arXiv subjects

Ji Liu

Publications and source records attributed to Ji Liu.

At least 145 records · Page 8Linked to original sources

arXiv2022

LPFS: Learnable Polarizing Feature Selection for Click-Through Rate Prediction

In industry, feature selection is a standard but necessary step to search for an optimal set of informative feature fields for efficient and effective training of deep Click-Through Rate (CTR) models. Most previous works measure the importance of feature fields by using their corresponding continuous weights from the model, then remove the feature fields with small weight values. However, removing many features that correspond to small but not exact zero weights will inevitably hurt model performance and not be friendly to hot-start model training. There is also no theoretical guarantee that the magnitude of weights can represent the importance, thus possibly leading to sub-optimal results if using these methods. To tackle this problem, we propose a novel Learnable Polarizing Feature Selection (LPFS) method using a smoothed-$\ell^0$ function in literature. Furthermore, we extend LPFS to LPFS++ by our newly designed smoothed-$\ell^0$-liked function to select a more informative subset of features. LPFS and LPFS++ can be used as gates inserted at the input of the deep network to control the active and inactive state of each feature. When training is finished, some gates are exact zero, while others are around one, which is particularly favored by the practical hot-start training in the industry, due to no damage to the model performance before and after removing the features corresponding to exact-zero gates. Experiments show that our methods outperform others by a clear margin, and have achieved great A/B test results in KuaiShou Technology.

cs.IR↗

arXiv2022

A Hybrid Observer for Estimating the State of a Distributed Linear System

A hybrid observer is described for estimating the state of a system of the form dot x=Ax, y_i=C_ix, i=1,...,m. The system's state x is simultaneously estimated by m agents assuming agent i senses y_i and receives appropriately defined data from its neighbors. Neighbor relations are characterized by a time-varying directed graph N(t). Agent i updates its estimate x_i of x at event times t_{i1},t_{i2} ... using a local continuous-time linear observer and a local parameter estimator which iterates q times during each event time interval [t_{i(s-1)},t_{is}), s>=1, to obtain an estimate of x(t_{is}). Subject to the assumptions that N(t) is strongly connected, and the system is jointly observable, it is possible to design parameters so that x_i converges to x with a pre-assigned rate. This result holds when agents communicate asynchronously with the assumption that N(t) changes slowly. Exponential convergence is also assured if the event time sequence of the agents are slightly different, although only if the system being observed is exponentially stable; this limitation however, is a robustness issue shared by all open loop state estimators with small modeling errors. The result also holds facing abrupt changes in the number of vertices and arcs in the inter-agent communication graph upon which the algorithm depends.

cs.DC↗

arXiv2022

Cooperative Actor-Critic via TD Error Aggregation

In decentralized cooperative multi-agent reinforcement learning, agents can aggregate information from one another to learn policies that maximize a team-average objective function. Despite the willingness to cooperate with others, the individual agents may find direct sharing of information about their local state, reward, and value function undesirable due to privacy issues. In this work, we introduce a decentralized actor-critic algorithm with TD error aggregation that does not violate privacy issues and assumes that communication channels are subject to time delays and packet dropouts. The cost we pay for making such weak assumptions is an increased communication burden for every agent as measured by the dimension of the transmitted data. Interestingly, the communication burden is only quadratic in the graph size, which renders the algorithm applicable in large networks. We provide a convergence analysis under diminishing step size to verify that the agents maximize the team-average objective function.

eess.SY↗

arXiv2022

HPS-Det: Dynamic Sample Assignment with Hyper-Parameter Search for Object Detection

Sample assignment plays a prominent part in modern object detection approaches. However, most existing methods rely on manual design to assign positive / negative samples, which do not explicitly establish the relationships between sample assignment and object detection performance. In this work, we propose a novel dynamic sample assignment scheme based on hyper-parameter search. We first define the number of positive samples assigned to each ground truth as the hyper-parameters and employ a surrogate optimization algorithm to derive the optimal choices. Then, we design a dynamic sample assignment procedure to dynamically select the optimal number of positives at each training iteration. Experiments demonstrate that the resulting HPS-Det brings improved performance over different object detection baselines. Moreover, We analyze the hyper-parameter reusability when transferring between different datasets and between different backbones for object detection, which exhibits the superiority and versatility of our method.

cs.CV↗

arXiv2022

Combining Intra-Risk and Contagion Risk for Enterprise Bankruptcy Prediction Using Graph Neural Networks

Predicting the bankruptcy risk of small and medium-sized enterprises (SMEs) is an important step for financial institutions when making decisions about loans. Existing studies in both finance and AI research fields, however, tend to only consider either the intra-risk or contagion risk of enterprises, ignoring their interactions and combinatorial effects. This study for the first time considers both types of risk and their joint effects in bankruptcy prediction. Specifically, we first propose an enterprise intra-risk encoder based on statistically significant enterprise risk indicators for its intra-risk learning. Then, we propose an enterprise contagion risk encoder based on enterprise relation information from an enterprise knowledge graph for its contagion risk embedding. In particular, the contagion risk encoder includes both the newly proposed Hyper-Graph Neural Networks and Heterogeneous Graph Neural Networks, which can model contagion risk in two different aspects, i.e. common risk factors based on hyperedges and direct diffusion risk from neighbors, respectively. To evaluate the model, we collect real-world multi-sources data on SMEs and build a novel benchmark dataset called SMEsD. We provide open access to the dataset, which is expected to further promote research on financial risk analysis. Experiments on SMEsD against twelve state-of-the-art baselines demonstrate the effectiveness of the proposed model for bankruptcy prediction.

q-fin.RM↗

arXiv2022

Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond

Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction results of deep models. In recent years, many interpretation tools have been proposed to explain or reveal how deep models make decisions. In this paper, we review this line of research and try to make a comprehensive survey. Specifically, we first introduce and clarify two basic concepts -- interpretations and interpretability -- that people usually get confused about. To address the research efforts in interpretations, we elaborate the designs of a number of interpretation algorithms, from different perspectives, by proposing a new taxonomy. Then, to understand the interpretation results, we also survey the performance metrics for evaluating interpretation algorithms. Further, we summarize the current works in evaluating models' interpretability using "trustworthy" interpretation algorithms. Finally, we review and discuss the connections between deep models' interpretations and other factors, such as adversarial robustness and learning from interpretations, and we introduce several open-source libraries for interpretation algorithms and evaluation approaches.

cs.LG↗

arXiv2022

Large-scale Knowledge Distillation with Elastic Heterogeneous Computing Resources

Although more layers and more parameters generally improve the accuracy of the models, such big models generally have high computational complexity and require big memory, which exceed the capacity of small devices for inference and incurs long training time. In addition, it is difficult to afford long training time and inference time of big models even in high performance servers, as well. As an efficient approach to compress a large deep model (a teacher model) to a compact model (a student model), knowledge distillation emerges as a promising approach to deal with the big models. Existing knowledge distillation methods cannot exploit the elastic available computing resources and correspond to low efficiency. In this paper, we propose an Elastic Deep Learning framework for knowledge Distillation, i.e., EDL-Dist. The advantages of EDL-Dist are three-fold. First, the inference and the training process is separated. Second, elastic available computing resources can be utilized to improve the efficiency. Third, fault-tolerance of the training and inference processes is supported. We take extensive experimentation to show that the throughput of EDL-Dist is up to 3.125 times faster than the baseline method (online knowledge distillation) while the accuracy is similar or higher.

cs.DC↗

arXiv2022

Accelerated Federated Learning with Decoupled Adaptive Optimization

The federated learning (FL) framework enables edge clients to collaboratively learn a shared inference model while keeping privacy of training data on clients. Recently, many heuristics efforts have been made to generalize centralized adaptive optimization methods, such as SGDM, Adam, AdaGrad, etc., to federated settings for improving convergence and accuracy. However, there is still a paucity of theoretical principles on where to and how to design and utilize adaptive optimization methods in federated settings. This work aims to develop novel adaptive optimization methods for FL from the perspective of dynamics of ordinary differential equations (ODEs). First, an analytic framework is established to build a connection between federated optimization methods and decompositions of ODEs of corresponding centralized optimizers. Second, based on this analytic framework, a momentum decoupling adaptive optimization method, FedDA, is developed to fully utilize the global momentum on each local iteration and accelerate the training convergence. Last but not least, full batch gradients are utilized to mimic centralized optimization in the end of the training process to ensure the convergence and overcome the possible inconsistency caused by adaptive optimization methods.

cs.LG↗

arXiv2022

FedHiSyn: A Hierarchical Synchronous Federated Learning Framework for Resource and Data Heterogeneity

Federated Learning (FL) enables training a global model without sharing the decentralized raw data stored on multiple devices to protect data privacy. Due to the diverse capacity of the devices, FL frameworks struggle to tackle the problems of straggler effects and outdated models. In addition, the data heterogeneity incurs severe accuracy degradation of the global model in the FL training process. To address aforementioned issues, we propose a hierarchical synchronous FL framework, i.e., FedHiSyn. FedHiSyn first clusters all available devices into a small number of categories based on their computing capacity. After a certain interval of local training, the models trained in different categories are simultaneously uploaded to a central server. Within a single category, the devices communicate the local updated model weights to each other based on a ring topology. As the efficiency of training in the ring topology prefers devices with homogeneous resources, the classification based on the computing capacity mitigates the impact of straggler effects. Besides, the combination of the synchronous update of multiple categories and the device communication within a single category help address the data heterogeneity issue while achieving high accuracy. We evaluate the proposed framework based on MNIST, EMNIST, CIFAR10 and CIFAR100 datasets and diverse heterogeneous settings of devices. Experimental results show that FedHiSyn outperforms six baseline methods, e.g., FedAvg, SCAFFOLD, and FedAT, in terms of training accuracy and efficiency.

cs.DC↗

arXiv2022

Stochastic Gradient Descent without Full Data Shuffle

Stochastic gradient descent (SGD) is the cornerstone of modern machine learning (ML) systems. Despite its computational efficiency, SGD requires random data access that is inherently inefficient when implemented in systems that rely on block-addressable secondary storage such as HDD and SSD, e.g., TensorFlow/PyTorch and in-DB ML systems over large files. To address this impedance mismatch, various data shuffling strategies have been proposed to balance the convergence rate of SGD (which favors randomness) and its I/O performance (which favors sequential access). In this paper, we first conduct a systematic empirical study on existing data shuffling strategies, which reveals that all existing strategies have room for improvement -- they all suffer in terms of I/O performance or convergence rate. With this in mind, we propose a simple but novel hierarchical data shuffling strategy, CorgiPile. Compared with existing strategies, CorgiPile avoids a full data shuffle while maintaining comparable convergence rate of SGD as if a full shuffle were performed. We provide a non-trivial theoretical analysis of CorgiPile on its convergence behavior. We further integrate CorgiPile into PyTorch by designing new parallel/distributed shuffle operators inside a new CorgiPileDataSet API. We also integrate CorgiPile into PostgreSQL by introducing three new physical operators with optimizations. Our experimental results show that CorgiPile can achieve comparable convergence rate with the full shuffle based SGD for both deep learning and generalized linear models. For deep learning models on ImageNet dataset, CorgiPile is 1.5X faster than PyTorch with full data shuffle. For in-DB ML with linear models, CorgiPile is 1.6X-12.8X faster than two state-of-the-art in-DB ML systems, Apache MADlib and Bismarck, on both HDD and SSD.

cs.LG↗

arXiv2022

E^2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles

Unmanned Aerial Vehicles (UAVs) based video text spotting has been extensively used in civil and military domains. UAV's limited battery capacity motivates us to develop an energy-efficient video text spotting solution. In this paper, we first revisit RCNN's crop & resize training strategy and empirically find that it outperforms aligned RoI sampling on a real-world video text dataset captured by UAV. To reduce energy consumption, we further propose a multi-stage image processor that takes videos' redundancy, continuity, and mixed degradation into account. Lastly, the model is pruned and quantized before deployed on Raspberry Pi. Our proposed energy-efficient video text spotting solution, dubbed as E^2VTS, outperforms all previous methods by achieving a competitive tradeoff between energy efficiency and performance. All our codes and pre-trained models are available at https://github.com/wuzhenyusjtu/LPCVC20-VideoTextSpotting.

cs.CV↗

arXiv2022

Multi-Entanglement Routing Design over Quantum Networks

Quantum networks are considered as a promising future platform for quantum information exchange and quantum applications, which have capabilities far beyond the traditional communication networks. Remote quantum entanglement is an essential component of a quantum network. How to efficiently design a multi-routing entanglement protocol is a fundamental yet challenging problem. In this paper, we study a quantum entanglement routing problem to simultaneously maximize the number of quantum-user pairs and their expected throughput. Our approach is to formulate the problem as two sequential integer programming steps. We propose efficient entanglement routing algorithms for the two integer programming steps and analyze their time complexity and performance bounds. Results of evaluation highlight that our approach outperforms existing solutions in both served quantum-user pairs numbers and the network expected throughput.

cs.NI↗

arXiv2022

Not All SWAPs Have the Same Cost: A Case for Optimization-Aware Qubit Routing

Despite rapid advances in quantum computing technologies, the qubit connectivity limitation remains to be a critical challenge. Both near-term NISQ quantum computers and relatively long-term scalable quantum architectures do not offer full connectivity. As a result, quantum circuits may not be directly executed on quantum hardware, and a quantum compiler needs to perform qubit routing to make the circuit compatible with the device layout. During the qubit routing step, the compiler inserts SWAP gates and performs circuit transformations. Given the connectivity topology of the target hardware, there are typically multiple qubit routing candidates. The state-of-the-art compilers use a cost function to evaluate the number of SWAP gates for different routes and then select the one with the minimum number of SWAP gates. After qubit routing, the quantum compiler performs gate optimizations upon the circuit with the newly inserted SWAP gates. In this paper, we observe that the aforementioned qubit routing is not optimal, and qubit routing should \textit{not} be independent on subsequent gate optimizations. We find that with the consideration of gate optimizations, not all of the SWAP gates have the same basis-gate cost. These insights lead to the development of our qubit routing algorithm, NASSC (Not All Swaps have the Same Cost). NASSC is the first algorithm that considers the subsequent optimizations during the routing step. Our optimization-aware qubit routing leads to better routing decisions and benefits subsequent optimizations. We also propose a new optimization-aware decomposition for the inserted SWAP gates. Our experiments show that the routing overhead compiled with our routing algorithm is reduced by up to $69.30\%$ ($21.30\%$ on average) in the number of CNOT gates and up to $43.50\%$ ($7.61\%$ on average) in the circuit depth compared with the state-of-the-art scheme, SABRE.

quant-ph↗

arXiv2022

Dynamic Sparse R-CNN

Sparse R-CNN is a recent strong object detection baseline by set prediction on sparse, learnable proposal boxes and proposal features. In this work, we propose to improve Sparse R-CNN with two dynamic designs. First, Sparse R-CNN adopts a one-to-one label assignment scheme, where the Hungarian algorithm is applied to match only one positive sample for each ground truth. Such one-to-one assignment may not be optimal for the matching between the learned proposal boxes and ground truths. To address this problem, we propose dynamic label assignment (DLA) based on the optimal transport algorithm to assign increasing positive samples in the iterative training stages of Sparse R-CNN. We constrain the matching to be gradually looser in the sequential stages as the later stage produces the refined proposals with improved precision. Second, the learned proposal boxes and features remain fixed for different images in the inference process of Sparse R-CNN. Motivated by dynamic convolution, we propose dynamic proposal generation (DPG) to assemble multiple proposal experts dynamically for providing better initial proposal boxes and features for the consecutive training stages. DPG thereby can derive sample-dependent proposal boxes and features for inference. Experiments demonstrate that our method, named Dynamic Sparse R-CNN, can boost the strong Sparse R-CNN baseline with different backbones for object detection. Particularly, Dynamic Sparse R-CNN reaches the state-of-the-art 47.2% AP on the COCO 2017 validation set, surpassing Sparse R-CNN by 2.2% AP with the same ResNet-50 backbone.

cs.CV↗

arXiv2022

Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification

Recently, self-attention mechanisms have shown impressive performance in various NLP and CV tasks, which can help capture sequential characteristics and derive global information. In this work, we explore how to extend self-attention modules to better learn subtle feature embeddings for recognizing fine-grained objects, e.g., different bird species or person identities. To this end, we propose a dual cross-attention learning (DCAL) algorithm to coordinate with self-attention learning. First, we propose global-local cross-attention (GLCA) to enhance the interactions between global images and local high-response regions, which can help reinforce the spatial-wise discriminative clues for recognition. Second, we propose pair-wise cross-attention (PWCA) to establish the interactions between image pairs. PWCA can regularize the attention learning of an image by treating another image as distractor and will be removed during inference. We observe that DCAL can reduce misleading attentions and diffuse the attention response to discover more complementary parts for recognition. We conduct extensive evaluations on fine-grained visual categorization and object re-identification. Experiments demonstrate that DCAL performs on par with state-of-the-art methods and consistently improves multiple self-attention baselines, e.g., surpassing DeiT-Tiny and ViT-Base by 2.8% and 2.4% mAP on MSMT17, respectively.

cs.CV↗

arXiv2022

FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server

Despite achieving remarkable performance, Federated Learning (FL) suffers from two critical challenges, i.e., limited computational resources and low training efficiency. In this paper, we propose a novel FL framework, i.e., FedDUAP, with two original contributions, to exploit the insensitive data on the server and the decentralized data in edge devices to further improve the training efficiency. First, a dynamic server update algorithm is designed to exploit the insensitive data on the server, in order to dynamically determine the optimal steps of the server update for improving the convergence and accuracy of the global model. Second, a layer-adaptive model pruning method is developed to perform unique pruning operations adapted to the different dimensions and importance of multiple layers, to achieve a good balance between efficiency and effectiveness. By integrating the two original techniques together, our proposed FL model, FedDUAP, significantly outperforms baseline approaches in terms of accuracy (up to 4.8% higher), efficiency (up to 2.8 times faster), and computational cost (up to 61.9% smaller).

cs.DC↗

arXiv2022

Digging into Primary Financial Market: Challenges and Opportunities of Adopting Blockchain

Since the emergence of blockchain technology, its application in the financial market has always been an area of focus and exploration by all parties. With the characteristics of anonymity, trust, tamper-proof, etc., blockchain technology can effectively solve some problems faced by the financial market, such as trust issues and information asymmetry issues. To deeply understand the application scenarios of blockchain in the financial market, the issue of securities issuance and trading in the primary market is a problem that must be studied clearly. We conducted an empirical study to investigate the main difficulties faced by primary market participants in their business practices and the potential challenges of the deepening application of blockchain technology in the primary market. We adopted a hybrid method combining interviews (qualitative methods) and surveys (quantitative methods) to conduct this research in two stages. In the first stage, we interview 15 major primary market participants with different backgrounds and expertise. In the second phase, we conducted a verification survey of 54 primary market practitioners to confirm various insights from the interviews, including challenges and desired improvements. Our interviews and survey results revealed several significant challenges facing blockchain applications in the primary market: complex due diligence, mismatch, and difficult monitoring. On this basis, we believe that our future research can focus on some aspects of these challenges.

q-fin.ST↗

arXiv2022

Resilient Constrained Consensus over Complete Graphs via Feasibility Redundancy

This paper considers a resilient high-dimensional constrained consensus problem and studies a resilient distributed algorithm for complete graphs. For convex constrained sets with a singleton intersection, a sufficient condition on feasibility redundancy and set regularity for reaching a desired consensus exponentially fast in the presence of Byzantine agents is derived, which can be directly applied to polyhedral sets. A necessary condition on feasibility redundancy for the resilient constrained consensus problem to be solvable is also provided.

eess.SY↗