arXiv subjects

Yu Cao

Publications and source records attributed to Yu Cao.

At least 109 records · Page 6Linked to original sources

arXiv2022

Interpretable Proof Generation via Iterative Backward Reasoning

We present IBR, an Iterative Backward Reasoning model to solve the proof generation tasks on rule-based Question Answering (QA), where models are required to reason over a series of textual rules and facts to find out the related proof path and derive the final answer. We handle the limitations of existed works in two folds: 1) enhance the interpretability of reasoning procedures with detailed tracking, by predicting nodes and edges in the proof path iteratively backward from the question; 2) promote the efficiency and accuracy via reasoning on the elaborate representations of nodes and history paths, without any intermediate texts that may introduce external noise during proof generation. There are three main modules in IBR, QA and proof strategy prediction to obtain the answer and offer guidance for the following procedure; parent node prediction to determine a node in the existing proof that a new child node will link to; child node prediction to find out which new node will be added to the proof. Experiments on both synthetic and paraphrased datasets demonstrate that IBR has better in-domain performance as well as cross-domain transferability than several strong baselines. Our code and models are available at https://github.com/find-knowledge/IBR .

cs.CL↗

arXiv2022

COIN: Communication-Aware In-Memory Acceleration for Graph Convolutional Networks

Graph convolutional networks (GCNs) have shown remarkable learning capabilities when processing graph-structured data found inherently in many application areas. GCNs distribute the outputs of neural networks embedded in each vertex over multiple iterations to take advantage of the relations captured by the underlying graphs. Consequently, they incur a significant amount of computation and irregular communication overheads, which call for GCN-specific hardware accelerators. To this end, this paper presents a communication-aware in-memory computing architecture (COIN) for GCN hardware acceleration. Besides accelerating the computation using custom compute elements (CE) and in-memory computing, COIN aims at minimizing the intra- and inter-CE communication in GCN operations to optimize the performance and energy efficiency. Experimental evaluations with widely used datasets show up to 105x improvement in energy consumption compared to state-of-the-art GCN accelerator.

cs.AR↗

arXiv2022

A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation

Towards building intelligent dialogue agents, there has been a growing interest in introducing explicit personas in generation models. However, with limited persona-based dialogue data at hand, it may be difficult to train a dialogue generation model well. We point out that the data challenges of this generation task lie in two aspects: first, it is expensive to scale up current persona-based dialogue datasets; second, each data sample in this task is more complex to learn with than conventional dialogue data. To alleviate the above data issues, we propose a data manipulation method, which is model-agnostic to be packed with any persona-based dialogue generation model to improve its performance. The original training samples will first be distilled and thus expected to be fitted more easily. Next, we show various effective ways that can diversify such easier distilled data. A given base model will then be trained via the constructed data curricula, i.e. first on augmented distilled samples and then on original ones. Experiments illustrate the superiority of our method with two strong base dialogue models (Transformer encoder-decoder and GPT2).

cs.CL↗

arXiv2022

A Knowledge-Based Decision Support System for In Vitro Fertilization Treatment

In Vitro Fertilization (IVF) is the most widely used Assisted Reproductive Technology (ART). IVF usually involves controlled ovarian stimulation, oocyte retrieval, fertilization in the laboratory with subsequent embryo transfer. The first two steps correspond with follicular phase of females and ovulation in their menstrual cycle. Therefore, we refer to it as the treatment cycle in our paper. The treatment cycle is crucial because the stimulation medications in IVF treatment are applied directly on patients. In order to optimize the stimulation effects and lower the side effects of the stimulation medications, prompt treatment adjustments are in need. In addition, the quality and quantity of the retrieved oocytes have a significant effect on the outcome of the following procedures. To improve the IVF success rate, we propose a knowledge-based decision support system that can provide medical advice on the treatment protocol and medication adjustment for each patient visit during IVF treatment cycle. Our system is efficient in data processing and light-weighted which can be easily embedded into electronic medical record systems. Moreover, an oocyte retrieval oriented evaluation demonstrates that our system performs well in terms of accuracy of advice for the protocols and medications.

cs.AI↗

arXiv2022

Dual-CLVSA: a Novel Deep Learning Approach to Predict Financial Markets with Sentiment Measurements

It is a challenging task to predict financial markets. The complexity of this task is mainly due to the interaction between financial markets and market participants, who are not able to keep rational all the time, and often affected by emotions such as fear and ecstasy. Based on the state-of-the-art approach particularly for financial market predictions, a hybrid convolutional LSTM Based variational sequence-to-sequence model with attention (CLVSA), we propose a novel deep learning approach, named dual-CLVSA, to predict financial market movement with both trading data and the corresponding social sentiment measurements, each through a separate sequence-to-sequence channel. We evaluate the performance of our approach with backtesting on historical trading data of SPDR SP 500 Trust ETF over eight years. The experiment results show that dual-CLVSA can effectively fuse the two types of data, and verify that sentiment measurements are not only informative for financial market predictions, but they also contain extra profitable features to boost the performance of our predicting system.

q-fin.ST↗

arXiv2021

Gradient-based Novelty Detection Boosted by Self-supervised Binary Classification

Novelty detection aims to automatically identify out-of-distribution (OOD) data, without any prior knowledge of them. It is a critical step in data monitoring, behavior analysis and other applications, helping enable continual learning in the field. Conventional methods of OOD detection perform multi-variate analysis on an ensemble of data or features, and usually resort to the supervision with OOD data to improve the accuracy. In reality, such supervision is impractical as one cannot anticipate the anomalous data. In this paper, we propose a novel, self-supervised approach that does not rely on any pre-defined OOD data: (1) The new method evaluates the Mahalanobis distance of the gradients between the in-distribution and OOD data. (2) It is assisted by a self-supervised binary classifier to guide the label selection to generate the gradients, and maximize the Mahalanobis distance. In the evaluation with multiple datasets, such as CIFAR-10, CIFAR-100, SVHN and TinyImageNet, the proposed approach consistently outperforms state-of-the-art supervised and unsupervised methods in the area under the receiver operating characteristic (AUROC) and area under the precision-recall curve (AUPR) metrics. We further demonstrate that this detector is able to accurately learn one OOD class in continual learning.

cs.LG↗

arXiv2021

A Joint Beamforming Design and Integrated CPM-LFM Signal for Dual-functional Radar-communication Systems

The dual-functional radar-communication (DFRC) system is an attractive technique, since it can support both wireless communications and radar by a unified hardware platform with real-time cooperation. Considering the appealing feature of multiple beams, this paper proposes a precoding scheme that simultaneously support multiuser transmission and target detection, with an integrated continuous phase modulation (CPM) and linear frequency modulation (LFM) signal, based on the designed dual mode framework. Similarly to the conception of communication rate, this paper defines radar rate to unify the DFRC system. Then, the maximum sum-rate that includes both the communication and radar rates is set to be the objective function. Regarding as the optimal issue is non-convex, the optimal problem is divided into two sub-issues, one is the user selection issue, and the other is the joint beamforming design and power allocation issue. A successive maximum iteration (SMI) algorithm is presented for the former issue, which can balance the performances between the sum-rate and complexity; and maximum minimization Lagrange multiplier (MMLM) iteration algorithm is utilized to solve the latter optimal issue. Moreover, we deduce the spectrum characteristic, bit error rate (BER) and ambiguity function (AF) for the proposed system. Simulation results show that our proposed system can provide appreciated sum-rate than the classical schemes, validating the efficiency of the proposed system.

eess.SP↗

arXiv2021

Plurality and Quantification in Graph Representation of Meaning

In this thesis we present a semantic representation formalism based on directed graphs and explore its linguistic adequacy and explanatory benefits in the semantics of plurality and quantification. Our graph language covers the essentials of natural language semantics using only monadic second-order variables. We define its model-theoretical interpretation in terms of graph traversal, where the relative scope of variables arises from their order of valuation. We present a unification-based mechanism for constructing semantic graphs at a simple syntax-semantics interface, where syntax as a partition function on discourse referents is implemented with categorial grammars by establishing a partly deterministic relation between semantics and syntactic distribution. This mechanism is automated to facilitate future exploration. The present graph formalism is applied to linguistic issues in distributive predication, cross-categorial conjunction, and scope permutation of quantificational expressions, including the exceptional scoping behaviors of indefinites.

cs.CL↗

arXiv2021

Serving DNN Models with Multi-Instance GPUs: A Case of the Reconfigurable Machine Scheduling Problem

Multi-Instance GPU (MIG) is a new feature introduced by NVIDIA A100 GPUs that partitions one physical GPU into multiple GPU instances. With MIG, A100 can be the most cost-efficient GPU ever for serving Deep Neural Networks (DNNs). However, discovering the most efficient GPU partitions is challenging. The underlying problem is NP-hard; moreover, it is a new abstract problem, which we define as the Reconfigurable Machine Scheduling Problem (RMS). This paper studies serving DNNs with MIG, a new case of RMS. We further propose a solution, MIG-serving. MIG- serving is an algorithm pipeline that blends a variety of newly designed algorithms and customized classic algorithms, including a heuristic greedy algorithm, Genetic Algorithm (GA), and Monte Carlo Tree Search algorithm (MCTS). We implement MIG-serving on Kubernetes. Our experiments show that compared to using A100 as-is, MIG-serving can save up to 40% of GPUs while providing the same throughput.

cs.DC↗

arXiv2021

Reversible modulation of metal-insulator transition in VO2 via chemically-induced oxygen migration

Metal-insulator transitions (MIT),an intriguing correlated phenomenon induced by the subtle competition of the electrons' repulsive Coulomb interaction and kinetic energy, is of great potential use for electronic applications due to the dramatic change in resistivity. Here, we demonstrate a reversible control of MIT in VO2 films via oxygen stoichiometry engineering. By facilely depositing and dissolving a water-soluble yet oxygen-active Sr3Al2O6 capping layer atop the VO2 at room temperature, oxygen ions can reversibly migrate between VO2 and Sr3Al2O6, resulting in a gradual suppression and a complete recovery of MIT in VO2. The migration of the oxygen ions is evidenced in a combination of transport measurement, structural characterization and first-principles calculations. This approach of chemically-induced oxygen migration using a water-dissolvable adjacent layer could be useful for advanced electronic and iontronic devices and studying oxygen stoichiometry effects on the MIT.

cond-mat.mtrl-sci↗

arXiv2021

SIAM: Chiplet-based Scalable In-Memory Acceleration with Mesh for Deep Neural Networks

In-memory computing (IMC) on a monolithic chip for deep learning faces dramatic challenges on area, yield, and on-chip interconnection cost due to the ever-increasing model sizes. 2.5D integration or chiplet-based architectures interconnect multiple small chips (i.e., chiplets) to form a large computing system, presenting a feasible solution beyond a monolithic IMC architecture to accelerate large deep learning models. This paper presents a new benchmarking simulator, SIAM, to evaluate the performance of chiplet-based IMC architectures and explore the potential of such a paradigm shift in IMC architecture design. SIAM integrates device, circuit, architecture, network-on-chip (NoC), network-on-package (NoP), and DRAM access models to realize an end-to-end system. SIAM is scalable in its support of a wide range of deep neural networks (DNNs), customizable to various network structures and configurations, and capable of efficient design space exploration. We demonstrate the flexibility, scalability, and simulation speed of SIAM by benchmarking different state-of-the-art DNNs with CIFAR-10, CIFAR-100, and ImageNet datasets. We further calibrate the simulation results with a published silicon result, SIMBA. The chiplet-based IMC architecture obtained through SIAM shows 130$\times$ and 72$\times$ improvement in energy-efficiency for ResNet-50 on the ImageNet dataset compared to Nvidia V100 and T4 GPUs.

cs.LG↗

arXiv2021

Continuous Data Assimilation For the 3D Ladyzhenskaya Model: Analysis and Computations

We analyze continuous data assimilation by nudging for the 3D Ladyzhenskaya equations. The analysis provides conditions on the spatial resolution of the observed data that guarantee synchronization to the reference solution associated with the observed, spatially coarse data. This synchronization holds even though it is not known whether the reference solution, with initial data in $L^2$, is unique; a particular reference solution is determined by the observed, coarse data. The efficacy of the algorithm in both 2D and 3D is demonstrated by numerical computations.

math.DS↗

arXiv2021

Underwater inspection and intervention dataset

This paper presents a novel dataset for the development of visual navigation and simultaneous localisation and mapping (SLAM) algorithms as well as for underwater intervention tasks. It differs from existing datasets as it contains ground truth for the vehicle's position captured by an underwater motion tracking system. The dataset contains distortion-free and rectified stereo images along with the calibration parameters of the stereo camera setup. Furthermore, the experiments were performed and recorded in a controlled environment, where current and waves could be generated allowing the dataset to cover a wide range of conditions - from calm water to waves and currents of significant strength.

cs.CV↗

arXiv2021

Impact of On-Chip Interconnect on In-Memory Acceleration of Deep Neural Networks

With the widespread use of Deep Neural Networks (DNNs), machine learning algorithms have evolved in two diverse directions -- one with ever-increasing connection density for better accuracy and the other with more compact sizing for energy efficiency. The increase in connection density increases on-chip data movement, which makes efficient on-chip communication a critical function of the DNN accelerator. The contribution of this work is threefold. First, we illustrate that the point-to-point (P2P)-based interconnect is incapable of handling a high volume of on-chip data movement for DNNs. Second, we evaluate P2P and network-on-chip (NoC) interconnect (with a regular topology such as a mesh) for SRAM- and ReRAM-based in-memory computing (IMC) architectures for a range of DNNs. This analysis shows the necessity for the optimal interconnect choice for an IMC DNN accelerator. Finally, we perform an experimental evaluation for different DNNs to empirically obtain the performance of the IMC architecture with both NoC-tree and NoC-mesh. We conclude that, at the tile level, NoC-tree is appropriate for compact DNNs employed at the edge, and NoC-mesh is necessary to accelerate DNNs with high connection density. Furthermore, we propose a technique to determine the optimal choice of interconnect for any given DNN. In this technique, we use analytical models of NoC to evaluate end-to-end communication latency of any given DNN. We demonstrate that the interconnect optimization in the IMC architecture results in up to 6$\times$ improvement in energy-delay-area product for VGG-19 inference compared to the state-of-the-art ReRAM-based IMC architectures.

cs.AR↗

arXiv2021

Alternate Model Growth and Pruning for Efficient Training of Recommendation Systems

Deep learning recommendation systems at scale have provided remarkable gains through increasing model capacity (i.e. wider and deeper neural networks), but it comes at significant training cost and infrastructure cost. Model pruning is an effective technique to reduce computation overhead for deep neural networks by removing redundant parameters. However, modern recommendation systems are still thirsty for model capacity due to the demand for handling big data. Thus, pruning a recommendation model at scale results in a smaller model capacity and consequently lower accuracy. To reduce computation cost without sacrificing model capacity, we propose a dynamic training scheme, namely alternate model growth and pruning, to alternatively construct and prune weights in the course of training. Our method leverages structured sparsification to reduce computational cost without hurting the model capacity at the end of offline training so that a full-size model is available in the recurring training stage to learn new data in real-time. To the best of our knowledge, this is the first work to provide in-depth experiments and discussion of applying structural dynamics to recommendation systems at scale to reduce training cost. The proposed method is validated with an open-source deep-learning recommendation model (DLRM) and state-of-the-art industrial-scale production models.

cs.IR↗

arXiv2021

Enhanced metal-insulator transition in freestanding VO2 down to 5 nm thickness

Ultrathin freestanding membranes with a pronounced metal-insulator transition (MIT) provides huge potential in future flexible electronic applications as well as a unique aspect of the study of lattice-electron interplay. However, the reduction of the thickness to an ultrathin region (a few nm) is typically detrimental to the MIT in epitaxial films, and even catastrophic for their freestanding form. Here, we report an enhanced MIT in VO2-based freestanding membranes, with a lateral size up to millimetres and VO2 thickness down to 5 nm. The VO2-membranes were detached by dissolving a Sr3Al2O6 sacrificial layer between the VO2 thin film and c-Al2O3(0001) substrate, allowing a transfer onto arbitrary surfaces. Furthermore, the MIT in the VO2-membrane was greatly enhanced by inserting an intermediate Al2O3 buffer layer. In comparison to the best available ultrathin VO2-membranes, the enhancement of MIT is over 400% at 5 nm VO2 thickness and more than one order of magnitude for VO2 above 10 nm. Our study widens the spectrum of functionality in ultrathin and large-scale membranes, and enables the potential integration of MIT into flexible electronics and photonics.

cond-mat.mtrl-sci↗

arXiv2021

DAGN: Discourse-Aware Graph Network for Logical Reasoning

Recent QA with logical reasoning questions requires passage-level relations among the sentences. However, current approaches still focus on sentence-level relations interacting among tokens. In this work, we explore aggregating passage-level clues for solving logical reasoning QA by using discourse-based information. We propose a discourse-aware graph network (DAGN) that reasons relying on the discourse structure of the texts. The model encodes discourse information as a graph with elementary discourse units (EDUs) and discourse relations, and learns the discourse-aware features via a graph network for downstream QA tasks. Experiments are conducted on two logical reasoning QA datasets, ReClor and LogiQA, and our proposed DAGN achieves competitive results. The source code is available at https://github.com/Eleanor-H/DAGN.

cs.CL↗

arXiv2021

CLVSA: A Convolutional LSTM Based Variational Sequence-to-Sequence Model with Attention for Predicting Trends of Financial Markets

Financial markets are a complex dynamical system. The complexity comes from the interaction between a market and its participants, in other words, the integrated outcome of activities of the entire participants determines the markets trend, while the markets trend affects activities of participants. These interwoven interactions make financial markets keep evolving. Inspired by stochastic recurrent models that successfully capture variability observed in natural sequential data such as speech and video, we propose CLVSA, a hybrid model that consists of stochastic recurrent networks, the sequence-to-sequence architecture, the self- and inter-attention mechanism, and convolutional LSTM units to capture variationally underlying features in raw financial trading data. Our model outperforms basic models, such as convolutional neural network, vanilla LSTM network, and sequence-to-sequence model with attention, based on backtesting results of six futures from January 2010 to December 2017. Our experimental results show that, by introducing an approximate posterior, CLVSA takes advantage of an extra regularizer based on the Kullback-Leibler divergence to prevent itself from overfitting traps.

q-fin.ST↗