Related papers: Factual and Edit-Sensitive Graph-to-Sequence Gener…

Graph Neural Networks (GNNs) are proficient in graph representation learning and achieve promising performance on versatile tasks such as node classification and link prediction. Usually, a comprehensive hyperparameter tuning is essential…

In the text-to-image generation field, recent remarkable progress in Stable Diffusion makes it possible to generate rich kinds of novel photorealistic images. However, current models still face misalignment issues (e.g., problematic spatial…

Graph generative models have been extensively studied in the data mining literature. While traditional techniques are based on generating structures that adhere to a pre-decided distribution, recent techniques have shifted towards learning…

Graph-structured data is prevalent in the real world. Recently, due to the powerful emergent capabilities, Large Language Models (LLMs) have shown promising performance in modeling graphs. The key to effectively applying LLMs on graphs is…

Masked diffusion language models enable parallel token generation and offer improved decoding efficiency over autoregressive models. However, their performance degrades significantly when generating multiple tokens simultaneously, due to a…

Recently, diffusion models have emerged as a new paradigm for generative models. Despite the success in domains using continuous signals such as vision and audio, adapting diffusion models to natural language is under-explored due to the…

The widespread deployment of Graph Neural Networks (GNNs) sparks significant interest in their explainability, which plays a vital role in model auditing and ensuring trustworthy graph learning. The objective of GNN explainability is to…

Cognitive diagnostics in the Web-based Intelligent Education System (WIES) aims to assess students' mastery of knowledge concepts from heterogeneous, noisy interactions. Recent work has tried to utilize Large Language Models (LLMs) for…

Large-scale pre-trained language models (PLMs) have advanced Graph-to-Text (G2T) generation by processing the linearised version of a graph. However, the linearisation is known to ignore the structural information. Additionally, PLMs are…

Although neural text-to-speech (TTS) models have attracted a lot of attention and succeeded in generating human-like speech, there is still room for improvements to its naturalness and architectural efficiency. In this work, we propose a…

This work introduces DiGress, a discrete denoising diffusion model for generating graphs with categorical node and edge attributes. Our model utilizes a discrete diffusion process that progressively edits graphs with noise, through the…

Text-attributed graphs have recently garnered significant attention due to their wide range of applications in web domains. Existing methodologies employ word embedding models for acquiring text representations as node features, which are…

Graph-based collaborative filtering has been established as a prominent approach in recommendation systems, leveraging the inherent graph topology of user-item interactions to model high-order connectivity patterns and enhance…

Graph representation learning, involving both node features and graph structures, is crucial for real-world applications but often encounters pervasive noise. State-of-the-art methods typically address noise by focusing separately on node…

Vision-Language Models (VLMs) generate discourse-level, multi-sentence visual descriptions, challenging text scene graph parsers built for single-sentence caption-to-graph mapping. Current approaches typically merge sentence-level parsing…

Over recent years, denoising diffusion generative models have come to be considered as state-of-the-art methods for synthetic data generation, especially in the case of generating images. These approaches have also proved successful in…

Dynamic Text-Attributed Graphs (DyTAGs) have numerous real-world applications, e.g. social, collaboration, citation, communication, and review networks. In these networks, nodes and edges often contain text descriptions, and the graph…

Novel diffusion models can synthesize photo-realistic images with integrated high-quality text. Surprisingly, we demonstrate through attention activation patching that only less than $1$% of diffusion models' parameters, all contained in…

Autoregressive large language models achieve strong results on many benchmarks, but decoding remains fundamentally latency-limited by sequential dependence on previously generated tokens. Diffusion language models (DLMs) promise parallel…

Temporal Graph Networks (TGNs) have shown remarkable performance in learning representation for continuous-time dynamic graphs. However, real-world dynamic graphs typically contain diverse and intricate noise. Noise can significantly…