arXiv subjects

Yichi Zhang

Publications and source records attributed to Yichi Zhang.

At least 307 records · Page 17Linked to original sources

arXiv2021

Improving Conversational Recommendation System by Pretraining on Billions Scale of Knowledge Graph

Conversational Recommender Systems (CRSs) in E-commerce platforms aim to recommend items to users via multiple conversational interactions. Click-through rate (CTR) prediction models are commonly used for ranking candidate items. However, most CRSs are suffer from the problem of data scarcity and sparseness. To address this issue, we propose a novel knowledge-enhanced deep cross network (K-DCN), a two-step (pretrain and fine-tune) CTR prediction model to recommend items. We first construct a billion-scale conversation knowledge graph (CKG) from information about users, items and conversations, and then pretrain CKG by introducing knowledge graph embedding method and graph convolution network to encode semantic and structural information respectively.To make the CTR prediction model sensible of current state of users and the relationship between dialogues and items, we introduce user-state and dialogue-interaction representations based on pre-trained CKG and propose K-DCN.In K-DCN, we fuse the user-state representation, dialogue-interaction representation and other normal feature representations via deep cross network, which will give the rank of candidate items to be recommended.We experimentally prove that our proposal significantly outperforms baselines and show it's real application in Alime.

cs.IR↗

arXiv2021

Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models

Existing dialog system models require extensive human annotations and are difficult to generalize to different tasks. The recent success of large pre-trained language models such as BERT and GPT-2 (Devlin et al., 2019; Radford et al., 2019) have suggested the effectiveness of incorporating language priors in down-stream NLP tasks. However, how much pre-trained language models can help dialog response generation is still under exploration. In this paper, we propose a simple, general, and effective framework: Alternating Roles Dialog Model (ARDM). ARDM models each speaker separately and takes advantage of the large pre-trained language model. It requires no supervision from human annotations such as belief states or dialog acts to achieve effective conversations. ARDM outperforms or is on par with state-of-the-art methods on two popular task-oriented dialog datasets: CamRest676 and MultiWOZ. Moreover, we can generalize ARDM to more challenging, non-collaborative tasks such as persuasion. In persuasion tasks, ARDM is capable of generating human-like responses to persuade people to donate to a charity.

cs.CL↗

arXiv2021

Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation

Sequential recommendation as an emerging topic has attracted increasing attention due to its important practical significance. Models based on deep learning and attention mechanism have achieved good performance in sequential recommendation. Recently, the generative models based on Variational Autoencoder (VAE) have shown the unique advantage in collaborative filtering. In particular, the sequential VAE model as a recurrent version of VAE can effectively capture temporal dependencies among items in user sequence and perform sequential recommendation. However, VAE-based models suffer from a common limitation that the representational ability of the obtained approximate posterior distribution is limited, resulting in lower quality of generated samples. This is especially true for generating sequences. To solve the above problem, in this work, we propose a novel method called Adversarial and Contrastive Variational Autoencoder (ACVAE) for sequential recommendation. Specifically, we first introduce the adversarial training for sequence generation under the Adversarial Variational Bayes (AVB) framework, which enables our model to generate high-quality latent variables. Then, we employ the contrastive loss. The latent variables will be able to learn more personalized and salient characteristics by minimizing the contrastive loss. Besides, when encoding the sequence, we apply a recurrent and convolutional structure to capture global and local relationships in the sequence. Finally, we conduct extensive experiments on four real-world datasets. The experimental results show that our proposed ACVAE model outperforms other state-of-the-art methods.

cs.IR↗

arXiv2020

Cascaded Convolutional Neural Network for Automatic Myocardial Infarction Segmentation from Delayed-Enhancement Cardiac MRI

Automatic segmentation of myocardial contours and relevant areas like infraction and no-reflow is an important step for the quantitative evaluation of myocardial infarction. In this work, we propose a cascaded convolutional neural network for automatic myocardial infarction segmentation from delayed-enhancement cardiac MRI. We first use a 2D U-Net to focus on the intra-slice information to perform a preliminary segmentation. After that, we use a 3D U-Net to utilize the volumetric spatial information for a subtle segmentation. Our method is evaluated on the MICCAI 2020 EMIDEC challenge dataset and achieves average Dice score of 0.8786, 0.7124 and 0.7851 for myocardium, infarction and no-reflow respectively, outperforms all the other teams of the segmentation contest.

eess.IV↗

arXiv2020

FracBNN: Accurate and FPGA-Efficient Binary Neural Networks with Fractional Activations

Binary neural networks (BNNs) have 1-bit weights and activations. Such networks are well suited for FPGAs, as their dominant computations are bitwise arithmetic and the memory requirement is also significantly reduced. However, compared to start-of-the-art compact convolutional neural network (CNN) models, BNNs tend to produce a much lower accuracy on realistic datasets such as ImageNet. In addition, the input layer of BNNs has gradually become a major compute bottleneck, because it is conventionally excluded from binarization to avoid a large accuracy loss. This work proposes FracBNN, which exploits fractional activations to substantially improve the accuracy of BNNs. Specifically, our approach employs a dual-precision activation scheme to compute features with up to two bits, using an additional sparse binary convolution. We further binarize the input layer using a novel thermometer encoding. Overall, FracBNN preserves the key benefits of conventional BNNs, where all convolutional layers are computed in pure binary MAC operations (BMACs). We design an efficient FPGA-based accelerator for our novel BNN model that supports the fractional activations. To evaluate the performance of FracBNN under a resource-constrained scenario, we implement the entire optimized network architecture on an embedded FPGA (Xilinx Ultra96v2). Our experiments on ImageNet show that FracBNN achieves an accuracy comparable to MobileNetV2, surpassing the best-known BNN design on FPGAs with an increase of 28.9% in top-1 accuracy and a 2.5x reduction in model size. FracBNN also outperforms a recently introduced BNN model with an increase of 2.4% in top-1 accuracy while using the same model size. On the embedded FPGA device, FracBNN demonstrates the ability of real-time image classification.

cs.LG↗

arXiv2020

Logic Synthesis Meets Machine Learning: Trading Exactness for Generalization

Logic synthesis is a fundamental step in hardware design whose goal is to find structural representations of Boolean functions while minimizing delay and area. If the function is completely-specified, the implementation accurately represents the function. If the function is incompletely-specified, the implementation has to be true only on the care set. While most of the algorithms in logic synthesis rely on SAT and Boolean methods to exactly implement the care set, we investigate learning in logic synthesis, attempting to trade exactness for generalization. This work is directly related to machine learning where the care set is the training set and the implementation is expected to generalize on a validation set. We present learning incompletely-specified functions based on the results of a competition conducted at IWLS 2020. The goal of the competition was to implement 100 functions given by a set of care minterms for training, while testing the implementation using a set of validation minterms sampled from the same function. We make this benchmark suite available and offer a detailed comparative analysis of the different approaches to learning

cs.LG↗

arXiv2020

A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning

Structured belief states are crucial for user goal tracking and database query in task-oriented dialog systems. However, training belief trackers often requires expensive turn-level annotations of every user utterance. In this paper we aim at alleviating the reliance on belief state labels in building end-to-end dialog systems, by leveraging unlabeled dialog data towards semi-supervised learning. We propose a probabilistic dialog model, called the LAtent BElief State (LABES) model, where belief states are represented as discrete latent variables and jointly modeled with system responses given user inputs. Such latent variable modeling enables us to develop semi-supervised learning under the principled variational learning framework. Furthermore, we introduce LABES-S2S, which is a copy-augmented Seq2Seq model instantiation of LABES. In supervised experiments, LABES-S2S obtains strong results on three benchmark datasets of different scales. In utilizing unlabeled dialog data, semi-supervised LABES-S2S significantly outperforms both supervised-only and semi-supervised baselines. Remarkably, we can reduce the annotation demands to 50% without performance loss on MultiWOZ.

cs.CL↗

arXiv2020

Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph

Multi-hop reasoning has been widely studied in recent years to seek an effective and interpretable method for knowledge graph (KG) completion. Most previous reasoning methods are designed for dense KGs with enough paths between entities, but cannot work well on those sparse KGs that only contain sparse paths for reasoning. On the one hand, sparse KGs contain less information, which makes it difficult for the model to choose correct paths. On the other hand, the lack of evidential paths to target entities also makes the reasoning process difficult. To solve these problems, we propose a multi-hop reasoning model named DacKGR over sparse KGs, by applying novel dynamic anticipation and completion strategies: (1) The anticipation strategy utilizes the latent prediction of embedding-based models to make our model perform more potential path search over sparse KGs. (2) Based on the anticipation information, the completion strategy dynamically adds edges as additional actions during the path search, which further alleviates the sparseness problem of KGs. The experimental results on five datasets sampled from Freebase, NELL and Wikidata show that our method outperforms state-of-the-art baselines. Our codes and datasets can be obtained from https://github.com/THU-KEG/DacKGR

cs.CL↗

arXiv2020

Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations

We propose precision gating (PG), an end-to-end trainable dynamic dual-precision quantization technique for deep neural networks. PG computes most features in a low precision and only a small proportion of important features in a higher precision to preserve accuracy. The proposed approach is applicable to a variety of DNN architectures and significantly reduces the computational cost of DNN execution with almost no accuracy loss. Our experiments indicate that PG achieves excellent results on CNNs, including statically compressed mobile-friendly networks such as ShuffleNet. Compared to the state-of-the-art prediction-based quantization schemes, PG achieves the same or higher accuracy with 2.4$\times$ less compute on ImageNet. PG furthermore applies to RNNs. Compared to 8-bit uniform quantization, PG obtains a 1.2% improvement in perplexity per word with 2.7$\times$ computational cost reduction on LSTM on the Penn Tree Bank dataset. Code is available at: https://github.com/cornell-zhang/dnn-gating

cs.CV↗

arXiv2020

Paraphrase Augmented Task-Oriented Dialog Generation

Neural generative models have achieved promising performance on dialog generation tasks if given a huge data set. However, the lack of high-quality dialog data and the expensive data annotation process greatly limit their application in real-world settings. We propose a paraphrase augmented response generation (PARG) framework that jointly trains a paraphrase model and a response generation model to improve the dialog generation performance. We also design a method to automatically construct paraphrase training data set based on dialog state and dialog act labels. PARG is applicable to various dialog generation models, such as TSCP (Lei et al., 2018) and DAMD (Zhang et al., 2019). Experimental results show that the proposed framework improves these state-of-the-art dialog models further on CamRest676 and MultiWOZ. PARG also significantly outperforms other data augmentation methods in dialog generation tasks, especially under low resource settings.

cs.CL↗

arXiv2019

Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context

Conversations have an intrinsic one-to-many property, which means that multiple responses can be appropriate for the same dialog context. In task-oriented dialogs, this property leads to different valid dialog policies towards task completion. However, none of the existing task-oriented dialog generation approaches takes this property into account. We propose a Multi-Action Data Augmentation (MADA) framework to utilize the one-to-many property to generate diverse appropriate dialog responses. Specifically, we first use dialog states to summarize the dialog history, and then discover all possible mappings from every dialog state to its different valid system actions. During dialog system training, we enable the current dialog state to map to all valid system actions discovered in the previous process to create additional state-action pairs. By incorporating these additional pairs, the dialog policy learns a balanced action distribution, which further guides the dialog model to generate diverse responses. Experimental results show that the proposed framework consistently improves dialog policy diversity, and results in improved response diversity and appropriateness. Our model obtains state-of-the-art results on MultiWOZ.

cs.CL↗

arXiv2019

Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection

Event detection (ED), a sub-task of event extraction, involves identifying triggers and categorizing event mentions. Existing methods primarily rely upon supervised learning and require large-scale labeled event datasets which are unfortunately not readily available in many real-life applications. In this paper, we consider and reformulate the ED task with limited labeled data as a Few-Shot Learning problem. We propose a Dynamic-Memory-Based Prototypical Network (DMB-PN), which exploits Dynamic Memory Network (DMN) to not only learn better prototypes for event types, but also produce more robust sentence encodings for event mentions. Differing from vanilla prototypical networks simply computing event prototypes by averaging, which only consume event mentions once, our model is more robust and is capable of distilling contextual information from event mentions for multiple times due to the multi-hop mechanism of DMNs. The experiments show that DMB-PN not only deals with sample scarcity better than a series of baseline models but also performs more robustly when the variety of event types is relatively large and the instance quantity is extremely small.

cs.CL↗

arXiv2019

Ultrafast creation of overlapping Rydberg electrons in an atomic BEC and Mott-insulator lattice

An array of ultracold atoms in an optical lattice (Mott insulator) excited to a state where single electron wave-functions spatially overlap would represent a new and ideal platform to simulate exotic electronic many-body phenomena in the condensed phase. However, this highly excited non-equilibrium system is expected to be so short-lived that it has eluded observation so far. Here, we demonstrate the first step toward its realization by exciting high-lying electronic (Rydberg) states of the atomic Mott insulator with a coherent ultrashort laser pulse. Beyond a threshold principal quantum number where Rydberg orbitals of neighboring lattice sites overlap with each other, the atoms efficiently undergo spontaneous Penning ionization resulting in a drastic change of ion-counting statistics, sharp increase of avalanche ionization and the formation of an ultracold plasma. These observations signal the actual creation of exotic electronic states with overlapping wave functions, which is further confirmed by a significant difference in ionization dynamics between a Bose-Einstein condensate and a Mott insulator.

physics.atom-ph↗

arXiv2019

Bayesian Optimization for Materials Design with Mixed Quantitative and Qualitative Variables

Although Bayesian Optimization (BO) has been employed for accelerating materials design in computational materials engineering, existing works are restricted to problems with quantitative variables. However, real designs of materials systems involve both qualitative and quantitative design variables representing material compositions, microstructure morphology, and processing conditions. For mixed-variable problems, existing Bayesian Optimization (BO) approaches represent qualitative factors by dummy variables first and then fit a standard Gaussian process (GP) model with numerical variables as the surrogate model. This approach is restrictive theoretically and fails to capture complex correlations between qualitative levels. We present in this paper the integration of a novel latent-variable (LV) approach for mixed-variable GP modeling with the BO framework for materials design. LVGP is a fundamentally different approach that maps qualitative design variables to underlying numerical LV in GP, which has strong physical justification. It provides flexible parameterization and representation of qualitative factors and shows superior modeling accuracy compared to the existing methods. We demonstrate our approach through testing with numerical examples and materials design examples. It is found that in all test examples the mapped LVs provide intuitive visualization and substantial insight into the nature and effects of the qualitative factors. Though materials designs are used as examples, the method presented is generic and can be utilized for other mixed variable design optimization problems that involve expensive physics-based simulations.

stat.ML↗

arXiv2019

Designing Anisotropic Microstructures with Spectral Density Function

Materials' microstructure strongly influences its performance and is thus a critical aspect in design of functional materials. Previous efforts on microstructure mediated design mostly assume isotropy, which is not ideal when material performance is dependent on an underlying transport phenomenon. In this article, we propose an anisotropic microstructure design strategy that leverages Spectral Density Function (SDF) for rapid reconstruction of high resolution, two phase, isotropic or anisotropic microstructures in 2D and 3D. We demonstrate that SDF microstructure representation provides an intuitive method for quantifying anisotropy through a dimensionless scalar variable termed anisotropy index. The computational efficiency and low dimensional microstructure representation enabled by our method is demonstrated through an active layer design case study for Bulk Heterojunction Organic Photovoltaic Cells (OPVCs). Results indicate that optimized design, exhibiting strong anisotropy, outperforms isotropic active layer designs. Further, we show that Cross-sectional Scanning Tunneling Microscopy and Spectroscopy (XSTM/S) is as an effective tool for characterization of anisotropic microstructures.

physics.app-ph↗

arXiv2019

Sound Search by Text Description or Vocal Imitation?

Searching sounds by text labels is often difficult, as text descriptions cannot describe the audio content in detail. Query by vocal imitation bridges such gap and provides a novel way to sound search. Several algorithms for sound search by vocal imitation have been proposed and evaluated in a simulation environment, however, they have not been deployed into a real search engine nor evaluated by real users. This pilot work conducts a subjective study to compare these two approaches to sound search, and tries to answer the question of which approach works better for what kinds of sounds. To do so, we developed two web-based search engines for sound, one by vocal imitation (Vroom!) and the other by text description (TextSearch). We also developed an experimental framework to host these engines to collect statistics of user behaviors and ratings. Results showed that Vroom! received significantly higher search satisfaction ratings than TextSearch did for sound categories that were difficult for subjects to describe by text. Results also showed a better overall ease-of-use rating for Vroom! than TextSearch on the limited sound library in our experiments. These findings suggest advantages of vocal-imitation-based search for sound in practice.

cs.HC↗

arXiv2019

Data-Centric Mixed-Variable Bayesian Optimization For Materials Design

Materials design can be cast as an optimization problem with the goal of achieving desired properties, by varying material composition, microstructure morphology, and processing conditions. Existence of both qualitative and quantitative material design variables leads to disjointed regions in property space, making the search for optimal design challenging. Limited availability of experimental data and the high cost of simulations magnify the challenge. This situation calls for design methodologies that can extract useful information from existing data and guide the search for optimal designs efficiently. To this end, we present a data-centric, mixed-variable Bayesian Optimization framework that integrates data from literature, experiments, and simulations for knowledge discovery and computational materials design. Our framework pivots around the Latent Variable Gaussian Process (LVGP), a novel Gaussian Process technique which projects qualitative variables on a continuous latent space for covariance formulation, as the surrogate model to quantify "lack of data" uncertainty. Expected improvement, an acquisition criterion that balances exploration and exploitation, helps navigate a complex, nonlinear design space to locate the optimum design. The proposed framework is tested through a case study which seeks to concurrently identify the optimal composition and morphology for insulating polymer nanocomposites. We also present an extension of mixed-variable Bayesian Optimization for multiple objectives to identify the Pareto Frontier within tens of iterations. These findings project Bayesian Optimization as a powerful tool for design of engineered material systems.

physics.comp-ph↗

arXiv2019

A Latent Variable Approach to Gaussian Process Modeling with Qualitative and Quantitative Factors

Computer simulations often involve both qualitative and numerical inputs. Existing Gaussian process (GP) methods for handling this mainly assume a different response surface for each combination of levels of the qualitative factors and relate them via a multiresponse cross-covariance matrix. We introduce a substantially different approach that maps each qualitative factor to an underlying numerical latent variable (LV), with the mapped value for each level estimated similarly to the correlation parameters. This provides a parsimonious GP parameterization that treats qualitative factors the same as numerical variables and views them as effecting the response via similar physical mechanisms. This has strong physical justification, as the effects of a qualitative factor in any physics-based simulation model must always be due to some underlying numerical variables. Even when the underlying variables are many, sufficient dimension reduction arguments imply that their effects can be represented by a low-dimensional LV. This conjecture is supported by the superior predictive performance observed across a variety of examples. Moreover, the mapped LVs provide substantial insight into the nature and effects of the qualitative factors.

stat.ML↗