1 citations · 4 across the 14 of their papers we have counts for
15 papers
Regularizing modality contribution drift in multimodal continual learning
Zhen Zhang, Jielei Chu, Bin Liu +5
Multimodal continual learning (MMCL) aims to acquire new knowledge from multimodal data while retaining previously learned knowledge. Existing MMCL methods primarily mitigate forge…
Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement
Jiaqing Chen, Zidu Yin, Yichao Cai +4
Graph neural networks (GNNs) excel at aggregating neighbor information for classification, yet their performance is hindered by graph structural entanglement, where spurious correl…
Causally Sufficient and Necessary Feature Expansion for Class-Incremental Learning
Zhen Zhang, Jielei Chu, Jiangtao Hu +4
Current expansion-based methods for Class Incremental Learning (CIL) effectively mitigate catastrophic forgetting by freezing old features. However, such task-specific features lea…
The Geometric Mechanics of Contrastive Representation Learning: Alignment Potentials, Entropic Dispersion, and Cross-modal Divergence
Yichao Cai, Zhen Zhang, Yuhang Liu +1
While InfoNCE underlies modern contrastive learning, its geometric mechanisms remain under-characterized beyond the canonical alignment--uniformity decomposition. We develop a meas…
Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning
Tianjiao Jiang, Zhen Zhang, Yuhang Liu +1
Few-shot learning (FSL) often requires effective adaptation of models using limited labeled data. However, most existing FSL methods rely on entangled representations, requiring th…
On the Value of Cross-Modal Misalignment in Multimodal Representation Learning
Yichao Cai, Yuhang Liu, Erdun Gao +4
Multimodal representation learning, exemplified by multimodal contrastive learning (MMCL) using image-text pairs, aims to learn powerful representations by aligning cues across mod…
Analytic DAG Constraints for Differentiable DAG Learning
Zhen Zhang, Ignavier Ng, Dong Gong +6
Recovering the underlying Directed Acyclic Graph (DAG) structures from observational data presents a formidable challenge, partly due to the combinatorial nature of the DAG-constra…
I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?
Yuhang Liu, Dong Gong, Yichao Cai +6
Recent empirical evidence shows that LLM representations encode human-interpretable concepts. Nevertheless, the mechanisms by which these representations emerge remain largely unex…
InvariantStock: Learning Invariant Features for Mastering the Shifting Market
Haiyao Cao, Jinan Zou, Yuhang Liu +4
Accurately predicting stock returns is crucial for effective portfolio management. However, existing methods often overlook a fundamental issue in the market, namely, distribution…
Rethinking State Disentanglement in Causal Reinforcement Learning
Haiyao Cao, Zhen Zhang, Panpan Cai +7
One of the significant challenges in reinforcement learning (RL) when dealing with noise is estimating latent states from observations. Causality provides rigorous theoretical supp…
Highway Graph to Accelerate Reinforcement Learning
Zidu Yin, Zhen Zhang, Dong Gong +2
Reinforcement Learning (RL) algorithms often struggle with low training efficiency. A common approach to address this challenge is integrating model-based planning algorithms, such…
Towards Identifiable Latent Additive Noise Models
Yuhang Liu, Zhen Zhang, Dong Gong +6
Causal representation learning (CRL) offers the promise of uncovering the underlying causal model by which observed data was generated, but the practical applicability of existing…
Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning
Yuhang Liu, Zhen Zhang, Dong Gong +6
Directed Acyclic Graphs (DAGs) are a standard tool in causal modeling, but their suitability for capturing the complexity of large-scale multimodal data is questionable. In practic…
CLAP: Isolating Content from Style through Contrastive Learning with Augmented Prompts
Yichao Cai, Yuhang Liu, Zhen Zhang +1
Contrastive vision-language models, such as CLIP, have garnered considerable attention for various downstream tasks, mainly due to the remarkable ability of the learned features fo…
Identifiable Latent Polynomial Causal Models Through the Lens of Change
Yuhang Liu, Zhen Zhang, Dong Gong +5
Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of id…