8 papers
Temporal Heterogeneous Graph Pretraining for Relational Deep Learning
Yixin Peng, Er Jin, Diego Collarana +1
Relational deep learning models database rows and foreign-key links as a heterogeneous graph for prediction from record attributes and relational context. These graphs contain two…
VisKG-LM: Compiling Knowledge Graphs into Visual Memory for Multiple-Choice Question Answering
Yixin Peng, Er Jin, Shiwei Luo +2
Knowledge graphs are usually integrated into question answering by encoding a retrieved subgraph with a graph neural network and fusing it with the language model in the online inf…
THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model
Yixin Peng, Diego Collarana, Er Jin +1
Temporal heterogeneous graphs offer a natural abstraction for dynamic relational systems in which diverse node and relation types co-exist and evolve over time. Learning on such gr…
Unconsciously Forget: Mitigating Memorization; Without Knowing What is being Memorized
Er Jin, Yang Zhang, Yongli Mou +4
Recent advances in generative models have demonstrated an exceptional ability to produce highly realistic images. However, previous studies show that generated images often resembl…
Segment Anything for Cell Tracking
Zhu Chen, Mert Edgü, Er Jin +1
Tracking cells and detecting mitotic events in time-lapse microscopy image sequences is a crucial task in biomedical research. However, it remains highly challenging due to dividin…
Minimalist Concept Erasure in Generative Models
Yang Zhang, Er Jin, Yanfei Dong +5
Recent advances in generative models have demonstrated remarkable capabilities in producing high-quality images, but their reliance on large-scale unlabeled data has raised signifi…
LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction
Er Jin, Qihui Feng, Yongli Mou +4
Logical image understanding involves interpreting and reasoning about the relationships and consistency within an image's visual content. This capability is essential in applicatio…
Learnable Sparsity for Vision Generative Models
Yang Zhang, Er Jin, Wenzhong Liang +5
Diffusion models have achieved impressive advancements in various vision tasks. However, these gains often rely on increasing model size, which escalates computational complexity a…