arXiv subjects

Hao Sun

Publications and source records attributed to Hao Sun.

At least 415 records · Page 23Linked to original sources

arXiv2022

Physics-informed Deep Super-resolution for Spatiotemporal Data

High-fidelity simulation of complex physical systems is exorbitantly expensive and inaccessible across spatiotemporal scales. Recently, there has been an increasing interest in leveraging deep learning to augment scientific data based on the coarse-grained simulations, which is of cheap computational expense and retains satisfactory solution accuracy. However, the major existing work focuses on data-driven approaches which rely on rich training datasets and lack sufficient physical constraints. To this end, we propose a novel and efficient spatiotemporal super-resolution framework via physics-informed learning, inspired by the independence between temporal and spatial derivatives in partial differential equations (PDEs). The general principle is to leverage the temporal interpolation for flow estimation, and then introduce convolutional-recurrent neural networks for learning temporal refinement. Furthermore, we employ the stacked residual blocks with wide activation and sub-pixel layers with pixelshuffle for spatial reconstruction, where feature extraction is conducted in a low-resolution latent space. Moreover, we consider hard imposition of boundary conditions in the network to improve reconstruction accuracy. Results demonstrate the superior effectiveness and efficiency of the proposed method compared with baseline algorithms through extensive numerical experiments.

cs.LG↗

arXiv2022

A Survey on Collaborative DNN Inference for Edge Intelligence

With the vigorous development of artificial intelligence (AI), the intelligent applications based on deep neural network (DNN) change people's lifestyles and the production efficiency. However, the huge amount of computation and data generated from the network edge becomes the major bottleneck, and traditional cloud-based computing mode has been unable to meet the requirements of real-time processing tasks. To solve the above problems, by embedding AI model training and inference capabilities into the network edge, edge intelligence (EI) becomes a cutting-edge direction in the field of AI. Furthermore, collaborative DNN inference among the cloud, edge, and end device provides a promising way to boost the EI. Nevertheless, at present, EI oriented collaborative DNN inference is still in its early stage, lacking a systematic classification and discussion of existing research efforts. Thus motivated, we have made a comprehensive investigation on the recent studies about EI oriented collaborative DNN inference. In this paper, we firstly review the background and motivation of EI. Then, we classify four typical collaborative DNN inference paradigms for EI, and analyze the characteristics and key technologies of them. Finally, we summarize the current challenges of collaborative DNN inference, discuss the future development trend and provide the future research direction.

cs.DC↗

arXiv2022

Testing the seesaw mechanisms via displaced right-handed neutrinos from a light scalar at the HL-LHC

We investigate the pair production of right-handed neutrinos from the decay of a light $B-L$ scalar in the $U(1)_{B-L}$ model. The $B-L$ scalar mixes to the SM Higgs, and the physical scalar is required to be lighter than the observed Higgs. The produced right-handed neutrinos are predicted to be long-lived according to the type-I seesaw mechanism, and yield potentially distinct signatures such as displaced vertex and time-delayed leptons at the CMS/ATLAS/LHCb, as well as signatures at the far detectors including the CODEX-b, FACET, FASER, MoEDAL-MAPP and MATHUSLA. We analyze the sensitivity reach at the HL-LHC for the right-handed neutrinos with masses of 2.5 $\sim$ 30 GeV, showing that the active-sterile mixing to muons can be probed to $V_{μN} \sim 10^{-5}$ at the CMS/ATLAS/LHCb using the displaced vertex searches, and one magnitude lower at the MATHUSLA/CMS using time-delayed leptons searches, reaching the parameter space interesting for type-I seesaw mechanisms.

hep-ph↗

arXiv2022

Shedding light on the electroweak phase transition from exotic Higgs boson decays at the lifetime frontiers

We study the scenarios where a strongly first-order electroweak phase transition (EWPT) is triggered by a light singlet scalar, which has feeble interactions to the Higgs. Since the singlet scalar is light and has weak couplings, it can decay at a macroscopic distance away from the collision point. Therefore, it can be regarded as a long-lived particles (LLP) in such scenarios. We perform the searches of the LLPs from the exotic Higgs decays, at the FASER, MAPP and CMS-Timing detectors of the 14 TeV HL-LHC, to probe the strongly first-order EWPT. In certain scenarios, we show that the LLP searches can help to reach the parameter space of the strongly first-order EWPT remarkably, where the searches for promptly exotic Higgs decays are not valid.

hep-ph↗

arXiv2022

HousE: Knowledge Graph Embedding with Householder Parameterization

The effectiveness of knowledge graph embedding (KGE) largely depends on the ability to model intrinsic relation patterns and mapping properties. However, existing approaches can only capture some of them with insufficient modeling capacity. In this work, we propose a more powerful KGE framework named HousE, which involves a novel parameterization based on two kinds of Householder transformations: (1) Householder rotations to achieve superior capacity of modeling relation patterns; (2) Householder projections to handle sophisticated relation mapping properties. Theoretically, HousE is capable of modeling crucial relation patterns and mapping properties simultaneously. Besides, HousE is a generalization of existing rotation-based models while extending the rotations to high-dimensional spaces. Empirically, HousE achieves new state-of-the-art performance on five benchmark datasets. Our code is available at https://github.com/anrep/HousE.

cs.AI↗

arXiv2022

Towards artificial general intelligence via a multimodal foundation model

The fundamental goal of artificial intelligence (AI) is to mimic the core cognitive activities of human. Despite tremendous success in the AI research, most of existing methods have only single-cognitive ability. To overcome this limitation and take a solid step towards artificial general intelligence (AGI), we develop a foundation model pre-trained with huge multimodal data, which can be quickly adapted for various downstream cognitive tasks. To achieve this goal, we propose to pre-train our foundation model by self-supervised learning with weak semantic correlation data crawled from the Internet and show that promising results can be obtained on a wide range of downstream tasks. Particularly, with the developed model-interpretability tools, we demonstrate that strong imagination ability is now possessed by our foundation model. We believe that our work makes a transformative stride towards AGI, from our common practice of "weak or narrow AI" to that of "strong or generalized AI".

cs.AI↗

arXiv2022

Distilling Governing Laws and Source Input for Dynamical Systems from Videos

Distilling interpretable physical laws from videos has led to expanded interest in the computer vision community recently thanks to the advances in deep learning, but still remains a great challenge. This paper introduces an end-to-end unsupervised deep learning framework to uncover the explicit governing equations of dynamics presented by moving object(s), based on recorded videos. Instead in the pixel (spatial) coordinate system of image space, the physical law is modeled in a regressed underlying physical coordinate system where the physical states follow potential explicit governing equations. A numerical integrator-based sparse regression module is designed and serves as a physical constraint to the autoencoder and coordinate system regression, and, in the meanwhile, uncover the parsimonious closed-form governing equations from the learned physical states. Experiments on simulated dynamical scenes show that the proposed method is able to distill closed-form governing equations and simultaneously identify unknown excitation input for several dynamical systems recorded by videos, which fills in the gap in literature where no existing methods are available and applicable for solving this type of problem.

cs.CV↗

arXiv2022

Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings

Vector quantization (VQ) based ANN indexes, such as Inverted File System (IVF) and Product Quantization (PQ), have been widely applied to embedding based document retrieval thanks to the competitive time and memory efficiency. Originally, VQ is learned to minimize the reconstruction loss, i.e., the distortions between the original dense embeddings and the reconstructed embeddings after quantization. Unfortunately, such an objective is inconsistent with the goal of selecting ground-truth documents for the input query, which may cause severe loss of retrieval quality. Recent works identify such a defect, and propose to minimize the retrieval loss through contrastive learning. However, these methods intensively rely on queries with ground-truth documents, whose performance is limited by the insufficiency of labeled data. In this paper, we propose Distill-VQ, which unifies the learning of IVF and PQ within a knowledge distillation framework. In Distill-VQ, the dense embeddings are leveraged as "teachers", which predict the query's relevance to the sampled documents. The VQ modules are treated as the "students", which are learned to reproduce the predicted relevance, such that the reconstructed embeddings may fully preserve the retrieval result of the dense embeddings. By doing so, Distill-VQ is able to derive substantial training signals from the massive unlabeled data, which significantly contributes to the retrieval quality. We perform comprehensive explorations for the optimal conduct of knowledge distillation, which may provide useful insights for the learning of VQ based ANN index. We also experimentally show that the labeled data is no longer a necessity for high-quality vector quantization, which indicates Distill-VQ's strong applicability in practice.

cs.IR↗

arXiv2022

A Roadmap for Big Model

With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm. Researchers have achieved various outcomes in the construction of BMs and the BM application in many fields. At present, there is a lack of research work that sorts out the overall progress of BMs and guides the follow-up research. In this paper, we cover not only the BM technologies themselves but also the prerequisites for BM training and applications with BMs, dividing the BM review into four parts: Resource, Models, Key Technologies and Application. We introduce 16 specific BM-related topics in those four parts, they are Data, Knowledge, Computing System, Parallel Training System, Language Model, Vision Model, Multi-modal Model, Theory&Interpretability, Commonsense Reasoning, Reliability&Security, Governance, Evaluation, Machine Translation, Text Generation, Dialogue and Protein Research. In each topic, we summarize clearly the current studies and propose some future research directions. At the end of this paper, we conclude the further development of BMs in a more general view.

cs.LG↗

arXiv2022

On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark

Dialogue safety problems severely limit the real-world deployment of neural conversational models and have attracted great research interests recently. However, dialogue safety problems remain under-defined and the corresponding dataset is scarce. We propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings, with focuses on context-sensitive unsafety, which is under-explored in prior works. To spur research in this direction, we compile DiaSafety, a dataset with rich context-sensitive unsafe examples. Experiments show that existing safety guarding tools fail severely on our dataset. As a remedy, we train a dialogue safety classifier to provide a strong baseline for context-sensitive dialogue unsafety detection. With our classifier, we perform safety evaluations on popular conversational models and show that existing dialogue systems still exhibit concerning context-sensitive safety problems.

cs.CL↗

arXiv2022

Free energy landscape of two-state protein Acylphosphatase with large contact order revealed by force-dependent folding and unfolding dynamics

Acylphosphatase (AcP) is a small protein with 98 amino acid residues that catalyzes the hydrolysis of carboxyl-phosphate bonds. AcP is a typical two-state protein with slow folding rate due to its relatively large contact order in the native structure. The mechanical properties and unfolding behavior of AcP has been studied by atomic force microscope. But the folding and unfolding dynamics at low forces has not been reported. Here using stable magnetic tweezers, we measured the force-dependent folding rates within a force range from 1 pN to 3 pN, and unfolding rates from 15 pN to 40 pN. The obtained unfolding rates show different force sensitivities at forces below and above ~27 pN, which determines a free energy landscape with two energy barriers. Our results indicate that the free energy landscape of small globule proteins have general Bactrian camel shape, and large contact order of the native state produces a high barrier dominate at low forces.

cond-mat.soft↗

arXiv2022

Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval

Ad-hoc search calls for the selection of appropriate answers from a massive-scale corpus. Nowadays, the embedding-based retrieval (EBR) becomes a promising solution, where deep learning based document representation and ANN search techniques are allied to handle this task. However, a major challenge is that the ANN index can be too large to fit into memory, given the considerable size of answer corpus. In this work, we tackle this problem with Bi-Granular Document Representation, where the lightweight sparse embeddings are indexed and standby in memory for coarse-grained candidate search, and the heavyweight dense embeddings are hosted in disk for fine-grained post verification. For the best of retrieval accuracy, a Progressive Optimization framework is designed. The sparse embeddings are learned ahead for high-quality search of candidates. Conditioned on the candidate distribution induced by the sparse embeddings, the dense embeddings are continuously learned to optimize the discrimination of ground-truth from the shortlisted candidates. Besides, two techniques: the contrastive quantization and the locality-centric sampling are introduced for the learning of sparse and dense embeddings, which substantially contribute to their performances. Thanks to the above features, our method effectively handles massive-scale EBR with strong advantages in accuracy: with up to +4.3% recall gain on million-scale corpus, and up to +17.5% recall gain on billion-scale corpus. Besides, Our method is applied to a major sponsored search platform with substantial gains on revenue (+1.95%), Recall (+1.01%) and CTR (+0.49%). Our code is available at https://github.com/microsoft/BiDR.

cs.IR↗

arXiv2022

Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL

Solving goal-conditioned tasks with sparse rewards using self-supervised learning is promising because of its simplicity and stability over current reinforcement learning (RL) algorithms. A recent work, called Goal-Conditioned Supervised Learning (GCSL), provides a new learning framework by iteratively relabeling and imitating self-generated experiences. In this paper, we revisit the theoretical property of GCSL -- optimizing a lower bound of the goal reaching objective, and extend GCSL as a novel offline goal-conditioned RL algorithm. The proposed method is named Weighted GCSL (WGCSL), in which we introduce an advanced compound weight consisting of three parts (1) discounted weight for goal relabeling, (2) goal-conditioned exponential advantage weight, and (3) best-advantage weight. Theoretically, WGCSL is proved to optimize an equivalent lower bound of the goal-conditioned RL objective and generates monotonically improved policies via an iterated scheme. The monotonic property holds for any behavior policies, and therefore WGCSL can be applied to both online and offline settings. To evaluate algorithms in the offline goal-conditioned RL setting, we provide a benchmark including a range of point and simulated robot domains. Experiments in the introduced benchmark demonstrate that WGCSL can consistently outperform GCSL and existing state-of-the-art offline methods in the fully offline goal-conditioned setting.

cs.LG↗

arXiv2022

Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search

Embedding based retrieval (EBR) is a fundamental building block in many web applications. However, EBR in sponsored search is distinguished from other generic scenarios and technically challenging due to the need of serving multiple retrieval purposes: firstly, it has to retrieve high-relevance ads, which may exactly serve user's search intent; secondly, it needs to retrieve high-CTR ads so as to maximize the overall user clicks. In this paper, we present a novel representation learning framework Uni-Retriever developed for Bing Search, which unifies two different training modes knowledge distillation and contrastive learning to realize both required objectives. On one hand, the capability of making high-relevance retrieval is established by distilling knowledge from the ``relevance teacher model''. On the other hand, the capability of making high-CTR retrieval is optimized by learning to discriminate user's clicked ads from the entire corpus. The two training modes are jointly performed as a multi-objective learning process, such that the ads of high relevance and CTR can be favored by the generated embeddings. Besides the learning strategy, we also elaborate our solution for EBR serving pipeline built upon the substantially optimized DiskANN, where massive-scale EBR can be performed with competitive time and memory efficiency, and accomplished in high-quality. We make comprehensive offline and online experiments to evaluate the proposed techniques, whose findings may provide useful insights for the future development of EBR systems. Uni-Retriever has been mainstreamed as the major retrieval path in Bing's production thanks to the notable improvements on the representation and EBR serving quality.

cs.IR↗

arXiv2022

Discovering Nonlinear PDEs from Scarce Data with Physics-encoded Learning

There have been growing interests in leveraging experimental measurements to discover the underlying partial differential equations (PDEs) that govern complex physical phenomena. Although past research attempts have achieved great success in data-driven PDE discovery, the robustness of the existing methods cannot be guaranteed when dealing with low-quality measurement data. To overcome this challenge, we propose a novel physics-encoded discrete learning framework for discovering spatiotemporal PDEs from scarce and noisy data. The general idea is to (1) firstly introduce a novel deep convolutional-recurrent network, which can encode prior physics knowledge (e.g., known PDE terms, assumed PDE structure, initial/boundary conditions, etc.) while remaining flexible on representation capability, to accurately reconstruct high-fidelity data, and (2) perform sparse regression with the reconstructed data to identify the explicit form of the governing PDEs. We validate our method on three nonlinear PDE systems. The effectiveness and superiority of the proposed method over baseline models are demonstrated.

cs.LG↗

arXiv2022

Localized Graph Collaborative Filtering

User-item interactions in recommendations can be naturally de-noted as a user-item bipartite graph. Given the success of graph neural networks (GNNs) in graph representation learning, GNN-based C methods have been proposed to advance recommender systems. These methods often make recommendations based on the learned user and item embeddings. However, we found that they do not perform well wit sparse user-item graphs which are quite common in real-world recommendations. Therefore, in this work, we introduce a novel perspective to build GNN-based CF methods for recommendations which leads to the proposed framework Localized Graph Collaborative Filtering (LGCF). One key advantage of LGCF is that it does not need to learn embeddings for each user and item, which is challenging in sparse scenarios. Alternatively, LGCF aims at encoding useful CF information into a localized graph and making recommendations based on such graph. Extensive experiments on various datasets validate the effectiveness of LGCF especially in sparse scenarios. Furthermore, empirical results demonstrate that LGCF provides complementary information to the embedding-based CF model which can be utilized to boost recommendation performance.

cs.IR↗

arXiv2021

Convergence on a symmetric accelerated stochastic ADMM with larger stepsizes

In this paper, we develop a symmetric accelerated stochastic Alternating Direction Method of Multipliers (SAS-ADMM) for solving separable convex optimization problems with linear constraints. The objective function is the sum of a possibly nonsmooth convex function and an average function of many smooth convex functions. Our proposed algorithm combines both ideas of ADMM and the techniques of accelerated stochastic gradient methods possibly with variance reduction to solve the smooth subproblem. One main feature of SAS-ADMM is that its dual variable is symmetrically updated after each update of the separated primal variable, which would allow a more flexible and larger convergence region of the dual variable compared with that of standard deter-ministic or stochastic ADMM. This new stochastic optimization algorithm is shown to have ergodic converge in expectation with O(1/T) convergence rate, where T is the number of outer iterations. Our preliminary experiments indicate the proposed algorithm is very effective for solving separable optimization problems from big-data applications. Finally, 3-block extensions of the algorithm and its variant of an accelerated stochastic augmented Lagrangian method are discussed in the appendix.

math.OC↗

arXiv2021

Hierarchical Topometric Representation of 3D Robotic Maps

In this paper, we propose a method for generating a hierarchical, volumetric topological map from 3D point clouds. There are three basic hierarchical levels in our map: $storey - region - volume$. The advantages of our method are reflected in both input and output. In terms of input, we accept multi-storey point clouds and building structures with sloping roofs or ceilings. In terms of output, we can generate results with metric information of different dimensionality, that are suitable for different robotics applications. The algorithm generates the volumetric representation by generating $volumes$ from a 3D voxel occupancy map. We then add $passage$s (connections between $volumes$), combine small $volumes$ into a big $region$ and use a 2D segmentation method for better topological representation. We evaluate our method on several freely available datasets. The experiments highlight the advantages of our approach.

cs.RO↗