Related papers: Improving the recall of decentralised linked data …

Large language models (LLMs) sometimes memorize undesirable knowledge, which must be removed after deployment. Prior work on machine unlearning has focused largely on optimization methods that adjust parameters to enforce forgetting while…

Machine unlearning techniques aim to mitigate unintended memorization in large language models (LLMs). However, existing approaches predominantly focus on the explicit removal of isolated facts, often overlooking latent inferential…

Over the last decades the Web has evolved from a human-human communication network to a network of complex human-machine interactions. An increasing amount of data is available as Linked Data which allows machines to "understand" the data,…

Side information fusion for sequential recommendation (SR) aims to effectively leverage various side information to enhance the performance of next-item prediction. Most state-of-the-art methods build on self-attention networks and focus on…

Offline reinforcement learning (RL) is challenged by the distributional shift between learning policies and datasets. To address this problem, existing works mainly focus on designing sophisticated algorithms to explicitly or implicitly…

The combination of the flexibility of RDF and the expressiveness of SPARQL provides a powerful mechanism to model, integrate and query data. However, these properties also mean that it is nontrivial to write performant SPARQL queries.…

Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, particularly when augmented with search mechanisms that enable systematic exploration of external knowledge bases. The field has evolved from…

With recent emerging technologies such as the Internet of Things (IoT), information collection on our physical world and environment can be achieved at a much higher granularity and such detailed knowledge will play a critical role in…

The number of linked data sources and the size of the linked open data graph keep growing every day. As a consequence, semantic RDF services are more and more confronted with various "big data" problems. Query processing in the presence of…

Word embeddings are vital descriptors of words in unigram representations of documents for many tasks in natural language processing and information retrieval. The representation of queries has been one of the most critical challenges in…

Although SPARQL has been the predominant query language over RDF graphs, some query intentions cannot be well captured by only using SPARQL syntax. On the other hand, the keyword search enjoys widespread usage because of its intuitive way…

While the Web of Data in principle offers access to a wide range of interlinked data, the architecture of the Semantic Web today relies mostly on the data providers to maintain access to their data through SPARQL endpoints. Several studies,…

Solutions to the classic problems of dealing with heterogeneous data and making entire collections interoperable while ensuring that any annotation, which includes the recognition-and-reward system of scientific publishing, need to fit into…

In deductive domains, three metacognitive knowledge types in ascending order are declarative, procedural, and conditional learning. This work leverages Deep Reinforcement Learning (DRL) in providing adaptive metacognitive interventions to…

First-order knowledge compilation techniques have proven efficient for lifted inference. They compile a relational probability model into a target circuit on which many inference queries can be answered efficiently. Early methods used data…

Evaluating and optimizing policies in the presence of unobserved confounders is a problem of growing interest in offline reinforcement learning. Using conventional methods for offline RL in the presence of confounding can not only lead to…

Large Language Models (LLMs) are adept at generating responses based on information within their context. While this ability is useful for interacting with structured data like code files, another popular method, Retrieval-Augmented…

Optimizing the trade-off among predictive performance and computational cost is a central focus in the deployment of Large Language Models (LLMs). Current routing methods primarily rely on direct mapping from queries to models based on…

The ubiquity of implicit feedback makes them the default choice to build modern recommender systems. Generally speaking, observed interactions are considered as positive samples, while unobserved interactions are considered as negative…

Carefully selected materialized views can greatly improve the performance of OLAP workloads. We study using deep reinforcement learning to learn adaptive view materialization and eviction policies. Our insight is that such selection…