81 citations · 127 across the 22 of their papers we have counts for
24 papers
Backpropagating Verifier Rewards Through Continuous Flow Language Models
Xu Han, Jiajing Hu, Li-Ping Liu
Reinforcement learning (RL) has substantially improved the reasoning of autoregressive and discrete-diffusion language models. Language models that generate continuous token embedd…
Deterministic Prediction as Global Velocity: Flow Matching for Probabilistic Time-Series Forecast
Jiajing Hu, Xu Han, Li-Ping Liu
Accurate uncertainty quantification is critical for many time series forecasting applications, and recent studies have increasingly adopted generative models to capture predictive…
Self-Consistent Flow: Unifying Velocity and Endpoint Prediction for Rectified Flow Models
Xu Han, Jiajing Hu, Li-Ping Liu
In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint, to perform d…
On Separate Normalization in Self-supervised Transformers
Xiaohui Chen, Yinkai Wang, Yuanqi Du +2
Self-supervised training methods for transformers have demonstrated remarkable performance across various domains. Previous transformer-based models, such as masked autoencoders (M…
Graph-Based Model-Agnostic Data Subsampling for Recommendation Systems
Xiaohui Chen, Jiankai Sun, Taiqing Wang +3
Data subsampling is widely used to speed up the training of large-scale recommendation systems. Most subsampling methods are model-based and often require a pre-trained pilot model…
Kriging Convolutional Networks
Gabriel Appleby, Linfeng Liu, Li-Ping Liu
Spatial interpolation is a class of estimation problems where locations with known values are used to estimate values at other locations, with an emphasis on harnessing spatial loc…
Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling
Xiaohui Chen, Jiaxing He, Xu Han +1
Diffusion-based generative graph models have been proven effective in generating high-quality small graphs. However, they need to be more scalable for generating large graphs conta…
Interpretable Node Representation with Attribute Decoding
Xiaohui Chen, Xi Chen, Liping Liu
Variational Graph Autoencoders (VGAEs) are powerful models for unsupervised learning of node representations from graph data. In this work, we systematically analyze modeling node…
PatchGT: Transformer over Non-trainable Clusters for Learning Graph Representations
Han Gao, Xu Han, Jiaoyang Huang +2
Recently the Transformer structure has shown good performances in graph learning tasks. However, these Transformer models directly work on graph nodes and may have difficulties lea…
NVDiff: Graph Generation through the Diffusion of Node Vectors
Xiaohui Chen, Yukun Li, Aonan Zhang +1
Learning to generate graphs is challenging as a graph is a set of pairwise connected, unordered nodes encoding complex combinatorial structures. Recently, several works have propos…
Towards Accurate Subgraph Similarity Computation via Neural Graph Pruning
Linfeng Liu, Xu Han, Dawei Zhou +1
Subgraph similarity search, one of the core problems in graph search, concerns whether a target graph approximately contains a query graph. The problem is recently touched by neura…
Ensemble Spectral Prediction (ESP) Model for Metabolite Annotation
Xinmeng Li, Hao Zhu, Li-ping Liu +1
A key challenge in metabolomics is annotating measured spectra from a biological sample with chemical identities. Currently, only a small fraction of measurements can be assigned i…
Predicting Physics in Mesh-reduced Space with Temporal Attention
Xu Han, Han Gao, Tobias Pfaff +2
Graph-based next-step prediction models have recently been very successful in modeling complex high-dimensional physical systems on irregular meshes. However, due to their short te…
Boost-RS: Boosted Embeddings for Recommender Systems and its Application to Enzyme-Substrate Interaction Prediction
Xinmeng Li, Li-ping Liu, Soha Hassoun
Despite experimental and curation efforts, the extent of enzyme promiscuity on substrates continues to be largely unexplored and under documented. Recommender systems (RS), which a…
Ladder Polynomial Neural Networks
Li-Ping Liu, Ruiyuan Gu, Xiaozhe Hu
Polynomial functions have plenty of useful analytical properties, but they are rarely used as learning models because their function class is considered to be restricted. This work…
Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation
Xiaohui Chen, Xu Han, Jiajing Hu +2
A graph generative model defines a distribution over graphs. One type of generative model is constructed by autoregressive neural networks, which sequentially add nodes and edges t…
Stochastic Iterative Graph Matching
Linfeng Liu, Michael C. Hughes, Soha Hassoun +1
Recent works leveraging Graph Neural Networks to approach graph matching tasks have shown promising results. Recent progress in learning discrete distributions poses new opportunit…
DiaKG: an Annotated Diabetes Dataset for Medical Knowledge Graph Construction
Dejie Chang, Mosha Chen, Chaozhen Liu +9
Knowledge Graph has been proven effective in modeling structured information and conceptual knowledge, especially in the medical domain. However, the lack of high-quality annotated…
Modeling Graph Node Correlations with Neighbor Mixture Models
Linfeng Liu, Michael C. Hughes, Li-Ping Liu
We propose a new model, the Neighbor Mixture Model (NMM), for modeling node labels in a graph. This model aims to capture correlations between the labels of nodes in a local neighb…
GAN Ensemble for Anomaly Detection
Xu Han, Xiaohui Chen, Li-Ping Liu
When formulated as an unsupervised learning problem, anomaly detection often requires a model to learn the distribution of normal data. Previous works apply Generative Adversarial…
Using Graph Neural Networks for Mass Spectrometry Prediction
Hao Zhu, Liping Liu, Soha Hassoun
Detecting and quantifying products of cellular metabolism using Mass Spectrometry (MS) has already shown great promise in many biological and biomedical applications. The biggest c…
Learning graph representations of biochemical networks and its application to enzymatic link prediction
Julie Jiang, Li-Ping Liu, Soha Hassoun
The complete characterization of enzymatic activities between molecules remains incomplete, hindering biological engineering and limiting biological discovery. We develop in this w…
Pathway-Activity Likelihood Analysis and Metabolite Annotation for Untargeted Metabolomics using Probabilistic Modeling
Ramtin Hosseini, Neda Hassanpour, Li-Ping Liu +1
Motivation: Untargeted metabolomics comprehensively characterizes small molecules and elucidates activities of biochemical pathways within a biological sample. Despite computationa…
Non-Parametric Variational Inference with Graph Convolutional Networks for Gaussian Processes
Linfeng Liu, Liping Liu
Inference for GP models with non-Gaussian noises is computationally expensive when dealing with large datasets. Many recent inference methods approximate the posterior distribution…