Yu Zheng

Recurrent Dirichlet Belief Networks for Interpretable Dynamic Relational Data Modelling

2020 · arXiv (Cornell University)

The Dirichlet Belief Network~(DirBN) has been recently proposed as a promising approach in learning interpretable deep latent representations for objects. In this work, we leverage its interpretable modelling architecture and propose a deep dynamic probabilistic …

Poformer: A simple pooling transformer for speaker verification

2021 · arXiv (Cornell University)

Most recent speaker verification systems are based on extracting speaker embeddings using a deep neural network. The pooling layer in the network aims to aggregate frame-level features extracted by the backbone. In this paper, we …

Gaussian conversion protocol for heralded generation of generalized Gottesman-Kitaev-Preskill states

2023 · Physical Review A

In the field of fault-tolerant quantum computing, continuous-variable systems can be utilized to protect quantum information from noise through the use of bosonic codes. These codes map qubit-type quantum information onto the larger bosonic Hilbert …

Mixed Attention Network for Cross-domain Sequential Recommendation

2023 · arXiv (Cornell University)

In modern recommender systems, sequential recommendation leverages chronological user behaviors to make effective next-item suggestions, which suffers from data sparsity issues, especially for new users. One promising line of work is the cross-domain recommendation, which …

Probing Neural Topology of Large Language Models

2025 · arXiv (Cornell University)

Probing large language models (LLMs) has yielded valuable insights into their internal mechanisms by linking neural activations to interpretable semantics. However, the complex mechanisms that link neuron's functional co-activation with the emergent model capabilities remains …

Disentangling User Interest and Conformity for Recommendation with Causal Embedding

2021

Recommendation models are usually trained on observational interaction data. However, observational interaction data could result from users’ conformity towards popular items, which entangles users’ real interest. Existing methods tracks this problem as eliminating popularity bias, …

Sequential Recommendation with Graph Neural Networks

2021

Sequential recommendation aims to leverage users' historical behaviors to predict their next interaction. Existing works have not yet addressed two main challenges in sequential recommendation. First, user behaviors in their rich historical sequences are often …

Disentangling Long and Short-Term Interests for Recommendation

2022 · Proceedings of the ACM Web Conference 2022

Modeling user’s long-term and short-term interests is crucial for accurate recommendation. However, since there is no manually annotated label for user interests, existing approaches always follow the paradigm of entangling these two aspects, which may …

A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions

2023 · ACM Transactions on Recommender Systems

Recommender system is one of the most important information services on today’s Internet. Recently, graph neural networks have become the new state-of-the-art approach to recommender systems. In this survey, we conduct a comprehensive review of …