Alert button
Picture for Mingyu Lu

Mingyu Lu

Alert button

TKwinFormer: Top k Window Attention in Vision Transformers for Feature Matching

Aug 29, 2023
Yun Liao, Yide Di, Hao Zhou, Kaijun Zhu, Mingyu Lu, Yijia Zhang, Qing Duan, Junhui Liu

Local feature matching remains a challenging task, primarily due to difficulties in matching sparse keypoints and low-texture regions. The key to solving this problem lies in effectively and accurately integrating global and local information. To achieve this goal, we introduce an innovative local feature matching method called TKwinFormer. Our approach employs a multi-stage matching strategy to optimize the efficiency of information interaction. Furthermore, we propose a novel attention mechanism called Top K Window Attention, which facilitates global information interaction through window tokens prior to patch-level matching, resulting in improved matching accuracy. Additionally, we design an attention block to enhance attention between channels. Experimental results demonstrate that TKwinFormer outperforms state-of-the-art methods on various benchmarks. Code is available at: https://github.com/LiaoYun0x0/TKwinFormer.

* 11 pages, 7 figures 
Viaarxiv icon

Learning to Maximize Mutual Information for Dynamic Feature Selection

Jan 02, 2023
Ian Covert, Wei Qiu, Mingyu Lu, Nayoon Kim, Nathan White, Su-In Lee

Figure 1 for Learning to Maximize Mutual Information for Dynamic Feature Selection
Figure 2 for Learning to Maximize Mutual Information for Dynamic Feature Selection
Figure 3 for Learning to Maximize Mutual Information for Dynamic Feature Selection
Figure 4 for Learning to Maximize Mutual Information for Dynamic Feature Selection

Feature selection helps reduce data acquisition costs in ML, but the standard approach is to train models with static feature subsets. Here, we consider the dynamic feature selection (DFS) problem where a model sequentially queries features based on the presently available information. DFS is often addressed with reinforcement learning (RL), but we explore a simpler approach of greedily selecting features based on their conditional mutual information. This method is theoretically appealing but requires oracle access to the data distribution, so we develop a learning approach based on amortized optimization. The proposed method is shown to recover the greedy policy when trained to optimality and outperforms numerous existing feature selection methods in our experiments, thus validating it as a simple but powerful approach for this problem.

Viaarxiv icon

A Deep Bayesian Bandits Approach for Anticancer Therapy: Exploration via Functional Prior

May 05, 2022
Mingyu Lu, Yifang Chen, Su-In Lee

Figure 1 for A Deep Bayesian Bandits Approach for Anticancer Therapy: Exploration via Functional Prior
Figure 2 for A Deep Bayesian Bandits Approach for Anticancer Therapy: Exploration via Functional Prior
Figure 3 for A Deep Bayesian Bandits Approach for Anticancer Therapy: Exploration via Functional Prior
Figure 4 for A Deep Bayesian Bandits Approach for Anticancer Therapy: Exploration via Functional Prior

Learning personalized cancer treatment with machine learning holds great promise to improve cancer patients' chance of survival. Despite recent advances in machine learning and precision oncology, this approach remains challenging as collecting data in preclinical/clinical studies for modeling multiple treatment efficacies is often an expensive, time-consuming process. Moreover, the randomization in treatment allocation proves to be suboptimal since some participants/samples are not receiving the most appropriate treatments during the trial. To address this challenge, we formulate drug screening study as a "contextual bandit" problem, in which an algorithm selects anticancer therapeutics based on contextual information about cancer cell lines while adapting its treatment strategy to maximize treatment response in an "online" fashion. We propose using a novel deep Bayesian bandits framework that uses functional prior to approximate posterior for drug response prediction based on multi-modal information consisting of genomic features and drug structure. We empirically evaluate our method on three large-scale in vitro pharmacogenomic datasets and show that our approach outperforms several benchmarks in identifying optimal treatment for a given cell line.

Viaarxiv icon

G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes

Mar 23, 2020
Rui Li, Zach Shahn, Jun Li, Mingyu Lu, Prithwish Chakraborty, Daby Sow, Mohamed Ghalwash, Li-wei H. Lehman

Figure 1 for G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes
Figure 2 for G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes
Figure 3 for G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes
Figure 4 for G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes

Counterfactual prediction is a fundamental task in decision-making. G-computation is a method for estimating expected counterfactual outcomes under dynamic time-varying treatment strategies. Existing G-computation implementations have mostly employed classical regression models with limited capacity to capture complex temporal and nonlinear dependence structures. This paper introduces G-Net, a novel sequential deep learning framework for G-computation that can handle complex time series data while imposing minimal modeling assumptions and provide estimates of individual or population-level time varying treatment effects. We evaluate alternative G-Net implementations using realistically complex temporal simulated data obtained from CVSim, a mechanistic model of the cardiovascular system.

Viaarxiv icon