arXiv subjects

Zhe Su

Publications and source records attributed to Zhe Su.

51 records · Page 3Linked to original sources

arXiv2023

The Metric Completion of the Space of Vector-Valued One-Forms

The space of full-ranked one-forms on a smooth, orientable, compact manifold (possibly with boundary) is metrically incomplete with respect to the induced geodesic distance of the generalized Ebin metric. We show a distance equality between the induced geodesic distances of the generalized Ebin metric on the space of full-ranked one-forms and the corresponding Riemannian metric defined on each fiber. Using this result we immediately have a concrete description of the metric completion of the space of full-ranked one-forms. Additionally, we study the relationship between the space of full-ranked one-forms and the space of all Riemannian metrics, leading to quotient structures for the space of Riemannian metrics and its completion.

math.DG↗

arXiv2023

Uncovering and Categorizing Social Biases in Text-to-SQL

Content Warning: This work contains examples that potentially implicate stereotypes, associations, and other harms that could be offensive to individuals in certain social groups.} Large pre-trained language models are acknowledged to carry social biases towards different demographics, which can further amplify existing stereotypes in our society and cause even more harm. Text-to-SQL is an important task, models of which are mainly adopted by administrative industries, where unfair decisions may lead to catastrophic consequences. However, existing Text-to-SQL models are trained on clean, neutral datasets, such as Spider and WikiSQL. This, to some extent, cover up social bias in models under ideal conditions, which nevertheless may emerge in real application scenarios. In this work, we aim to uncover and categorize social biases in Text-to-SQL models. We summarize the categories of social biases that may occur in structured data for Text-to-SQL models. We build test benchmarks and reveal that models with similar task accuracy can contain social biases at very different rates. We show how to take advantage of our methodology to uncover and assess social biases in the downstream Text-to-SQL task. We will release our code and data.

cs.CL↗

arXiv2023

Uncovering and Quantifying Social Biases in Code Generation

With the popularity of automatic code generation tools, such as Copilot, the study of the potential hazards of these tools is gaining importance. In this work, we explore the social bias problem in pre-trained code generation models. We propose a new paradigm to construct code prompts and successfully uncover social biases in code generation models. To quantify the severity of social biases in generated code, we develop a dataset along with three metrics to evaluate the overall social bias and fine-grained unfairness across different demographics. Experimental results on three pre-trained code generation models (Codex, InCoder, and CodeGen) with varying sizes, reveal severe social biases. Moreover, we conduct analysis to provide useful insights for further choice of code generation models with low social bias. (This work contains examples that potentially implicate stereotypes, associations, and other harms that could be offensive to individuals in certain social groups.)

cs.CL↗

arXiv2022

Supervised Learning and Reinforcement Learning of Feedback Models for Reactive Behaviors: Tactile Feedback Testbed

Robots need to be able to adapt to unexpected changes in the environment such that they can autonomously succeed in their tasks. However, hand-designing feedback models for adaptation is tedious, if at all possible, making data-driven methods a promising alternative. In this paper we introduce a full framework for learning feedback models for reactive motion planning. Our pipeline starts by segmenting demonstrations of a complete task into motion primitives via a semi-automated segmentation algorithm. Then, given additional demonstrations of successful adaptation behaviors, we learn initial feedback models through learning from demonstrations. In the final phase, a sample-efficient reinforcement learning algorithm fine-tunes these feedback models for novel task settings through few real system interactions. We evaluate our approach on a real anthropomorphic robot in learning a tactile feedback task.

cs.RO↗

arXiv2022

Knowledge-Driven New Drug Recommendation

Drug recommendation assists doctors in prescribing personalized medications to patients based on their health conditions. Existing drug recommendation solutions adopt the supervised multi-label classification setup and only work with existing drugs with sufficient prescription data from many patients. However, newly approved drugs do not have much historical prescription data and cannot leverage existing drug recommendation methods. To address this, we formulate the new drug recommendation as a few-shot learning problem. Yet, directly applying existing few-shot learning algorithms faces two challenges: (1) complex relations among diseases and drugs and (2) numerous false-negative patients who were eligible but did not yet use the new drugs. To tackle these challenges, we propose EDGE, which can quickly adapt to the recommendation for a new drug with limited prescription data from a few support patients. EDGE maintains a drug-dependent multi-phenotype few-shot learner to bridge the gap between existing and new drugs. Specifically, EDGE leverages the drug ontology to link new drugs to existing drugs with similar treatment effects and learns ontology-based drug representations. Such drug representations are used to customize the metric space of the phenotype-driven patient representations, which are composed of a set of phenotypes capturing complex patient health status. Lastly, EDGE eliminates the false-negative supervision signal using an external drug-disease knowledge base. We evaluate EDGE on two real-world datasets: the public EHR data (MIMIC-IV) and private industrial claims data. Results show that EDGE achieves 7.3% improvement on the ROC-AUC score over the best baseline.

cs.LG↗

arXiv2022

Cortical-inspired placement and routing: minimizing the memory resources in multi-core neuromorphic processors

Brain-inspired event-based neuromorphic processing systems have emerged as a promising technology in particular for bio-medical circuits and systems. However, both neuromorphic and biological implementations of neural networks have critical energy and memory constraints. To minimize the use of memory resources in multi-core neuromorphic processors, we propose a network design approach inspired by biological neural networks. We use this approach to design a new routing scheme optimized for small-world networks and, at the same time, to present a hardware-aware placement algorithm that optimizes the allocation of resources for small-world network models. We validate the algorithm with a canonical small-world network and present preliminary results for other networks derived from it

cs.NE↗

arXiv2022

Integrated Construction of Multimodal Atlases with Structural Connectomes in the Space of Riemannian Metrics

The structural network of the brain, or structural connectome, can be represented by fiber bundles generated by a variety of tractography methods. While such methods give qualitative insights into brain structure, there is controversy over whether they can provide quantitative information, especially at the population level. In order to enable population-level statistical analysis of the structural connectome, we propose representing a connectome as a Riemannian metric, which is a point on an infinite-dimensional manifold. We equip this manifold with the Ebin metric, a natural metric structure for this space, to get a Riemannian manifold along with its associated geometric properties. We then use this Riemannian framework to apply object-oriented statistical analysis to define an atlas as the Fréchet mean of a population of Riemannian metrics. This formulation ties into the existing framework for diffeomorphic construction of image atlases, allowing us to construct a multimodal atlas by simultaneously integrating complementary white matter structure details from DWMRI and cortical details from T1-weighted MRI. We illustrate our framework with 2D data examples of connectome registration and atlas formation. Finally, we build an example 3D multimodal atlas using T1 images and connectomes derived from diffusion tensors estimated from a subset of subjects from the Human Connectome Project.

cs.CV↗

arXiv2022

A hardware-software co-design approach to minimize the use of memory resources in multi-core neuromorphic processors

Both in electronics and biology, physical implementations of neural networks have severe energy and memory constraints. We propose a hardware-software co-design approach for minimizing the use of memory resources in multi-core neuromorphic processors, by taking inspiration from biological neural networks. We use this approach to design new routing schemes optimized for small-world networks and to provide guidelines for designing novel application-specific multi-core neuromorphic chips. Starting from the hierarchical routing scheme proposed, we present a hardware-aware placement algorithm that optimizes the allocation of resources for arbitrary network models. We validate the algorithm with a canonical small-world network and present preliminary results for other networks derived from it.

cs.NE↗

arXiv2021

Structural Connectome Atlas Construction in the Space of Riemannian Metrics

The structural connectome is often represented by fiber bundles generated from various types of tractography. We propose a method of analyzing connectomes by representing them as a Riemannian metric, thereby viewing them as points in an infinite-dimensional manifold. After equipping this space with a natural metric structure, the Ebin metric, we apply object-oriented statistical analysis to define an atlas as the Fréchet mean of a population of Riemannian metrics. We demonstrate connectome registration and atlas formation using connectomes derived from diffusion tensors estimated from a subset of subjects from the Human Connectome Project.

cs.CV↗

arXiv2020

A diffeomorphism-invariant metric on the space of vector-valued one-forms

In this article we introduce a diffeomorphism-invariant Riemannian metric on the space of vector valued one-forms. The particular choice of metric is motivated by potential future applications in the field of functional data and shape analysis and by connections to the Ebin metric on the space of all Riemannian metrics. In the present work we calculate the geodesic equations and obtain an explicit formula for the solutions to the corresponding initial value problem. Using this we show that it is a geodesically and metrically incomplete space and study the existence of totally geodesic subspaces. Furthermore, we calculate the sectional curvature and observe that, depending on the dimension of the base manifold and the target space, it either has a semidefinite sign or admits both signs.

math.DG↗

arXiv2019

Shape Analysis of Surfaces Using General Elastic Metrics

In this article we introduce a family of elastic metrics on the space of parametrized surfaces in 3D space using a corresponding family of metrics on the space of vector valued one-forms. We provide a numerical framework for the computation of geodesics with respect to these metrics. The family of metrics is invariant under rigid motions and reparametrizations; hence it induces a metric on the "shape space" of surfaces. This new class of metrics generalizes a previously studied family of elastic metrics and includes in particular the Square Root Normal Function (SRNF) metric, which has been proven successful in various applications. We demonstrate our framework by showing several examples of geodesics and compare our results with earlier results obtained from the SRNF framework.

math.DG↗

arXiv2019

Learning Latent Space Dynamics for Tactile Servoing

To achieve a dexterous robotic manipulation, we need to endow our robot with tactile feedback capability, i.e. the ability to drive action based on tactile sensing. In this paper, we specifically address the challenge of tactile servoing, i.e. given the current tactile sensing and a target/goal tactile sensing --memorized from a successful task execution in the past-- what is the action that will bring the current tactile sensing to move closer towards the target tactile sensing at the next time step. We develop a data-driven approach to acquire a dynamics model for tactile servoing by learning from demonstration. Moreover, our method represents the tactile sensing information as to lie on a surface --or a 2D manifold-- and perform a manifold learning, making it applicable to any tactile skin geometry. We evaluate our method on a contact point tracking task using a robot equipped with a tactile finger. A video demonstrating our approach can be seen in https://youtu.be/0QK0-Vx7WkI

cs.RO↗

arXiv2018

Learning Sensor Feedback Models from Demonstrations via Phase-Modulated Neural Networks

In order to robustly execute a task under environmental uncertainty, a robot needs to be able to reactively adapt to changes arising in its environment. The environment changes are usually reflected in deviation from expected sensory traces. These deviations in sensory traces can be used to drive the motion adaptation, and for this purpose, a feedback model is required. The feedback model maps the deviations in sensory traces to the motion plan adaptation. In this paper, we develop a general data-driven framework for learning a feedback model from demonstrations. We utilize a variant of a radial basis function network structure --with movement phases as kernel centers-- which can generally be applied to represent any feedback models for movement primitives. To demonstrate the effectiveness of our framework, we test it on the task of scraping on a tilt board. In this task, we are learning a reactive policy in the form of orientation adaptation, based on deviations of tactile sensor traces. As a proof of concept of our method, we provide evaluations on an anthropomorphic robot. A video demonstrating our approach and its results can be seen in https://youtu.be/7Dx5imy1Kcw

cs.RO↗

arXiv2017

Comparing Curves in Homogeneous Spaces

Of concern is the study of the space of curves in homogeneous spaces. Motivated by applications in shape analysis we identify two curves if they only differ by their parametrization and/or a rigid motion. For curves in Euclidean space the Square-Root-Velocity-Function (SRVF) allows to define and efficiently compute a distance on this infinite dimensional quotient space. In this article we present a generalization of the SRVF to curves in homogeneous spaces. We prove that, under mild conditions on the curves, there always exist optimal reparametrizations realizing the quotient distance and demonstrate the efficiency of our framework in selected numerical examples.

math.DG↗

arXiv2017

The Square Root Velocity Framework for Curves in a Homogeneous Space

In this paper we study the shape space of curves with values in a homogeneous space $M = G/K$, where $G$ is a Lie group and $K$ is a compact Lie subgroup. We generalize the square root velocity framework to obtain a reparametrization invariant metric on the space of curves in $M$. By identifying curves in $M$ with their horizontal lifts in $G$, geodesics then can be computed. We can also mod out by reparametrizations and by rigid motions of $M$. In each of these quotient spaces, we can compute Karcher means, geodesics, and perform principal component analysis. We present numerical examples including the analysis of a set of hurricane paths.

math.DG↗