Search Results for author:
Found 20 papers, 15 papers with code
Inference over Unseen Entities, Relations and Literals on Knowledge Graphs
We propose the attentive byte-pair encoding layer (BytE) to construct a triple embedding from a sequence of byte-pair encoded subword units of entities and relations.
Embedding Knowledge Graph in Function Spaces
We introduce a novel embedding method diverging from conventional approaches by operating within function spaces of finite dimension rather than finite vector space, thus departing significantly from standard knowledge graph embedding techniques.
Performance Evaluation of Knowledge Graph Embedding Approaches under Non-adversarial Attacks
We close this gap by evaluating the impact of non-adversarial attacks on the performance of 5 state-of-the-art KGE algorithms on 5 datasets with respect to attacks on 3 attack surfaces-graph, parameter, and label perturbation.
Adaptive Stochastic Weight Averaging
Despite its potential benefits, maintaining a running average of parameters can hinder generalization, as an underlying running model begins to overfit.
Embedding Knowledge Graphs in Degenerate Clifford Algebras
We propose to consider nilpotent base vectors with a nilpotency index of two.
Universal Knowledge Graph Embeddings
Most of them obtain embeddings by learning the structure of the knowledge graph within a link prediction setting.
LitCQD: Multi-Hop Reasoning in Incomplete Knowledge Graphs with Numeric Literals
We evaluate LitCQD on query types with and without literal values.
Learning Permutation-Invariant Embeddings for Description Logic Concepts
We reformulate the learning problem as a multi-label classification problem and propose a neural embedding model (NERO) that learns permutation-invariant embeddings for sets of examples tailored towards predicting $F_1$ scores of pre-selected description logic concepts.
Hardware-agnostic Computation for Large-scale Knowledge Graph Embeddings
Knowledge graph embedding research has mainly focused on learning continuous representations of knowledge graphs towards the link prediction problem.
Conformal Credal Self-Supervised Learning
One such method, so-called credal self-supervised learning, maintains pseudo-supervision in the form of sets of (instead of single) probability distributions over labels, thereby allowing for a flexible yet uncertainty-aware labeling.
Kronecker Decomposition for Knowledge Graph Embeddings
Our experiments suggest that applying Kronecker decomposition on embedding matrices leads to an improved parameter efficiency on all benchmark datasets.
Neural Class Expression Synthesis
In this paper, we cast class expression learning as a translation problem and propose a new family of class expression learning approaches which we dub neural class expression synthesizers.
EvoLearner: Learning Description Logics with Evolutionary Algorithms
We contribute a novel initialization method for the initial population: starting from positive examples, we perform biased random walks and translate them to description logic concepts.
Learning Concept Lengths Accelerates Concept Learning in ALC
We then extend the CELOE algorithm, which learns ALC concepts, with our concept length predictor.
DRILL-- Deep Reinforcement Learning for Refinement Operators in $\mathcal{ALC}$
In this work, we leverage deep reinforcement learning to accelerate the learning of concepts in $\mathcal{ALC}$ by proposing DRILL -- a novel class expression learning approach that uses a convolutional deep Q-learning model to steer its search.
Convolutional Hypercomplex Embeddings for Link Prediction
We propose the four approaches QMult, OMult, ConvQ and ConvO to tackle the link prediction problem.
Out-of-Vocabulary Entities in Link Prediction
As benchmarks are crucial for the fair comparison of algorithms, ensuring their quality is tantamount to providing a solid ground for developing better solutions to link prediction and ipso facto embedding knowledge graphs.
A shallow neural model for relation prediction
We predict missing triples via the relation prediction.
Convolutional Complex Knowledge Graph Embeddings
In this paper, we study the problem of learning continuous vector representations of knowledge graphs for predicting missing links.
A Physical Embedding Model for Knowledge Graphs
We present a novel and scalable paradigm for the computation of knowledge graph embeddings, which we dub PYKE .
