Related papers: SeDyT: A General Framework for Multi-Step Event Fo…

Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing…

Given the inherent class imbalance issue within student performance datasets, samples belonging to the edges of the target class distribution pose a challenge for predictive machine learning algorithms to learn. In this paper, we introduce…

How can we effectively encode evolving information over dynamic graphs into low-dimensional representations? In this paper, we propose DyRep, an inductive deep representation learning framework that learns a set of functions to efficiently…

Knowledge graphs (KGs) have been increasingly employed for link prediction and recommendation using real-world datasets. However, the majority of current methods rely on static data, neglecting the dynamic nature and the hidden…

Multi-modal entity alignment aims to identify equivalent entities between two multi-modal Knowledge graphs by integrating multi-modal data, such as images and text, to enrich the semantic representations of entities. However, existing…

Embedding learning, a.k.a. representation learning, has been shown to be able to model large-scale semantic knowledge graphs. A key concept is a mapping of the knowledge graph to a tensor representation whose entries are predicted by models…

Event detection refers to identifying event occurrences in a text and comprises of two subtasks; event identification and classification. We present EDM3, a novel approach for Event Detection that formulates three generative tasks:…

Session-based recommendation plays a central role in a wide spectrum of online applications, ranging from e-commerce to online advertising services. However, the majority of existing session-based recommendation techniques (e.g.,…

Entity alignment aims to use pre-aligned seed pairs to find other equivalent entities from different knowledge graphs (KGs) and is widely used in graph fusion-related fields. However, as the scale of KGs increases, manually annotating…

Temporal event data are collected across a broad range of domains, and a variety of visual analytics techniques have been developed to empower analysts working with this form of data. These techniques generally display aggregate statistics…

Fine-tuning MLLMs for Video Temporal Grounding (VTG) often improves in-domain performance but degrades sharply under domain shift. In this work, we find that this failure is primarily driven not just by unseen query concepts, but by visual…

We introduce the Temporal Contrastive Transformer (TCT), a representation learning framework designed to capture contextual temporal dynamics in sequences of financial transactions. The model is trained using a self-supervised contrastive…

To improve the performance of long text generation, recent studies have leveraged automatically planned event structures (i.e. storylines) to guide story generation. Such prior works mostly employ end-to-end neural generation models to…

Representation learning on temporal interaction graphs (TIG) is to model complex networks with the dynamic evolution of interactions arising in a broad spectrum of problems. Existing dynamic embedding methods on TIG discretely update node…

In incremental learning, enhancing the generality of knowledge is crucial for adapting to dynamic data inputs. It can develop generalized representations or more balanced decision boundaries, preventing the degradation of long-term…

Dynamic Text-Attributed Graphs (DyTAGs) are a novel graph paradigm that captures evolving temporal events (edges) alongside rich textual attributes. Existing studies can be broadly categorized into TGNN-driven and LLM-driven approaches,…

Models of narrative schema knowledge have proven useful for a range of event-related tasks, but they typically do not capture the temporal relationships between events. We propose a single model that addresses both temporal ordering,…

Temporal heterogeneous networks (THNs) are evolving networks that characterize many real-world applications such as citation and events networks, recommender systems, and knowledge graphs. Although different Graph Neural Networks (GNNs)…

Event analysis from news and social networks is very useful for a wide range of social studies and real-world applications. Recently, event graphs have been explored to model event datasets and their complex relationships, where events are…

Entity Resolution (ER) is a constitutional part for integrating different knowledge graphs in order to identify entities referring to the same real-world object. A promising approach is the use of graph embeddings for ER in order to…