Related papers: Inductive Meta-path Learning for Schema-complex He…

Schema and data integration have been a challenge for more than 40 years. While data warehouse technologies are quite a success story, there is still a lack of information integration methods, especially if the data sources are based on…

A key assumption in multi-task learning is that at the inference time the multi-task model only has access to a given data point but not to the data point's labels from other tasks. This presents an opportunity to extend multi-task learning…

We introduce semi-parametric inducing point networks (SPIN), a general-purpose architecture that can query the training set at inference time in a compute-efficient manner. Semi-parametric architectures are typically more compact than…

The digitization of cultural heritage collections has opened new directions for research, yet the lack of enriched metadata poses a substantial challenge to accessibility, interoperability, and cross-institutional collaboration. In several…

This paper focuses on the data-insufficiency problem in multi-task learning within an episodic training setup. Specifically, we explore the potential of heterogeneous information across tasks and meta-knowledge among episodes to effectively…

Ensembles are popular methods for solving practical supervised learning problems. They reduce the risk of having underperforming models in production-grade software. Although critical, methods for learning heterogeneous regression ensembles…

The heterogeneous information network (HIN), which contains rich semantics depicted by meta-paths, has emerged as a potent tool for mitigating data sparsity in recommender systems. Existing HIN-based recommender systems operate under the…

Multi-layer networks are networks in which several protocols may coexist at different layers. The Pseudo-Wire architecture provides encapsulation and de-capsulation functions of protocols over Packet-Switched Networks. In a multi-domain…

Scene graph generation aims to produce structured representations for images, which requires to understand the relations between objects. Due to the continuous nature of deep neural networks, the prediction of scene graphs is divided into…

Over the past decade, deep neural networks have demonstrated significant success using the training scheme that involves mini-batch stochastic gradient descent on extensive datasets. Expanding upon this accomplishment, there has been a…

In-Context Learning (ICL) enables transformer-based language models to adapt to new tasks by conditioning on demonstration examples. However, traditional example-driven in-context learning lacks explicit modules for knowledge retrieval and…

Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed…

Many real-world problems are naturally modeled as heterogeneous graphs, where nodes and edges represent multiple types of entities and relations. Existing learning models for heterogeneous graph representation usually depend on the…

Recipe is a set of instructions that describes how to make food. It can help people from the preparation of ingredients, food cooking process, etc. to prepare the food, and increasingly in demand on the Web. To help users find the vast…

In this paper, we study network representation learning for tripartite heterogeneous networks which learns node representation features for networks with three types of node entities. We argue that tripartite networks are common in real…

Metamodeling refers to scenarios in ontologies in which classes and roles can be members of classes or occur in roles. This is a desirable modelling feature in several applications, but allowing it without restrictions is problematic for…

While deep learning has achieved phenomenal successes in many AI applications, its enormous model size and intensive computation requirements pose a formidable challenge to the deployment in resource-limited nodes. There has recently been…

Bi-type multi-relational heterogeneous graph (BMHG) is one of the most common graphs in practice, for example, academic networks, e-commerce user behavior graph and enterprise knowledge graph. It is a critical and challenge problem on how…

Expanding existing learning systems to provide high-quality customized models for more domains, such as new users, is challenged by the limited labeled data and the data and device heterogeneities. While knowledge distillation methods could…

Contrastive Learning (CL)-based recommender systems have gained prominence in the context of Heterogeneous Graph (HG) due to their capacity to enhance the consistency of representations across different views. However, existing frameworks…