arXiv subjects

Nan Wu

Publications and source records attributed to Nan Wu.

At least 73 records · Page 4Linked to original sources

arXiv2022

A Closed-Form EVSI Expression for a Multinomial Data-Generating Process

This paper derives analytic expressions for the expected value of sample information (EVSI), the expected value of distribution information (EVDI), and the optimal sample size when data consists of independent draws from a bounded sequence of integers. Due to challenges of creating tractable EVSI expressions, most existing work valuing data does so in one of three ways: 1) analytically through closed-form expressions on the upper bound of the value of data, 2) calculating the expected value of data using numerical comparisons of decisions made using simulated data to optimal decisions where the underlying data distribution is known, or 3) using variance reduction as proxy for the uncertainty reduction that accompanies more data. For the very flexible case of modelling integer-valued observations using a multinomial data-generating process with Dirichlet prior, this paper develops expressions that 1) generalize existing beta-Binomial computations, 2) do not require prior knowledge of some underlying "true" distribution, and 3) can be computed prior to the collection of any sample data.

stat.ME↗

arXiv2022

Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation

Using machine learning to solve combinatorial optimization (CO) problems is challenging, especially when the data is unlabeled. This work proposes an unsupervised learning framework for CO problems. Our framework follows a standard relaxation-plus-rounding approach and adopts neural networks to parameterize the relaxed solutions so that simple back-propagation can train the model end-to-end. Our key contribution is the observation that if the relaxed objective satisfies entry-wise concavity, a low optimization loss guarantees the quality of the final integral solutions. This observation significantly broadens the applicability of the previous framework inspired by Erdos' probabilistic method. In particular, this observation can guide the design of objective models in applications where the objectives are not given explicitly while requiring being modeled in prior. We evaluate our framework by solving a synthetic graph optimization problem, and two real-world applications including resource allocation in circuit design and approximate computing. Our framework largely outperforms the baselines based on naïve relaxation, reinforcement learning, and Gumbel-softmax tricks.

cs.LG↗

arXiv2022

LOSTIN: Logic Optimization via Spatio-Temporal Information with Hybrid Graph Models

Despite the stride made by machine learning (ML) based performance modeling, two major concerns that may impede production-ready ML applications in EDA are stringent accuracy requirements and generalization capability. To this end, we propose hybrid graph neural network (GNN) based approaches towards highly accurate quality-of-result (QoR) estimations with great generalization capability, specifically targeting logic synthesis optimization. The key idea is to simultaneously leverage spatio-temporal information from hardware designs and logic synthesis flows to forecast performance (i.e., delay/area) of various synthesis flows on different designs. The structural characteristics inside hardware designs are distilled and represented by GNNs; the temporal knowledge (i.e., relative ordering of logic transformations) in synthesis flows can be imposed on hardware designs by combining a virtually added supernode or a sequence processing model with conventional GNN models. Evaluation on 3.3 million data points shows that the testing mean absolute percentage error (MAPE) on designs seen and unseen during training are no more than 1.2% and 3.1%, respectively, which are 7-15X lower than existing studies.

cs.LG↗

arXiv2022

Data-driven Efficient Solvers for Langevin Dynamics on Manifold in High Dimensions

We study the Langevin dynamics of a physical system with manifold structure $\mathcal{M}\subset\mathbb{R}^p$ based on collected sample points $\{\mathsf{x}_i\}_{i=1}^n \subset \mathcal{M}$ that probe the unknown manifold $\mathcal{M}$. Through the diffusion map, we first learn the reaction coordinates $\{\mathsf{y}_i\}_{i=1}^n\subset \mathcal{N}$ corresponding to $\{\mathsf{x}_i\}_{i=1}^n$, where $\mathcal{N}$ is a manifold diffeomorphic to $\mathcal{M}$ and isometrically embedded in $\mathbb{R}^\ell$ with $\ell \ll p$. The induced Langevin dynamics on $\mathcal{N}$ in terms of the reaction coordinates captures the slow time scale dynamics such as conformational changes in biochemical reactions. To construct an efficient and stable approximation for the Langevin dynamics on $\mathcal{N}$, we leverage the corresponding Fokker-Planck equation on the manifold $\mathcal{N}$ in terms of the reaction coordinates $\mathsf{y}$. We propose an implementable, unconditionally stable, data-driven finite volume scheme for this Fokker-Planck equation, which automatically incorporates the manifold structure of $\mathcal{N}$. Furthermore, we provide a weighted $L^2$ convergence analysis of the finite volume scheme to the Fokker-Planck equation on $\mathcal{N}$. The proposed finite volume scheme leads to a Markov chain on $\{\mathsf{y}_i\}_{i=1}^n$ with an approximated transition probability and jump rate between the nearest neighbor points. After an unconditionally stable explicit time discretization, the data-driven finite volume scheme gives an approximated Markov process for the Langevin dynamics on $\mathcal{N}$ and the approximated Markov process enjoys detailed balance, ergodicity, and other good properties.

math.NA↗

arXiv2022

Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks

We hypothesize that due to the greedy nature of learning in multi-modal deep neural networks, these models tend to rely on just one modality while under-fitting the other modalities. Such behavior is counter-intuitive and hurts the models' generalization, as we observe empirically. To estimate the model's dependence on each modality, we compute the gain on the accuracy when the model has access to it in addition to another modality. We refer to this gain as the conditional utilization rate. In the experiments, we consistently observe an imbalance in conditional utilization rates between modalities, across multiple tasks and architectures. Since conditional utilization rate cannot be computed efficiently during training, we introduce a proxy for it based on the pace at which the model learns from each modality, which we refer to as the conditional learning speed. We propose an algorithm to balance the conditional learning speeds between modalities during training and demonstrate that it indeed addresses the issue of greedy learning. The proposed algorithm improves the model's generalization on three datasets: Colored MNIST, ModelNet40, and NVIDIA Dynamic Hand Gesture.

cs.LG↗

arXiv2022

GReS: Graphical Cross-domain Recommendation for Supply Chain Platform

Supply Chain Platforms (SCPs) provide downstream industries with numerous raw materials. Compared with traditional e-commerce platforms, data in SCPs is more sparse due to limited user interests. To tackle the data sparsity problem, one can apply Cross-Domain Recommendation (CDR) which improves the recommendation performance of the target domain with the source domain information. However, applying CDR to SCPs directly ignores the hierarchical structure of commodities in SCPs, which reduce the recommendation performance. To leverage this feature, in this paper, we take the catering platform as an example and propose GReS, a graphical cross-domain recommendation model. The model first constructs a tree-shaped graph to represent the hierarchy of different nodes of dishes and ingredients, and then applies our proposed Tree2vec method combining GCN and BERT models to embed the graph for recommendations. Experimental results on a commercial dataset show that GReS significantly outperforms state-of-the-art methods in Cross-Domain Recommendation for Supply Chain Platforms.

cs.IR↗

arXiv2022

Heterogeneous Graph Tree Networks

Heterogeneous graph neural networks (HGNNs) have attracted increasing research interest in recent three years. Most existing HGNNs fall into two classes. One class is meta-path-based HGNNs which either require domain knowledge to handcraft meta-paths or consume huge amount of time and memory to automatically construct meta-paths. The other class does not rely on meta-path construction. It takes homogeneous convolutional graph neural networks (Conv-GNNs) as backbones and extend them to heterogeneous graphs by introducing node-type- and edge-type-dependent parameters. Regardless of the meta-path dependency, most existing HGNNs employ shallow Conv-GNNs such as GCN and GAT to aggregate neighborhood information, and may have limited capability to capture information from high-order neighborhood. In this work, we propose two heterogeneous graph tree network models: Heterogeneous Graph Tree Convolutional Network (HetGTCN) and Heterogeneous Graph Tree Attention Network (HetGTAN), which do not rely on meta-paths to encode heterogeneity in both node features and graph structure. Extensive experiments on three real-world heterogeneous graph data demonstrate that the proposed HetGTCN and HetGTAN are efficient and consistently outperform all state-of-the-art HGNN baselines on semi-supervised node classification tasks, and can go deep without compromising performance.

cs.LG↗

arXiv2022

Prediction of protein allosteric signalling pathways and functional residues through paths of optimised propensity

Allostery commonly refers to the mechanism that regulates protein activity through the binding of a molecule at a different, usually distal, site from the orthosteric site. The omnipresence of allosteric regulation in nature and its potential for drug design and screening render the study of allostery invaluable. Nevertheless, challenges remain as few computational methods are available to effectively predict allosteric sites, identify signalling pathways involved in allostery, or to aid with the design of suitable molecules targeting such sites. Recently, bond-to-bond propensity analysis has been shown successful at identifying allosteric sites for a large and diverse group of proteins from knowledge of the orthosteric sites and its ligands alone by using network analysis applied to energy-weighted atomistic protein graphs. To address the identification of signalling pathways, we propose here a method to compute and score paths of optimised propensity that link the orthosteric site with the identified allosteric sites, and identifies crucial residues that contribute to those paths. We showcase the approach with three well-studied allosteric proteins: h-Ras, caspase-1, and 3-phosphoinositide-dependent kinase-1 (PDK1). Key residues in both orthosteric and allosteric sites were identified and showed agreement with experimental results, and pivotal signalling residues along the pathway were also revealed, thus providing alternative targets for drug design. By using the computed path scores, we were also able to differentiate the activity of different allosteric modulators.

q-bio.BM↗

arXiv2022

Fairness and Cost Constrained Privacy-Aware Record Linkage

Record linkage algorithms match and link records from different databases that refer to the same real-world entity based on direct and/or quasi-identifiers, such as name, address, age, and gender, available in the records. Since these identifiers generally contain personal identifiable information (PII) about the entities, record linkage algorithms need to be developed with privacy constraints. Known as privacy-preserving record linkage (PPRL), many research studies have been conducted to perform the linkage on encoded and/or encrypted identifiers. Differential privacy (DP) combined with computationally efficient encoding methods, e.g. Bloom filter encoding, has been used to develop PPRL with provable privacy guarantees. The standard DP notion does not however address other constraints, among which the most important ones are fairness-bias and cost of linkage in terms of number of record pairs to be compared. In this work, we propose new notions of fairness-constrained DP and fairness and cost-constrained DP for PPRL and develop a framework for PPRL with these new notions of DP combined with Bloom filter encoding. We provide theoretical proofs for the new DP notions for fairness and cost-constrained PPRL and experimentally evaluate them on two datasets containing person-specific data. Our experimental results show that with these new notions of DP, PPRL with better performance (compared to the standard DP notion for PPRL) can be achieved with regard to privacy, cost and fairness constraints.

cs.CR↗

arXiv2022

Dog nose print matching with dual global descriptor based on Contrastive Learning

Recent studies in biometric-based identification tasks have shown that deep learning methods can achieve better performance. These methods generally extract the global features as descriptor to represent the original image. Nonetheless, it does not perform well for biometric identification under fine-grained tasks. The main reason is that the single image descriptor contains insufficient information to represent image. In this paper, we present a dual global descriptor model, which combines multiple global descriptors to exploit multi level image features. Moreover, we utilize a contrastive loss to enlarge the distance between image representations of confusing classes. The proposed framework achieves the top2 on the CVPR2022 Biometrics Workshop Pet Biometric Challenge. The source code and trained models are publicly available at: https://github.com/flyingsheepbin/pet-biometrics

cs.CV↗

arXiv2022

GTNet: A Tree-Based Deep Graph Learning Architecture

We propose Graph Tree Networks (GTNets), a deep graph learning architecture with a new general message passing scheme that originates from the tree representation of graphs. In the tree representation, messages propagate upward from the leaf nodes to the root node, and each node preserves its initial information prior to receiving information from its child nodes (neighbors). We formulate a general propagation rule following the nature of message passing in the tree to update a node's feature by aggregating its initial feature and its neighbor nodes' updated features. Two graph representation learning models are proposed within this GTNet architecture - Graph Tree Attention Network (GTAN) and Graph Tree Convolution Network (GTCN), with experimentally demonstrated state-of-the-art performance on several popular benchmark datasets. Unlike the vanilla Graph Attention Network (GAT) and Graph Convolution Network (GCN) which have the "over-smoothing" issue, the proposed GTAN and GTCN models can go deep as demonstrated by comprehensive experiments and rigorous theoretical analysis.

cs.LG↗

arXiv2022

DeepMix: Mobility-aware, Lightweight, and Hybrid 3D Object Detection for Headsets

Mobile headsets should be capable of understanding 3D physical environments to offer a truly immersive experience for augmented/mixed reality (AR/MR). However, their small form-factor and limited computation resources make it extremely challenging to execute in real-time 3D vision algorithms, which are known to be more compute-intensive than their 2D counterparts. In this paper, we propose DeepMix, a mobility-aware, lightweight, and hybrid 3D object detection framework for improving the user experience of AR/MR on mobile headsets. Motivated by our analysis and evaluation of state-of-the-art 3D object detection models, DeepMix intelligently combines edge-assisted 2D object detection and novel, on-device 3D bounding box estimations that leverage depth data captured by headsets. This leads to low end-to-end latency and significantly boosts detection accuracy in mobile scenarios. A unique feature of DeepMix is that it fully exploits the mobility of headsets to fine-tune detection results and boost detection accuracy. To the best of our knowledge, DeepMix is the first 3D object detection that achieves 30 FPS (an end-to-end latency much lower than the 100 ms stringent requirement of interactive AR/MR). We implement a prototype of DeepMix on Microsoft HoloLens and evaluate its performance via both extensive controlled experiments and a user study with 30+ participants. DeepMix not only improves detection accuracy by 9.1--37.3% but also reduces end-to-end latency by 2.68--9.15x, compared to the baseline that uses existing 3D object detection models.

cs.CV↗

arXiv2022

Almost sharp Sobolev trace inequalities in the unit ball under constraints

We establish three families of Sobolev trace inequalities of orders two and four in the unit ball under higher order moments constraint, and are able to construct \emph{smooth} test functions to show all such inequalities are \emph{almost optimal}. Some distinct feature in \emph{almost sharpness} examples between the fourth order and second order Sobolev trace inequalities is discovered. This has been neglected in higher order Sobolev inequality case in \cite{Hang}. As a byproduct, the method of our construction can be used to show the sharpness of the generalized Lebedev-Milin inequality under constraints.

math.DG↗

arXiv2022

High-Level Synthesis Performance Prediction using GNNs: Benchmarking, Modeling, and Advancing

Agile hardware development requires fast and accurate circuit quality evaluation from early design stages. Existing work of high-level synthesis (HLS) performance prediction usually needs extensive feature engineering after the synthesis process. To expedite circuit evaluation from as earlier design stage as possible, we propose a rapid and accurate performance modeling, exploiting the representation power of graph neural networks (GNNs) by representing C/C++ programs as graphs. The contribution of this work is three-fold. First, we build a standard benchmark containing 40k C synthesizable programs, which includes both synthetic programs and three sets of real-world HLS benchmarks. Each program is implemented on FPGA to generate ground-truth performance metrics. Second, we formally formulate the HLS performance prediction problem on graphs, and propose multiple modeling strategies with GNNs that leverage different trade-offs between prediction timeliness (early/late prediction) and accuracy. Third, we further propose a novel hierarchical GNN that does not sacrifice timeliness but largely improves prediction accuracy, significantly outperforming HLS tools. We apply extensive evaluations for both synthetic and unseen real-case programs; our proposed predictor largely outperforms HLS by up to 40X and excels existing predictors by 2X to 5X in terms of resource usage and timing prediction.

cs.LG↗

arXiv2021

IronMan: GNN-assisted Design Space Exploration in High-Level Synthesis via Reinforcement Learning

Despite the great success of High-Level Synthesis (HLS) tools, we observe several unresolved challenges: 1) the high-level abstraction of programming styles in HLS sometimes conceals optimization opportunities; 2) existing HLS tools do not provide flexible trade-off (Pareto) solutions among different objectives and constraints; 3) the actual quality of the resulting RTL designs is hard to predict. To address these challenges, we propose an end-to-end framework, namelyIronMan. The primary goal is to enable a flexible and automated design space exploration (DSE), to provide either optimal solutions under user-specified constraints, or various trade-offs among different objectives (such as different types of resources, area, and latency). Such DSE either requires tedious manual efforts or is not achievable to attain these goals through existing HLS tools. There are three components in IronMan: 1) GPP, a highly accurate graph-neural-network-based performance and resource predictor; 2) RLMD, a reinforcement-learning-based multi-objective DSE engine that explores the optimal resource allocation strategy, to provide Pareto solutions between different objectives; 3) CT, a code transformer to assist RLMD and GPP, which extracts the data flow graph from original HLS C/C++ and automatically generates synthesizable code with HLS directives. The experimental results show that: 1) GPP achieves high prediction accuracy, reducing prediction errors of HLS tools by 10.9x in resource utilization and 5.7x in timing; 2) RLMD obtains optimal or Pareto solutions that outperform the genetic algorithm and simulated annealing by 12.7% and 12.9%, respectively; 3) IronMan is able to find optimized solutions perfectly matching various DSP constraints, with 2.54x fewer DSPs and up to 6x shorter latency than those of HLS tools while being up to 400x faster than the heuristic algorithms and HLS tools.

cs.AR↗

arXiv2021

A Survey of Machine Learning for Computer Architecture and Systems

It has been a long time that computer architecture and systems are optimized for efficient execution of machine learning (ML) models. Now, it is time to reconsider the relationship between ML and systems, and let ML transform the way that computer architecture and systems are designed. This embraces a twofold meaning: improvement of designers' productivity, and completion of the virtuous cycle. In this paper, we present a comprehensive review of the work that applies ML for computer architecture and system design. First, we perform a high-level taxonomy by considering the typical role that ML techniques take in architecture/system design, i.e., either for fast predictive modeling or as the design methodology. Then, we summarize the common problems in computer architecture/system design that can be solved by ML techniques, and the typical ML techniques employed to resolve each of them. In addition to emphasis on computer architecture in a narrow sense, we adopt the concept that data centers can be recognized as warehouse-scale computers; sketchy discussions are provided in adjacent computer systems, such as code generation and compiler; we also give attention to how ML techniques can aid and transform design automation. We further provide a future vision of opportunities and potential directions, and envision that applying ML for computer architecture and systems would thrive in the community.

cs.LG↗

arXiv2021

Graph Based Gaussian Processes on Restricted Domains

In nonparametric regression, it is common for the inputs to fall in a restricted subset of Euclidean space. Typical kernel-based methods that do not take into account the intrinsic geometry of the domain across which observations are collected may produce sub-optimal results. In this article, we focus on solving this problem in the context of Gaussian process (GP) models, proposing a new class of Graph Laplacian based GPs (GL-GPs), which learn a covariance that respects the geometry of the input domain. As the heat kernel is intractable computationally, we approximate the covariance using finitely-many eigenpairs of the Graph Laplacian (GL). The GL is constructed from a kernel which depends only on the Euclidean coordinates of the inputs. Hence, we can benefit from the full knowledge about the kernel to extend the covariance structure to newly arriving samples by a Nyström type extension. We provide substantial theoretical support for the GL-GP methodology, and illustrate performance gains in various applications.

stat.ME↗

arXiv2021

SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training

Unsupervised pre-training is now the predominant approach for both text and speech understanding. Self-attention models pre-trained on large amounts of unannotated data have been hugely successful when fine-tuned on downstream tasks from a variety of domains and languages. This paper takes the universality of unsupervised language pre-training one step further, by unifying speech and text pre-training within a single model. We build a single encoder with the BERT objective on unlabeled text together with the w2v-BERT objective on unlabeled speech. To further align our model representations across modalities, we leverage alignment losses, specifically Translation Language Modeling (TLM) and Speech Text Matching (STM) that make use of supervised speech-text recognition data. We demonstrate that incorporating both speech and text data during pre-training can significantly improve downstream quality on CoVoST~2 speech translation, by around 1 BLEU compared to single-modality pre-trained models, while retaining close to SotA performance on LibriSpeech and SpeechStew ASR tasks. On four GLUE tasks and text-normalization, we observe evidence of capacity limitations and interference between the two modalities, leading to degraded performance compared to an equivalent text-only model, while still being competitive with BERT. Through extensive empirical analysis we also demonstrate the importance of the choice of objective function for speech pre-training, and the beneficial effect of adding additional supervised signals on the quality of the learned representations.

cs.CL↗