Ontology matching is defined as finding a relationship or correspondence between two or more entities in two or more ontologies. To solve the interoperability problem of the domain ontologies, semantically similar entities in these ontologies must be found and aligned before merging them. GraphMatcher, developed in this study, is an ontology matching system using a graph attention approach to compute higher-level representation of a class together with its surrounding terms. The GraphMatcher has obtained remarkable results in in the Ontology Alignment Evaluation Initiative (OAEI) 2022 conference track. Its codes are available at https://github.com/sefeoglu/gat_ontology_matching.
Networks of Bento et al. (2020) [
Since the ontology represents the data with the arbitrary graph, we aim to develop a graph
representation learning model based on a graph attention mechanism [
GraphMatcher utilises a graph representation learning approach that uses the graph attention [
Data preprocessing is one of the most significant parts of developing a ML model and is required to explain the variability of features in a sample. In this study, we have handled data preprocessing of an ontology in six steps: (i) an ontology parsing, (ii) tokenization, (iii) finding the abbreviations, (iv) cleaning from stop words, (v) neighbourhood aggregation for creating the context, and (vi) finding the embedding of the terms.
We used the pre-trained Universal Sentence Encoder (USE) to obtain the word embedding vector
of the class and property. According to benchmark results [
The graph attention introduced in graph attention networks is used to cluster and classify the
citation graphs [
The relation between the centre class and other terms in each homogeneous graph is the same. For example, the relation between the centre node and other terms in Figure 2 is ‘subClassOf’. ℎ = {︁ℎ⃗1, ℎ⃗2, ℎ⃗3......ℎ⃗ , }︁ ℎ′ = ︂{ ⃗ ⃗ ⃗
ℎ′1, ℎ′2, ℎ′3......ℎ⃗′ , ︂} ℎ′ = ||=1 ︁( ∑︁ ℎ⃗ )︁
= ( ⃗ℎ, ⃗ℎ )
Using features in Eq. 1, we have obtained the higher-level representation of the class’ neighbours,
namely its contextual information in this layer. The new features are computed by Eq. 3, and
indicates the linear activation function like sigmoid or softmax in the Eq. 3. To indicate the
higher-level representation of the set of features, R ′ is used as a learnable parameter,
and shared linear transformation is applied to each feature. “K” is the number of independent
heads, and “K” equals five in our system.
(1)
(2)
(3)
(4)
However, some homogeneous graphs having ‘equivalentClass’ or ‘subClassOf’ relationships
might contain some terms regarding restrictions defined with ‘ObjectProperty’ in the
neighbourhood aggregation. The figure explains how the centre class’ contextual information is computed
by the graph attention in one of its homogeneous neighbourhood graphs. The main diference
between the original graph attention approach and our graph attention is that this attention
mechanism is applied to the heterogeneous graph containing five homogeneous subgraphs. The
attention in this layer runs the following various attention mechanisms [
A set of features (the centre class and its neighbouring terms), which is inputs of the graph attention layer, is denoted in Eq. 1 where ℎ⃗ R .
The layer converts the input features to the new higher-level representation of the feature ⃗′ list like defined in Eq. 2 where ℎ R ′ R ′ R ′ denotes a shared attention mechanism and a layer using the self-attention. The following equation computes attention coeficients ( ):
To compute the for ℎ′ in the Eq. 2, this coeficient attention mechanism is applied in Eq. 5 where ⃗ R2 , and is attention mechanism parameterized by ⃗ weight vector. = ( ) =
exp( (⃗ [ ℎ⃗|| ℎ⃗ ])) ∑︀ exp( (⃗ [ ℎ⃗|| ℎ⃗])) (5)
Using the formula in the Eq. 3 in this layer, we have obtained the higher-level representation of the class’ neighbours, namely its contextual information in this layer.
The output layer provides down sampling (dimensional reduction) of the contextual information, which is the concatenation of the class embedding and higher representations of the class’ neighbours.
The cosine similarity layer measures the cosine similarity of output in the previous layer.
The GraphMatcher’s framework has been developed in Python with PyTorch and Ontospy, and
is packed by SEALS using MELT [
The model’s parameters 3 are 0.01 of learning rate, 5 epochs, 0.001 of weight decay and 16 of
batch size. The threshold is computed from false positive alignments in the validation data as
how the VeeAlign [
The conference track consists of sixteen ontologies, but only seven ontologies have (twenty-one) reference alignment cases. These reference alignments have been utilized as ground truths to use true positive alignments. Besides, negative alignment cases have been computed by oversampling from all the possible class and property alignments. Therefore, once we apply a supervised machine learning approach, we can use only these seven ontologies from this dataset.
The Table 1 shows the GraphMatcher results in the conference track. The performance of the GraphMatcher is better in M1 variants than in M2 in terms of F1-measure. Therefore, its F1-measure has been decreased in M3 variants. As a result, the model has a weakness in the M2 variants, namely property alignments. 3These parameters do not give the optimum model. The best model has diferent parameters, but we mistakenly submitted the model using these parameters to the conference track challenge. 4The project uses VeeAlign’s approach directly to compute the threshold with the permission of the first author.
LogMap
SEBMatcher ATMatcher ALIN LogMapLt LSMatch AMD KGMatcher+ ALIOn Matcha
The GraphMatcher is the new ontology matching system participating in OAEI 2022 and is evaluated in the conference track. The GraphMatcher demonstrates remarkable performance in the M1 and M3 evaluation variants in terms of F1-measure, even though it does not have high performance in the M2 evaluation variant. However, all other matchers do not show remarkable results in this M2 evaluation variant.
On the other hand, it is also evaluated in the uncertain reference alignments in OAEI 2022 conference track. It has the highest F1-measure (72% in both of them) in the discrete and continuous metrics 5 among all other matchers evaluated in this track. This means that the GraphMatcher’s confidence is higher than the other matchers evaluated in the OAEI 2022 conference track.
The GraphMatcher should be improved to match the properties, since it does not perform well in the M2 evaluation variants. Its current version does not apply the graph attention to align the properties because of the lack of properties’ neighbours, especially datatype properties. These object type and data type properties might not have enough neighbouring terms to construct contextual information in the ontology. In this case, the property’s context might be improved with the external information in its next version, and the graph attention can also be applied to align the properties. In addition to these improvements, we will train the model with its optimum parameter settings in its further version. 5The evaluation based on the uncertain reference alignments: http://oaei.ontologymatching.org/2022/results/ conference/index.html
In this study, we have introduced the new ontology-matching system called GraphMatcher. The GraphMatcher adapted the graph attention to the homogeneous subgraphs of the centre class’ neighbours to obtain the contextual information about the centre class. The graph attention has computed the higher-level representation of each class and its surrounding classes and properties. The results demonstrate promising performances in M1 and M3 evaluation variants. The future work of this study will be to increase its performance in M2 evaluation variants.