42 citations · 148 across the 38 of their papers we have counts for
39 papers
Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation
Yifan Jin, Qirui Ji, Bin Qin +4
Graph foundation models (GFMs) emerged as a dominant paradigm in graph representation learning by leveraging large-scale pre-training for cross-domain inference. However, the param…
All-in-One Image Restoration via Causal-Deconfounding Wavelet-Disentangled Prompt Network
Bingnan Wang, Bin Qin, Jiangmeng Li +3
Image restoration represents a promising approach for addressing the inherent defects of image content distortion. Standard image restoration approaches suffer from high storage co…
HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning
Qirui Ji, Bin Qin, Yifan Jin +5
Graph contrastive learning (GCL) aims to learn discriminative semantic invariance by contrasting different views of the same graph that share critical topological patterns. However…
On the Transferability and Discriminability of Repersentation Learning in Unsupervised Domain Adaptation
Wenwen Qiang, Ziyin Gu, Lingyu Si +4
In this paper, we addressed the limitation of relying solely on distribution alignment and source-domain empirical risk minimization in Unsupervised Domain Adaptation (UDA). Our in…
On the Out-of-Distribution Generalization of Self-Supervised Learning
Wenwen Qiang, Jingyao Wang, Zeen Song +2
In this paper, we focus on the out-of-distribution (OOD) generalization of self-supervised learning (SSL). By analyzing the mini-batch construction during the SSL training phase, w…
Rethinking Multi-Modal Learning from Gradient Uncertainty
Peizheng Guo, Jingyao Wang, Wenwen Qiang +3
Multi-Modal Learning (MML) integrates information from diverse modalities to improve predictive accuracy. While existing optimization strategies have made significant strides by mi…
Beyond All-to-All: Causal-Aligned Transformer with Dynamic Structure Learning for Multivariate Time Series Forecasting
Xingyu Zhang, Hanyun Du, Zeen Song +3
Most existing multivariate time series forecasting methods adopt an all-to-all paradigm that feeds all variable histories into a unified model to predict their future values withou…
Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks
Shuang Cui, Yi Li, Jiangmeng Li +4
Single image defocus deblurring (SIDD) aims to restore an all-in-focus image from a defocused one. Distribution shifts in defocused images generally lead to performance degradation…
Rethinking the Bias of Foundation Model under Long-tailed Distribution
Jiahao Chen, Bin Qin, Jiangmeng Li +2
Long-tailed learning has garnered increasing attention due to its practical significance. Among the various approaches, the fine-tuning paradigm has gained considerable interest wi…
Rethinking Generalizability and Discriminability of Self-Supervised Learning from Evolutionary Game Theory Perspective
Jiangmeng Li, Zehua Zang, Qirui Ji +6
Representations learned by self-supervised approaches are generally considered to possess sufficient generalizability and discriminability. However, we disclose a nontrivial mutual…
Neuromodulated Meta-Learning
Jingyao Wang, Huijie Guo, Wenwen Qiang +4
Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological…
Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective
Yanan Zhang, Jiangmeng Li, Lixiang Liu +1
Foundational Vision-Language models such as CLIP have exhibited impressive generalization in downstream tasks. However, CLIP suffers from a two-level misalignment issue, i.e., task…
On the Generalization and Causal Explanation in Self-Supervised Learning
Wenwen Qiang, Zeen Song, Ziyin Gu +4
Self-supervised learning (SSL) methods learn from unlabeled data and achieve high generalization performance on downstream tasks. However, they may also suffer from overfitting to…
Rethinking Meta-Learning from a Learning Lens
Jingyao Wang, Wenwen Qiang, Changwen Zheng +2
Meta-learning seeks to learn a well-generalized model initialization from training tasks to solve unseen tasks. From the "learning to learn" perspective, the quality of the initial…
Towards the Causal Complete Cause of Multi-Modal Representation Learning
Jingyao Wang, Siyu Zhao, Wenwen Qiang +4
Multi-Modal Learning (MML) aims to learn effective representations across modalities for accurate predictions. Existing methods typically focus on modality consistency and specific…
Teleporter Theory: A General and Simple Approach for Modeling Cross-World Counterfactual Causality
Jiangmeng Li, Bin Qin, Qirui Ji +4
Leveraging the development of structural causal model (SCM), researchers can establish graphical models for exploring the causal mechanisms behind machine learning techniques. As t…
Revisiting Spurious Correlation in Domain Generalization
Bin Qin, Jiangmeng Li, Yi Li +4
Without loss of generality, existing machine learning techniques may learn spurious correlation dependent on the domain, which exacerbates the generalization of models in out-of-di…
Interventional Imbalanced Multi-Modal Representation Learning via -Generalization Front-Door Criterion
Yi Li, Fei Song, Changwen Zheng +3
Multi-modal methods establish comprehensive superiority over uni-modal methods. However, the imbalanced contributions of different modalities to task-dependent predictions constant…
Learning Invariant Causal Mechanism from Vision-Language Models
Zeen Song, Siyu Zhao, Xingyu Zhang +3
Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, but its performance can degrade when fine-tuned in out-of-distribution (OOD) scenarios. We model the…
On the Universality of Self-Supervised Learning
Wenwen Qiang, Jingyao Wang, Changwen Zheng +2
In this paper, we investigate what constitutes a good representation or model in self-supervised learning (SSL). We argue that a good representation should exhibit universality, ch…
Graph Partial Label Learning with Potential Cause Discovering
Hang Gao, Jiaguo Yuan, Jiangmeng Li +4
Graph Neural Networks (GNNs) have garnered widespread attention for their potential to address the challenges posed by graph representation learning, which face complex graph-struc…
BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction
Jiangmeng Li, Fei Song, Yifan Jin +4
As a novel and effective fine-tuning paradigm based on large-scale pre-trained language models (PLMs), prompt-tuning aims to reduce the gap between downstream tasks and pre-trainin…
Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning
Jiangmeng Li, Yifan Jin, Hang Gao +3
Graph contrastive learning (GCL) aims to align the positive features while differentiating the negative features in the latent space by minimizing a pair-wise contrastive loss. As…
Rethinking Causal Relationships Learning in Graph Neural Networks
Hang Gao, Chengyu Yao, Jiangmeng Li +5
Graph Neural Networks (GNNs) demonstrate their significance by effectively modeling complex interrelationships within graph-structured data. To enhance the credibility and robustne…