noteworthy that some embedding techniques already consider analogical properties. For
example, Liu et al. [17] argue that analogical inference is desirable for knowledge graph com-
pletion and include analogical structures in their learning objective. Alternatively, Portisch
et al. [18] evaluate link prediction and data mining approaches developed for knowledge graphs
on an analogy inference task with the goal of retrieving the last element (𝐷) of a quadruple
given the three first elements (𝐴, 𝐵, and 𝐶). Inspired by such previous work, we advocate in
this article for a further study of interactions between analogical reasoning and knowledge
graph-related tasks.
This paper is organized as follows. In Section 2, we discuss possible interactions between ana-
logical reasoning and Semantic Table Interpretation (STI) as STI can be supported by knowledge
graph embeddings. In Section 3 we reformulate knowledge matching in terms of analogical
proportions, and we further explore this discussion for knowledge graph-based recommendation
(Section 4). We then conclude by briefly outlining some noteworthy perspectives in Section 5.
2. Analogies for Semantic Table Interpretation
Semantic Table Interpretation (STI) aims at understanding the semantic content of tabular data
such as Excel or CSV files, or Web tables. This process is carried out by annotating elements of
tables with constituents of a knowledge graph through the three following tasks:
Cell-Entity Annotation (CEA) associates cells with entities;
Column-Type Annotation (CTA) associates columns with types;
Columns-Property Annotation (CPA) associates pairs of columns with properties.
2
Pierre Monnin et al. ICCBR’22 Workshop Proceedings
Table 1
Example of a table listing countries, their capitals, their official language(s), and their GDP. This table
is inspired from the Wikipedia pages “List of countries and dependencies and their capitals in native
languages”1 and “List of countries by GDP (nominal)”.2
Country Capital Official language(s) GDP (US$ million)
Finland (empty) Finnish, Swedish 297,617
France Paris French 2,936,702
Germany Berlin German 4,256,540
Sweden Stockholm Swedish 621,241
Switzerland Bern (de facto) German, French, Italian, Romansh 841,969
STI has seen a growing research interest over the past few years, for example with the SemTab
challenge [19]. Indeed, large parts of company knowledge or knowledge available on the Web
are encoded as tabular data. Consequently, understanding the content of tables paves the way
for several downstream tasks such as table completion with KG content, KG completion with
table content, or data set search services [20].
When interpreting tabular data, several issues arise, e.g., different encoding charsets, mis-
aligned cells, or missing values (for example, the capital of Finland in Table 1). Tables alone
also provide little context to help disambiguate candidate entities for cell annotation [21].
For example, consider Table 1 and its annotation with Wikidata, an encyclopedic knowledge
graph [22]. Based solely on entity labels and string matching, annotation candidates for cell
“Germany” are entity Q1423 (Germany, the European country) and entity Q13505654 (Germany,
the constituency of the European Parliament). To cope with such issues, current STI approaches
rely on syntactic lookups and majority voting [23, 24], or graph embedding-based disambigua-
tion [25]. In the latter case, Chabot et al. [25] rely on the assumption that columns of tables
are semantically coherent. Thus, when applying a clustering algorithm on the embeddings of
candidate entities for a whole column, valid entities should be grouped in the same cluster. In
our example, Q142 should be grouped in the same cluster as the entities representing the other
countries appearing in the table.
Interestingly, the semantic coherence of columns also allows to see a table through the
lens of analogies. A first view consists in considering cells in pairs of columns as taking part
in analogical proportions. For example, Table 1 can be seen as sets of analogies of the form
France : Paris :: Germany : Berlin or France : French :: Germany : German. In such a
setting, the task of filling missing table values can be thought of as an analogy solving task, e.g.,
we would like to find 𝑥 such that France : Paris :: Finland : x is a valid analogy. In STI,
such as task could be carried out both by retrieval (in case the correct entity is in the knowledge
graph) and generation (in case the correct entity is absent from the target knowledge graph).
Regarding disambiguation between candidate entities, this could be achieved by choosing the
entity that satisfies the highest number of analogies generated from the table. However, it is
2
https://en.wikipedia.org/wiki/List_of_countries_and_dependencies_and_their_capitals_in_native_languages
2
https://en.wikipedia.org/wiki/List_of_countries_by_GDP_(nominal)
3
https://www.wikidata.org/wiki/Q183
4
https://www.wikidata.org/wiki/Q1350565
3
Pierre Monnin et al. ICCBR’22 Workshop Proceedings
noteworthy that tables can lead to a high number of analogies. For example, only considering
columns “Country” and “Capital” of Table 1 already produces 12 analogies. One could thus
wonder about the computational complexity of such an approach. Future work could investigate
the need for generating all possible analogies or, on the contrary, for restricting to the most
useful analogies to the task at hand. Such a notion of usefulness may be task- or domain-
dependent and remains to be defined and discussed. A first approach to generating all analogies
or pruning redundant analogies can be achieved by taking into account properties such as the
symmetry of analogical proportions (i.e., 𝐴 : 𝐵 :: 𝐶 : 𝐷 → 𝐶 : 𝐷 :: 𝐴 : 𝐵).
Alternatively to generating analogies from pairs of columns independently, tables could be
considered as whole in an analogical setting that follows the work of Prade and Richard [26]
and Hug et al. [27]. Rows 𝑟1 , 𝑟2 , 𝑟3 , and 𝑟4 could be seen as vectors →
−
𝑟𝑖 = (𝑟𝑖1 , 𝑟𝑖2 , . . . , 𝑟𝑖𝑛 )
such that analogical proportions hold on some of their components 𝐽 ⊂ [1, 𝑛]. Then, from the
analogical inference principle, it follows that analogical proportions should also hold on the
remaining components:
∀𝑗 ∈ 𝐽, 𝑟1𝑗 : 𝑟2𝑗 :: 𝑟3𝑗 : 𝑟4𝑗
(4)
∀𝑘 ∈ [1, 𝑛] ∖ 𝐽, 𝑟1𝑘 : 𝑟2𝑘 :: 𝑟3𝑘 : 𝑟4𝑘
This more holistic view may guide the STI process by focusing on analogical proportions that
are valid on a high number of columns. However, in both views, analogical validity may not be
possible over the entire table, i.e., all generated analogies may not be detected as valid. In such
case, analogical validity ratios may be interesting metrics to guide and evaluate the quality of
the STI process.
Inspired by recent approaches [3, 17, 18], we assume that analogical reasoning for Semantic
Table Interpretation could be supported by graph or table embeddings [12, 28]. However, some
challenges inherent to tabular data must be integrated into analogical formalizations. For
example, tables can contain cells with multiple entities (e.g. “Finnish, Swedish” in Table 1) and
columns can involve a mix of entities and literals (e.g., column “GDP (US$ million)”). This leads
to consider multi-modal embeddings. In a table-graph multi-modal embedding space, one could
also envision the CEA task as detecting or solving analogies of the form 𝑟𝑖1 : 𝑒𝑖1 :: 𝑟𝑖2 : 𝑒𝑖2
where 𝑟𝑖𝑗 are cells of a table and 𝑒𝑖𝑗 are their matching entities in the knowledge graph.
3. Analogies for Knowledge Matching
Knowledge graphs are freely aggregated, published, and edited in the Web of data, and may thus
overlap. Hence, a key task resides in matching (or aligning) their content [29]. This task encom-
passes the identification, within an aggregated knowledge graph or across knowledge graphs, of
nodes that are equivalent, more specific, weakly related, or that represent contradictory knowl-
edge units. Matching allows to obtain a consolidated view of scattered elements of knowledge
which is beneficial to many applications, such as fact-checking or query answering. The task
of matching elements of knowledge graphs has been extensively studied in the literature. We
refer the interested reader to the book of Euzenat and Shvaiko [29] for a comprehensive review
of existing work.
A knowledge matching task can be approached as an analogical setting. Indeed, nodes
of knowledge graphs can be seen in analogical proportions with their neighbors. For ex-
4
Pierre Monnin et al. ICCBR’22 Workshop Proceedings
𝒦1 𝒦2
French of Paris Paris French
fi
ci uage
al
la lang
ng al
u ag
capital capital ici
e off
? 82.27317
La Marseillaise France France
anthem life expectancy year
Figure 1: Example of a knowledge matching setting between two knowledge graphs 𝒦1 and 𝒦2 inspired
from Wikidata.
ample, from the two knowledge graphs represented in Figure 1, it is possible to generate
the analogy France𝒦1 : Paris𝒦1 :: France𝒦2 : Paris𝒦2 . The matching task then comes
down to aligning nodes that maximize the validity of such analogical proportions between
their respective neighbors with an analogy detection task. This corresponds to a structure-
based matching [29]. This analogy-based matching process could be strengthen by consider-
ing existing alignments between neighbors (e.g., Paris𝒦1 and Paris𝒦2 ) that could result
from different matching methods (e.g., string matching). For example, from the reflexiv-
ity property of analogical proportions (i.e., 𝐴 : 𝐵 :: 𝐴 : 𝐵), the inner symmetry (i.e.,
𝐴 : 𝐵 :: 𝐶 : 𝐷 =⇒ 𝐵 : 𝐴 :: 𝐷 : 𝐶), the uniqueness postulate (i.e., given 𝐴, 𝐵, and
𝐶, there exists only one 𝐷 such that 𝐴 : 𝐵 :: 𝐶 : 𝐷), the alignment Paris𝒦1 = Paris𝒦2 ,
and the analogical proportion Paris : France𝒦1 :: Paris : France𝒦2 , it follows that
France𝒦1 = France𝒦2 . Such an analogical matching process could also produce valid results
without preexisting alignments by only taking into account structural similarities. Thus, it
could be used to start a matching pipeline. Note that the previous analogical proportion relies
on similarities between identical nodes to match. By generating analogies based on granularity
differences or contradictions between nodes, we could output such different alignment types.
From the previous observations, a challenge thus resides in having a set of preexisting align-
ments of different types that could guide the analogy-based matching towards specific types of
alignments.
It should be noted that other analogy-based views to match nodes can be considered. For
example, given a set of preexisting alignments, matching a node France𝒦1 can be seen as
solving a set of analogical equations of the form
Paris𝒦2 : Paris𝒦2 :: France𝒦1 : 𝑥
French𝒦2 : French𝒦2 :: France𝒦1 : 𝑥
and chosing the entity that is mostly output as 𝑥. Analogies could also serve as a basis to
align predicates (e.g., capital𝒦1 and capital𝒦2 ). Indeed, if two predicate are identical, then
analogical proportions should hold between the entities they link, e.g.,
France𝒦1 : Paris𝒦1 :: France𝒦2 : Paris𝒦2
Germany𝒦1 : Berlin𝒦1 :: Germany𝒦2 : Berlin𝒦2
5
Pierre Monnin et al. ICCBR’22 Workshop Proceedings
France𝒦1 : Paris𝒦1 :: Germany𝒦2 : Berlin𝒦2
Hence, the alignment of predicates could be carried out by matching predicates that have a high
number of valid analogical proportions between the entities they respectively connect.
Recent matching approaches rely on graph embeddings [30, 31, 32, 33]. Hence, it could be
of interest to use such graph embeddings in an analogical setting for matching. This could
correspond to aligning the embedding spaces of the KGs to match [34]. Enforcing analogical
properties in the training procedure similarly to Liu et al. [17] could also be tested to learn
specific graph embeddings tailored for analogical reasoning. However, it should be noted that
analogy-based approaches to knowledge matching need to cope with issues similar to those
described in Section 2. Indeed, KGs mix entities and literals (e.g., the life expectancy in 𝒦2 ),
which may require the use of multi-modal embeddings. Additionally, KGs may be incomplete
and two equivalent nodes may not be entirely comparable based on their neigbhors. For example,
in Figure 1, France𝒦1 is associated with its anthem La Marseillaise which is absent from
𝒦2 . Additionally, not all nodes from a KG may found their counterpart in another KG. Hence, an
analogy-based matching approach should try to maximize analogical validity without reaching
full coverage. Due to the increasing size of KGs, the computational complexity of such an
analogy-based matching approach and the need for generating all possible analogies or only
the most useful should also be taken into account.
4. Analogies for Knowledge Graph-Based Recommendation
In this section, we consider the task of recommending items to users. Traditional approaches rely
on similarity between users and/or items. Indeed, collaborative filtering-based recommender
systems simultaneously consider similarities between users, items, and users and items based
on their interactions. Alternatively, content based-recommender systems consider features of
items to find and recommend items similar to the ones liked by the users.
As such, recommendation is a natural setting for analogical reasoning since it is also based
on similarities. That is why, analogies have already been applied to recommendation with
the objective of predicting the rating of an item by a user based on ratings of other similar
users [27, 35]. Precisely, consider four users 𝑎, 𝑏, 𝑐, and 𝑑 such that for each item 𝑗 commonly
rated, the analogical proportion 𝑟𝑎𝑗 : 𝑟𝑏𝑗 :: 𝑟𝑐𝑗 : 𝑟𝑑𝑗 holds, with 𝑟𝑎𝑗 the rating of user 𝑎 for item
𝑗. From the analogical inference principle, it is possible to predict the rating 𝑟𝑑𝑖 for an item 𝑖
that has only been rated by 𝑎, 𝑏, and 𝑐 by solving the analogical proportion 𝑟𝑎𝑖 : 𝑟𝑏𝑖 :: 𝑟𝑐𝑖 : 𝑥.
This analogy-based setting has also been adapted to preference learning with the objective of
learning to rank a set of objects [36, 37], and considered in case-based reasoning [38, 39].
Recently, KGs have been introduced in recommender systems as sources of side informa-
tion [11, 13]. Indeed, KGs allow to represent relations between items and their attributes,
between users and items, and any additional user information. Hence, KGs better capture
mutual relations between these different entities. Such rich KGs and their advantages moti-
vated the use of knowledge graph embeddings for recommendation [11, 13]. However, these
embeddings models do not take into account potential analogical constraints holding between
users and items. Hence, we propose to study how knowledge graph embeddings could be
combined with analogical proportions for recommendation. Such proportions could involve
6
Pierre Monnin et al. ICCBR’22 Workshop Proceedings
users and items to directly support the recommendation, e.g., user1 : item1 :: user2 : item2 .
We could also envision user-only analogies user1 : user2 :: user3 : user4 allowing to
find similar users that could then support the recommendation of an item. Item-attribute
analogies item1 : attribute2 :: item3 : attribute4 could highlight similarities between
items whereas user-attribute analogies user1 : attribute2 :: user3 : attribute4 could
emphasize the importance of some attributes to users. Such analogical proportions could be
used to enrich training data or to check outputs of models by ensuring a minimum level of
valid analogies with the recommended item(s). Alternatively, such analogies could be directly
integrated in the learning procedure of the graph embeddings, similarly to the work of Liu
et al. [17].
5. Conclusion & Perspectives
In this article, we advocated for the deeper study of the interactions between analogical reasoning
and knowledge graph-related tasks. On the one hand, one can profit from recent analogy-based
settings with state-of-the-art results on various tasks such as in Natural Language Processing
and decision making, that make use of suitable data representations (embeddings). On the other
hand, approaches based on knowledge graph embeddings are now mainstream and achieve
competitive results for several tasks associated with knowledge graphs.
Motivated by these developments, we illustrated how analogy-based settings emerge naturally
in semantic table interpretation, knowledge matching, and recommendation. While they could
be suitably supported by available table or graph embeddings, such settings pose several
challenges and open questions that need to be addressed. In particular, it remains to assess
whether analogical views of such tasks actually improve performance. Interestingly, aside
performance, such an integration of analogical reasoning could pave the way towards additional
interpretability and explainability of approaches as discussed by Hüllermeier [40]. This could,
in turn, strengthen the line of research studying knowledge graphs as tools for explainable
AI [41].
References
[1] M. Mitchell, Abstraction and analogy-making in artificial intelligence, Annals of the New
York Academy of Sciences 1505 (2021) 79–101.
[2] Y. Lepage, De l’analogie rendant compte de la commutation en linguistique, 2003. URL:
https://tel.archives-ouvertes.fr/tel-00004372.
[3] S. Alsaidi, A. Decker, P. Lay, E. Marquer, P. Murena, M. Couceiro, A neural approach for
detecting morphological analogies, in: 8th IEEE International Conference on Data Science
and Advanced Analytics, DSAA 2021, Porto, Portugal, October 6-9, 2021, IEEE, 2021, pp.
1–10. doi:10.1109/DSAA53316.2021.9564186.
[4] P. Murena, M. Al-Ghossein, J. Dessalles, A. Cornuéjols, Solving analogies on words based
on minimal complexity transformation, in: Proceedings of the Twenty-Ninth International
Joint Conference on Artificial Intelligence, IJCAI 2020, ijcai.org, 2020, pp. 1848–1854.
doi:10.24963/ijcai.2020/256.
7
Pierre Monnin et al. ICCBR’22 Workshop Proceedings
[5] V. Taillandier, L. Wang, Y. Lepage, Réseaux de neurones pour la résolution d’analogies
entre phrases en traduction automatique par l’exemple (neural networks for the resolu-
tion of analogies between sentences in EBMT), in: Actes de la 6e conférence conjointe
Journées d’Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues
Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour
le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 2 : Traitement
Automatique des Langues Naturelle, Nancy, France, June 8-19, 2020, ATALA et AFCP, 2020,
pp. 108–121. URL: https://aclanthology.org/2020.jeptalnrecital-taln.9/.
[6] S. D. Afantenos, T. Kunze, S. Lim, H. Prade, G. Richard, Analogies between sentences:
Theoretical aspects - preliminary experiments, in: J. Vejnarová, N. Wilson (Eds.), Symbolic
and Quantitative Approaches to Reasoning with Uncertainty - 16th European Conference,
ECSQARU 2021, Prague, Czech Republic, September 21-24, 2021, Proceedings, volume
12897 of Lecture Notes in Computer Science, Springer, 2021, pp. 3–18.
[7] S. Lim, H. Prade, G. Richard, Classifying and completing word analogies by machine
learning, Int. J. Approx. Reason. 132 (2021) 1–25.
[8] Y. Lepage, Analogies between short sentences: A semantico-formal approach, in: Z. Vetu-
lani, P. Paroubek, M. Kubis (Eds.), Human Language Technology. Challenges for Computer
Science and Linguistics - 9th Language and Technology Conference, LTC 2019, Poznan,
Poland, May 17-19, 2019, Revised Selected Papers, volume 13212 of Lecture Notes in Com-
puter Science, Springer, 2019, pp. 163–179.
[9] A. Hogan, E. Blomqvist, M. Cochez, C. d’Amato, G. de Melo, C. Gutiérrez, S. Kirrane,
J. E. L. Gayo, R. Navigli, S. Neumaier, A. N. Ngomo, A. Polleres, S. M. Rashid, A. Rula,
L. Schmelzeisen, J. Sequeda, S. Staab, A. Zimmermann, Knowledge Graphs, Synthesis
Lectures on Data, Semantics, and Knowledge, Morgan & Claypool Publishers, 2021. doi:10.
2200/S01125ED1V01Y202109DSK022.
[10] X. L. Dong, Building a broad knowledge graph for products, in: 35th IEEE International
Conference on Data Engineering, ICDE 2019, Macao, China, April 8-11, 2019, IEEE, 2019,
p. 25. doi:10.1109/ICDE.2019.00010.
[11] Q. Guo, F. Zhuang, C. Qin, H. Zhu, X. Xie, H. Xiong, Q. He, A survey on knowledge graph-
based recommender systems, IEEE Transactions on Knowledge and Data Engineering
(2020) 1–1. doi:10.1109/TKDE.2020.3028705.
[12] S. Ji, S. Pan, E. Cambria, P. Marttinen, P. S. Yu, A survey on knowledge graphs: Represen-
tation, acquisition, and applications, IEEE Transactions on Neural Networks and Learning
Systems 33 (2022) 494–514. doi:10.1109/TNNLS.2021.3070843.
[13] C. Liu, L. Li, X. Yao, L. Tang, A survey of recommendation algorithms based on knowledge
graph embedding, in: 2019 IEEE International Conference on Computer Science and
Educational Informatization (CSEI), 2019, pp. 168–171. doi:10.1109/CSEI47661.2019.
8938875.
[14] N. F. Noy, Y. Gao, A. Jain, A. Narayanan, A. Patterson, J. Taylor, Industry-scale knowledge
graphs: lessons and challenges, Communications of the ACM 62 (2019) 36–43. doi:10.
1145/3331166.
[15] M. Nickel, K. Murphy, V. Tresp, E. Gabrilovich, A review of relational machine learning
for knowledge graphs, Proceedings of the IEEE 104 (2016) 11–33. doi:10.1109/JPROC.
2015.2483592.
8
Pierre Monnin et al. ICCBR’22 Workshop Proceedings
[16] A. Bordes, N. Usunier, A. García-Durán, J. Weston, O. Yakhnenko, Translating em-
beddings for modeling multi-relational data, in: Advances in Neural Information Pro-
cessing Systems 26: 27th Annual Conference on Neural Information Processing Sys-
tems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada,
United States, 2013, pp. 2787–2795. URL: https://proceedings.neurips.cc/paper/2013/hash/
1cecc7a77928ca8133fa24680a88d2f9-Abstract.html.
[17] H. Liu, Y. Wu, Y. Yang, Analogical inference for multi-relational embeddings, in: Proceed-
ings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW,
Australia, 6-11 August 2017, volume 70 of Proceedings of Machine Learning Research, PMLR,
2017, pp. 2168–2178. URL: http://proceedings.mlr.press/v70/liu17d.html.
[18] J. Portisch, N. Heist, H. Paulheim, Knowledge graph embedding for data mining vs.
knowledge graph embedding for link prediction - two sides of the same coin?, Semantic
Web 13 (2022) 399–422. doi:10.3233/SW-212892.
[19] E. Jiménez-Ruiz, V. Efthymiou, J. Chen, V. Cutrona, O. Hassanzadeh, J. Sequeda, K. Srinivas,
N. Abdelmageed, M. Hulsebos, D. Oliveira, C. Pesquita (Eds.), Proceedings of the Semantic
Web Challenge on Tabular Data to Knowledge Graph Matching co-located with the 20th
International Semantic Web Conference (ISWC 2021), Virtual conference, October 27, 2021,
volume 3103 of CEUR Workshop Proceedings, CEUR-WS.org, 2022. URL: http://ceur-ws.org/
Vol-3103.
[20] A. Chapman, E. Simperl, L. Koesten, G. Konstantinidis, L. Ibáñez, E. Kacprzak, P. Groth,
Dataset search: a survey, VLDB Journal 29 (2020) 251–272.
[21] S. Zhang, K. Balog, Web table extraction, retrieval, and augmentation: A survey, ACM
Transactions on Intelligent Systems and Technology 11 (2020) 13:1–13:35. doi:10.1145/
3372117.
[22] D. Vrandecic, M. Krötzsch, Wikidata: a free collaborative knowledgebase, Communications
of the ACM 57 (2014) 78–85. doi:10.1145/2629489.
[23] M. Cremaschi, R. Avogadro, D. Chieregato, Mantistable: an automatic approach for the
semantic table interpretation, in: Proceedings of the Semantic Web Challenge on Tabular
Data to Knowledge Graph Matching co-located with the 18th International Semantic Web
Conference, SemTab@ISWC 2019, Auckland, New Zealand, October 30, 2019, volume 2553
of CEUR Workshop Proceedings, CEUR-WS.org, 2019, pp. 15–24. URL: http://ceur-ws.org/
Vol-2553/paper3.pdf.
[24] V. Huynh, J. Liu, Y. Chabot, F. Deuzé, T. Labbé, P. Monnin, R. Troncy, DAGOBAH: table
and graph contexts for efficient semantic annotation of tabular data, in: Proceedings of
the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching co-located
with the 20th International Semantic Web Conference (ISWC 2021), Virtual conference,
October 27, 2021, volume 3103 of CEUR Workshop Proceedings, CEUR-WS.org, 2021, pp.
19–31. URL: http://ceur-ws.org/Vol-3103/paper2.pdf.
[25] Y. Chabot, T. Labbé, J. Liu, R. Troncy, DAGOBAH: an end-to-end context-free tabular data
semantic annotation system, in: Proceedings of the Semantic Web Challenge on Tabular
Data to Knowledge Graph Matching co-located with the 18th International Semantic Web
Conference, SemTab@ISWC 2019, Auckland, New Zealand, October 30, 2019, volume 2553
of CEUR Workshop Proceedings, CEUR-WS.org, 2019, pp. 41–48. URL: http://ceur-ws.org/
Vol-2553/paper6.pdf.
9
Pierre Monnin et al. ICCBR’22 Workshop Proceedings
[26] H. Prade, G. Richard, Reasoning with logical proportions, in: Principles of Knowledge
Representation and Reasoning: Proceedings of the Twelfth International Conference, KR
2010, Toronto, Ontario, Canada, May 9-13, 2010, AAAI Press, 2010. URL: http://aaai.org/
ocs/index.php/KR/KR2010/paper/view/1413.
[27] N. Hug, H. Prade, G. Richard, M. Serrurier, Analogy in recommendation. numerical
vs. ordinal: A discussion, in: 2016 IEEE International Conference on Fuzzy Systems,
FUZZ-IEEE 2016, Vancouver, BC, Canada, July 24-29, 2016, IEEE, 2016, pp. 2220–2226.
doi:10.1109/FUZZ-IEEE.2016.7737969.
[28] X. Deng, H. Sun, A. Lees, Y. Wu, C. Yu, TURL: table understanding through representation
learning, Proceedings of the VLDB Endowment 14 (2020) 307–319. URL: http://www.vldb.
org/pvldb/vol14/p307-deng.pdf. doi:10.5555/3430915.3442430.
[29] J. Euzenat, P. Shvaiko, Ontology Matching, Second Edition, Springer, 2013.
[30] E. Jiménez-Ruiz, A. Agibetov, J. Chen, M. Samwald, V. Cross, Dividing the ontology
alignment task with semantic embeddings and logic-based modules, in: ECAI 2020 - 24th
European Conference on Artificial Intelligence, 29 August-8 September 2020, Santiago
de Compostela, Spain, August 29 - September 8, 2020 - Including 10th Conference on
Prestigious Applications of Artificial Intelligence (PAIS 2020), volume 325 of Frontiers
in Artificial Intelligence and Applications, IOS Press, 2020, pp. 784–791. doi:10.3233/
FAIA200167.
[31] P. Monnin, C. Raïssi, A. Napoli, A. Coulet, Discovering alignment relations with graph
convolutional networks: A biomedical case study, Semantic Web 13 (2022) 379–398.
doi:10.3233/SW-210452.
[32] N. Pang, W. Zeng, J. Tang, Z. Tan, X. Zhao, Iterative entity alignment with improved neural
attribute embedding, in: Proceedings of the Workshop on Deep Learning for Knowledge
Graphs (DL4KG2019) Co-located with the 16th Extended Semantic Web Conference 2019
(ESWC 2019), Portoroz, Slovenia, June 2, 2019, volume 2377 of CEUR Workshop Proceedings,
CEUR-WS.org, 2019, pp. 41–46.
[33] Z. Wang, Q. Lv, X. Lan, Y. Zhang, Cross-lingual knowledge graph alignment via graph
convolutional networks, in: Proceedings of the 2018 Conference on Empirical Methods in
Natural Language Processing, Brussels, Belgium, October 31 - November 4, 2018, Associa-
tion for Computational Linguistics, 2018, pp. 349–357. doi:10.18653/v1/d18-1032.
[34] R. Biswas, M. Alam, H. Sack, Is aligning embedding spaces a challenging task? a study on
heterogeneous embedding alignment methods, 2020. URL: https://arxiv.org/abs/2002.09247.
arXiv:2002.09247.
[35] N. Hug, H. Prade, G. Richard, Experimenting analogical reasoning in recommendation, in:
Foundations of Intelligent Systems - 22nd International Symposium, ISMIS 2015, Lyon,
France, October 21-23, 2015, Proceedings, volume 9384 of Lecture Notes in Computer Science,
Springer, 2015, pp. 69–78. doi:10.1007/978-3-319-25252-0\_8.
[36] M. A. Fahandar, E. Hüllermeier, Learning to rank based on analogical reasoning, in:
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-
18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th
AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New
Orleans, Louisiana, USA, February 2-7, 2018, AAAI Press, 2018, pp. 2951–2958. URL:
https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16830.
10
Pierre Monnin et al. ICCBR’22 Workshop Proceedings
[37] M. A. Fahandar, E. Hüllermeier, Analogical embedding for analogy-based learning to
rank, in: Advances in Intelligent Data Analysis XIX - 19th International Symposium
on Intelligent Data Analysis, IDA 2021, Porto, Portugal, April 26-28, 2021, Proceedings,
volume 12695 of Lecture Notes in Computer Science, Springer, 2021, pp. 76–88. doi:10.
1007/978-3-030-74251-5_7.
[38] M. M. Richter, R. O. Weber, Case-based reasoning, Springer, 2016.
[39] J. Lieber, E. Nauer, H. Prade, When Revision-Based Case Adaptation Meets Analogical
Extrapolation, in: 29th ICCBR, volume 12877 of LNCS, 2021, pp. 156–170.
[40] E. Hüllermeier, Towards analogy-based explanations in machine learning, in: Modeling
Decisions for Artificial Intelligence - 17th International Conference, MDAI 2020, Sant
Cugat, Spain, September 2-4, 2020, Proceedings, volume 12256 of Lecture Notes in Computer
Science, Springer, 2020, pp. 205–217. doi:10.1007/978-3-030-57524-3_17.
[41] I. Tiddi, S. Schlobach, Knowledge graphs as tools for explainable machine learning: A
survey, Artificial Intelligence 302 (2022) 103627. doi:10.1016/j.artint.2021.103627.
11