1 citations · 3 across the 14 of their papers we have counts for
15 papers
ZeroDSS: Semantic Segmentation from Class Names Alone
Tian Ming, Marzi Heidari, Yuhong Guo
Semantic segmentation depends heavily on real images with pixel-level annotations, making dense supervision a major obstacle to deployment in new domains. We study task-specific da…
Target-Oriented Single Domain Generalization
Marzi Heidari, Yuhong Guo
Deep models trained on a single source domain often fail catastrophically under distribution shifts, a critical challenge in Single Domain Generalization (SDG). While existing meth…
Zero-Shot Action Generalization with Limited Observations
Abdullah Alchihabi, Hanping Zhang, Yuhong Guo
Reinforcement Learning (RL) has demonstrated remarkable success in solving sequential decision-making problems. However, in real-world scenarios, RL agents often struggle to genera…
Single Domain Generalization with Adversarial Memory
Hao Yan, Marzi Heidari, Yuhong Guo
Domain Generalization (DG) aims to train models that can generalize to unseen testing domains by leveraging data from multiple training domains. However, traditional DG methods rel…
A Unified Framework for Heterogeneous Semi-supervised Learning
Marzi Heidari, Abdullah Alchihabi, Hao Yan +1
In this work, we introduce a novel problem setup termed as Heterogeneous Semi-Supervised Learning (HSSL), which presents unique challenges by bridging the semi-supervised learning…
Single Domain Generalization with Model-aware Parametric Batch-wise Mixup
Marzi Heidari, Yuhong Guo
Single Domain Generalization (SDG) remains a formidable challenge in the field of machine learning, particularly when models are deployed in environments that differ significantly…
Unbiased GNN Learning via Fairness-Aware Subgraph Diffusion
Abdullah Alchihabi, Yuhong Guo
Graph Neural Networks (GNNs) have demonstrated remarkable efficacy in tackling a wide array of graph-related tasks across diverse domains. However, a significant challenge lies in…
Overcoming Class Imbalance: Unified GNN Learning with Structural and Semantic Connectivity Representations
Abdullah Alchihabi, Hao Yan, Yuhong Guo
Class imbalance is pervasive in real-world graph datasets, where the majority of annotated nodes belong to a small set of classes (majority classes), leaving many other classes (mi…
Reinforcement Learning-Guided Semi-Supervised Learning
Marzi Heidari, Hanping Zhang, Yuhong Guo
In recent years, semi-supervised learning (SSL) has gained significant attention due to its ability to leverage both labeled and unlabeled data to improve model performance, especi…
Prompt-Driven Feature Diffusion for Open-World Semi-Supervised Learning
Marzi Heidari, Hanping Zhang, Yuhong Guo
In this paper, we present a novel approach termed Prompt-Driven Feature Diffusion (PDFD) within a semi-supervised learning framework for Open World Semi-Supervised Learning (OW-SSL…
Adaptive Weighted Co-Learning for Cross-Domain Few-Shot Learning
Abdullah Alchihabi, Marzi Heidari, Yuhong Guo
Due to the availability of only a few labeled instances for the novel target prediction task and the significant domain shift between the well annotated source domain and the targe…
Efficient Low-Rank GNN Defense Against Structural Attacks
Abdullah Alchihabi, Qing En, Yuhong Guo
Graph Neural Networks (GNNs) have been shown to possess strong representation abilities over graph data. However, GNNs are vulnerable to adversarial attacks, and even minor perturb…
GDM: Dual Mixup for Graph Classification with Limited Supervision
Abdullah Alchihabi, Yuhong Guo
Graph Neural Networks (GNNs) require a large number of labeled graph samples to obtain good performance on the graph classification task. The performance of GNNs degrades significa…
Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classification
Marzi Heidari, Abdullah Alchihabi, Qing En +1
Cross-domain few-shot classification induces a much more challenging problem than its in-domain counterpart due to the existence of domain shifts between the training and test task…
Dual GNNs: Graph Neural Network Learning with Limited Supervision
Abdullah Alchihabi, Yuhong Guo
Graph Neural Networks (GNNs) require a relatively large number of labeled nodes and a reliable/uncorrupted graph connectivity structure in order to obtain good performance on the s…