DAGE: DAG Query Answering via Relational Combinator with Logical Constraints

• URL: http://arxiv.org/abs/2410.22105v1
• Date: Tue, 29 Oct 2024 15:02:48 GMT
• Title: DAGE: DAG Query Answering via Relational Combinator with Logical Constraints
• Authors: Yunjie He, Bo Xiong, Daniel Hernández, Yuqicheng Zhu, Evgeny Kharlamov, Steffen Staab,
• Abstract summary: We propose a query embedding method for DAG queries called DAGE. DAGE combines the possibly multiple paths between two nodes into a single path with a trainable operator. We show that it is possible to implement DAGE on top of existing query embedding methods.
• Score: 24.60431781360608
• License:
• Abstract: Predicting answers to queries over knowledge graphs is called a complex reasoning task because answering a query requires subdividing it into subqueries. Existing query embedding methods use this decomposition to compute the embedding of a query as the combination of the embedding of the subqueries. This requirement limits the answerable queries to queries having a single free variable and being decomposable, which are called tree-form queries and correspond to the $\mathcal{SROI}^-$ description logic. In this paper, we define a more general set of queries, called DAG queries and formulated in the $\mathcal{ALCOIR}$ description logic, propose a query embedding method for them, called DAGE, and a new benchmark to evaluate query embeddings on them. Given the computational graph of a DAG query, DAGE combines the possibly multiple paths between two nodes into a single path with a trainable operator that represents the intersection of relations and learns DAG-DL from tautologies. We show that it is possible to implement DAGE on top of existing query embedding methods, and we empirically measure the improvement of our method over the results of vanilla methods evaluated in tree-form queries that approximate the DAG queries of our proposed benchmark.

Related papers

• Effective Instruction Parsing Plugin for Complex Logical Query Answering on Knowledge Graphs [51.33342412699939]
  Knowledge Graph Query Embedding (KGQE) aims to embed First-Order Logic (FOL) queries in a low-dimensional KG space for complex reasoning over incomplete KGs. Recent studies integrate various external information (such as entity types and relation context) to better capture the logical semantics of FOL queries. We propose an effective Query Instruction Parsing (QIPP) that captures latent query patterns from code-like query instructions.
  arXiv  Detail & Related papers  (2024-10-27T03:18:52Z)
• RConE: Rough Cone Embedding for Multi-Hop Logical Query Answering on Multi-Modal Knowledge Graphs [30.94793132285142]
  Multi-hop query answering over a Knowledge Graph involves traversing one or more hops from the start node to answer a query. We propose RConE, an embedding method to capture the multi-modal information needed to answer a query. We are the first to introduce logical constructs in querying MMKGs and to answer queries that involve sub-entities of multi-modal entities as the answer.
  arXiv  Detail & Related papers  (2024-08-21T11:02:35Z)
• Database-Augmented Query Representation for Information Retrieval [59.57065228857247]
  We present a novel retrieval framework called Database-Augmented Query representation (DAQu) DAQu augments the original query with various (query-related) metadata across multiple tables. We validate DAQu in diverse retrieval scenarios that can incorporate metadata from the relational database.
  arXiv  Detail & Related papers  (2024-06-23T05:02:21Z)
• Pathformer: Recursive Path Query Encoding for Complex Logical Query Answering [20.521886749524814]
  We propose a neural one-point embedding method called Pathformer based on the tree-like computation graph, i.e., query tree. Specifically, Pathformer decomposes the query computation tree into path query sequences by branches. This allows Pathformer to fully utilize future context information to explicitly model the complex interactions between various parts of a path query.
  arXiv  Detail & Related papers  (2024-06-21T06:02:58Z)
• Query2Particles: Knowledge Graph Reasoning with Particle Embeddings [49.64006979045662]
  We propose a query embedding method to answer complex logical queries on knowledge graphs with missing edges. The answer entities are selected according to the similarities between the entity embeddings and the query embedding. A complex KG query answering method, Q2P, is proposed to retrieve diverse answers from different areas over the embedding space.
  arXiv  Detail & Related papers  (2022-04-27T11:16:08Z)
• Graph Enhanced BERT for Query Understanding [55.90334539898102]
  query understanding plays a key role in exploring users' search intents and facilitating users to locate their most desired information. In recent years, pre-trained language models (PLMs) have advanced various natural language processing tasks. We propose a novel graph-enhanced pre-training framework, GE-BERT, which can leverage both query content and the query graph.
  arXiv  Detail & Related papers  (2022-04-03T16:50:30Z)
• Learning Query Expansion over the Nearest Neighbor Graph [94.80212602202518]
  Graph Query Expansion (GQE) is presented, which is learned in a supervised manner and performs aggregation over an extended neighborhood of the query. The technique achieves state-of-the-art results over known benchmarks.
  arXiv  Detail & Related papers  (2021-12-05T19:48:42Z)
• Query Embedding on Hyper-relational Knowledge Graphs [0.4779196219827507]
  Multi-hop logical reasoning is an established problem in the field of representation learning on knowledge graphs. We extend the multi-hop reasoning problem to hyper-relational KGs allowing to tackle this new type of complex queries.
  arXiv  Detail & Related papers  (2021-06-15T14:08:50Z)
• Bounded-Memory Criteria for Streams with Application Time [0.0]
  Bounded-memory computability continues to be in the focus of those areas of AI and databases that deal with feasible computations over streams. This work presents criteria for bounded-memory computability of select-project-join (SPJ) queries over streams with application time.
  arXiv  Detail & Related papers  (2020-07-30T12:05:04Z)
• Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings [84.0206612938464]
  query2box is an embedding-based framework for reasoning over arbitrary queries on incomplete knowledge graphs. We show that query2box is capable of handling arbitrary logical queries with $wedge$, $vee$, $exists$ in a scalable manner. We demonstrate the effectiveness of query2box on three large KGs and show that query2box achieves up to 25% relative improvement over the state of the art.
  arXiv  Detail & Related papers  (2020-02-14T11:20:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.