409 citations · 677 across the 54 of their papers we have counts for
10 papers · 1 filter
Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration
Wenju Sun, Qingyong Li, Wen Wang +3
Multi-task model merging aims to consolidate knowledge from multiple fine-tuned task-specific experts into a unified model while minimizing performance degradation. Existing method…
Improving Generalization of Neural Vehicle Routing Problem Solvers Through the Lens of Model Architecture
Yubin Xiao, Di Wang, Xuan Wu +5
Neural models produce promising results when solving Vehicle Routing Problems (VRPs), but often fall short in generalization. Recent attempts to enhance model generalization often…
Distilling Autoregressive Models to Obtain High-Performance Non-Autoregressive Solvers for Vehicle Routing Problems with Faster Inference Speed
Yubin Xiao, Di Wang, Boyang Li +4
Neural construction models have shown promising performance for Vehicle Routing Problems (VRPs) by adopting either the Autoregressive (AR) or Non-Autoregressive (NAR) learning appr…
Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering
Chang Liu, Han Yu, Boyang Li +6
Noisy labels are commonly found in real-world data, which cause performance degradation of deep neural networks. Cleaning data manually is labour-intensive and time-consuming. Prev…
Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection
Xu Guo, Boyang Li, Han Yu +1
The existence of multiple datasets for sarcasm detection prompts us to apply transfer learning to exploit their commonality. The adversarial neural transfer (ANT) framework utilize…
HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks
Yuanyuan Chen, Boyang Li, Han Yu +2
The behaviors of deep neural networks (DNNs) are notoriously resistant to human interpretations. In this paper, we propose Hypergradient Data Relevance Analysis, or HYDRA, which in…
Searching for Stage-wise Neural Graphs In the Limit
Xin Zhou, Dejing Dou, Boyang Li
Search space is a key consideration for neural architecture search. Recently, Xie et al. (2019) found that randomly generated networks from the same distribution perform similarly,…
An Empirical Study on the Relation between Network Interpretability and Adversarial Robustness
Adam Noack, Isaac Ahern, Dejing Dou +1
Deep neural networks (DNNs) have had many successes, but they suffer from two major issues: (1) a vulnerability to adversarial examples and (2) a tendency to elude human interpreta…
NormLime: A New Feature Importance Metric for Explaining Deep Neural Networks
Isaac Ahern, Adam Noack, Luis Guzman-Nateras +3
The problem of explaining deep learning models, and model predictions generally, has attracted intensive interest recently. Many successful approaches forgo global approximations i…
A Multi-task Neural Approach for Emotion Attribution, Classification and Summarization
Guoyun Tu, Yanwei Fu, Boyang Li +3
Emotional content is a crucial ingredient in user-generated videos. However, the sparsity of emotional expressions in the videos poses an obstacle to visual emotion analysis. In th…