Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Sampling
该研究通过多哈希用户嵌入和时间邻居采样方法，解决了在大规模社交图上部署图神经网络进行好友推荐的问题。
0 citationsRead paper
Selected work
Representative Papers
Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction
该研究针对短视频观看时长分布预测问题，提出了一种分层指数-高斯混合模型(HEGM)，通过改进EGMN存在的方差崩溃、组件冗余等问题，提高了预测准确性及稳定性。
0 citationsRead paper
VARAN: Variational Inference for Self-Supervised Speech Models Fine-Tuning on Downstream Tasks
In conventional fine-tuning of self-supervised speech models, fixed-layer aggregation—such as using only the top layer or static weighted summation—introduces an information bottleneck and limits cross-sample generalization. To address this, we propose VARAN, a novel framework featuring input-adaptive dynamic layer aggregation. VARAN employs layer-specific probe heads and data-dependent weights to dynamically allocate contributions from different transformer layers per sample, thereby preserving layer-specific characteristics while enhancing representational flexibility. The aggregation process is optimized via variational inference, and VARAN integrates LoRA for parameter-efficient fine-tuning. Evaluated on automatic speech recognition and speech emotion recognition tasks, VARAN consistently outperforms strong baselines; its combination with LoRA yields particularly substantial gains. These results demonstrate VARAN’s superior downstream adaptability and robust generalization capability across diverse speech understanding tasks.
0 citationsRead paper
Recent publications
Latest Papers
Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Sampling
该研究通过多哈希用户嵌入和时间邻居采样方法，解决了在大规模社交图上部署图神经网络进行好友推荐的问题。
0 citationsRead paper
Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction
该研究针对短视频观看时长分布预测问题，提出了一种分层指数-高斯混合模型(HEGM)，通过改进EGMN存在的方差崩溃、组件冗余等问题，提高了预测准确性及稳定性。
0 citationsRead paper
VARAN: Variational Inference for Self-Supervised Speech Models Fine-Tuning on Downstream Tasks
In conventional fine-tuning of self-supervised speech models, fixed-layer aggregation—such as using only the top layer or static weighted summation—introduces an information bottleneck and limits cross-sample generalization. To address this, we propose VARAN, a novel framework featuring input-adaptive dynamic layer aggregation. VARAN employs layer-specific probe heads and data-dependent weights to dynamically allocate contributions from different transformer layers per sample, thereby preserving layer-specific characteristics while enhancing representational flexibility. The aggregation process is optimized via variational inference, and VARAN integrates LoRA for parameter-efficient fine-tuning. Evaluated on automatic speech recognition and speech emotion recognition tasks, VARAN consistently outperforms strong baselines; its combination with LoRA yields particularly substantial gains. These results demonstrate VARAN’s superior downstream adaptability and robust generalization capability across diverse speech understanding tasks.
0 citationsRead paper