Author name cluster

Minjie Cheng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

AAAI Conference 2025 Conference Paper

WatE: A Wasserstein t-distributed Embedding Method for Information-enriched Graph Visualization

Minjie Cheng
Dixin Luo
Hongteng Xu

As a fundamental problem of graph analysis, graph visualization aims to embed a set of graphs in a low-dimensional (e.g., 2D) space and provide insights into their distribution and clustering structure. Focusing on this problem, we propose a novel Wasserstein t-distributed embedding (WatE) method, leading to an information-enriched graph visualization paradigm. Our method learns a graph neural network to represent each graph as the mean and covariance of its node embedding distribution. Accordingly, our method can visualize each graph as an ellipse (determined by the mean and the covariance) rather than a single point. The positions of different ellipses reveal the relations among different graphs as traditional visualization methods do, while the size and shape of an ellipse preserve the node-level structural information of the corresponding graph. We propose a regularized t-distributed stochastic neighbor embedding (Rt-SNE) framework to learn the visualization model, deriving a Wasserstein distance-based Student's t-distribution of graph pairs and fitting the distribution to the data distribution under regularization. Both subjective and objective evaluations demonstrate that WatE achieves encouraging performance in various graph visualization and clustering tasks.

PDF Details DOI

ICML Conference 2025 Conference Paper

WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation Prediction

Fanmeng Wang
Minjie Cheng
Hongteng Xu

Predicting molecular ground-state conformation (i. e. , energy-minimized conformation) is crucial for many chemical applications such as molecular docking and property prediction. Classic energy-based simulation is time-consuming when solving this problem, while existing learning-based methods have advantages in computational efficiency but sacrifice accuracy and interpretability. In this work, we propose a novel and effective method to bridge the energy-based simulation and the learning-based strategy, which designs and learns a Wasserstein gradient flow-driven SE(3)-Transformer, called WGFormer, for ground-state conformation prediction. Specifically, our method tackles this task within an auto-encoding framework, which encodes low-quality conformations by the proposed WGFormer and decodes corresponding ground-state conformations by an MLP. The architecture of WGFormer corresponds to Wasserstein gradient flows — it optimizes conformations by minimizing an energy function defined on the latent mixture models of atoms, thereby significantly improving performance and interpretability. Extensive experiments demonstrate that our method consistently outperforms state-of-the-art competitors, providing a new and insightful paradigm to predict ground-state conformation. The code is available at https: //github. com/FanmengWang/WGFormer.

Details

AAAI Conference 2023 Conference Paper

Hierarchical Contrastive Learning for Temporal Point Processes

Qingmei Wang
Minjie Cheng
Shen Yuan
Hongteng Xu

As an important sequential model, the temporal point process (TPP) plays a central role in real-world sequence modeling and analysis, whose learning is often based on the maximum likelihood estimation (MLE). However, due to imperfect observations, such as incomplete and sparse sequences that are common in practice, the MLE of TPP models often suffers from overfitting and leads to unsatisfactory generalization power. In this work, we develop a novel hierarchical contrastive (HCL) learning method for temporal point processes, which provides a new regularizer of MLE. In principle, our HCL considers the noise contrastive estimation (NCE) problem at the event-level and at the sequence-level jointly. Given a sequence, the event-level NCE maximizes the probability of each observed event given its history while penalizing the conditional probabilities of the unobserved events. At the same time, we generate positive and negative event sequences from the observed sequence and maximize the discrepancy between their likelihoods through the sequence-level NCE. Instead of using time-consuming simulation methods, we generate the positive and negative sequences via a simple but efficient model-guided thinning process. Experimental results show that the MLE method assisted by the HCL regularizer outperforms classic MLE and other contrastive learning methods in learning various TPP models consistently. The code is available at https://github.com/qingmeiwangdaily/HCL_TPP.

PDF Details DOI

EAAI Journal 2021 Journal Article

DTaxa: An actor–critic for automatic taxonomy induction

Yongming Han
Yanwei Lang
Minjie Cheng
Zhiqiang Geng
Guofei Chen
Tao Xia

Automatic taxonomy induction is a challenging task in the field of natural language understanding (NLU) and information retrieval (IR) because it requires machine learning and understanding the is-a relation (i. e. hypernym relation) between term pairs. Therefore, the deep taxa (DTaxa) based on the actor–critic algorithm framework is designed to deal with the aforementioned problems in this paper. The agent in the DTaxa regards the taxonomy induction process as the sequential decision steps so that the agent can take the operation of a term as an action via the policy network to jointly optimize hypernym detection and hypernym organization. Meanwhile, the DTaxa obtains a stable performance from the experiences buffered in the memory. In order to verify the effectiveness of the DTaxa for the automatic taxonomy induction, two experiments are performed on the all bottomed-out full subtrees extracted from WordNet 3. 0 and the English environment and science taxonomies in the SemEval-2016 task 13, respectively. The proposed method outperforms these existing methods and achieves state-of-the-art among most metrics.

Details DOI