arXiv subjects

Jian Tang

Publications and source records attributed to Jian Tang.

At least 307 records · Page 17Linked to original sources

arXiv2020

Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs

This paper studies few-shot relation extraction, which aims at predicting the relation for a pair of entities in a sentence by training with a few labeled examples in each relation. To more effectively generalize to new relations, in this paper we study the relationships between different relations and propose to leverage a global relation graph. We propose a novel Bayesian meta-learning approach to effectively learn the posterior distribution of the prototype vectors of relations, where the initial prior of the prototype vectors is parameterized with a graph neural network on the global relation graph. Moreover, to effectively optimize the posterior distribution of the prototype vectors, we propose to use the stochastic gradient Langevin dynamics, which is related to the MAML algorithm but is able to handle the uncertainty of the prototype vectors. The whole framework can be effectively and efficiently optimized in an end-to-end fashion. Experiments on two benchmark datasets prove the effectiveness of our proposed approach against competitive baselines in both the few-shot and zero-shot settings.

cs.LG↗

arXiv2020

An Advert Creation System for 3D Product Placements

Over the past decade, the evolution of video-sharing platforms has attracted a significant amount of investments on contextual advertising. The common contextual advertising platforms utilize the information provided by users to integrate 2D visual ads into videos. The existing platforms face many technical challenges such as ad integration with respect to occluding objects and 3D ad placement. This paper presents a Video Advertisement Placement & Integration (Adverts) framework, which is capable of perceiving the 3D geometry of the scene and camera motion to blend 3D virtual objects in videos and create the illusion of reality. The proposed framework contains several modules such as monocular depth estimation, object segmentation, background-foreground separation, alpha matting and camera tracking. Our experiments conducted using Adverts framework indicates the significant potential of this system in contextual ad integration, and pushing the limits of advertising industry using mixed reality technologies.

cs.CV↗

arXiv2020

Adversarial Meta-Learning

Meta-learning enables a model to learn from very limited data to undertake a new task. In this paper, we study the general meta-learning with adversarial samples. We present a meta-learning algorithm, ADML (ADversarial Meta-Learner), which leverages clean and adversarial samples to optimize the initialization of a learning model in an adversarial manner. ADML leads to the following desirable properties: 1) it turns out to be very effective even in the cases with only clean samples; 2) it is robust to adversarial samples, i.e., unlike other meta-learning algorithms, it only leads to a minor performance degradation when there are adversarial samples; 3) it sheds light on tackling the cases with limited and even contaminated samples. It has been shown by extensive experimental results that ADML consistently outperforms three representative meta-learning algorithms in the cases involving adversarial samples, on two widely-used image datasets, MiniImageNet and CIFAR100, in terms of both accuracy and robustness.

cs.LG↗

arXiv2020

Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning

Over the last decade, there has been significant progress in the field of machine learning for de novo drug design, particularly in deep generative models. However, current generative approaches exhibit a significant challenge as they do not ensure that the proposed molecular structures can be feasibly synthesized nor do they provide the synthesis routes of the proposed small molecules, thereby seriously limiting their practical applicability. In this work, we propose a novel forward synthesis framework powered by reinforcement learning (RL) for de novo drug design, Policy Gradient for Forward Synthesis (PGFS), that addresses this challenge by embedding the concept of synthetic accessibility directly into the de novo drug design system. In this setup, the agent learns to navigate through the immense synthetically accessible chemical space by subjecting commercially available small molecule building blocks to valid chemical reactions at every time step of the iterative virtual multi-step synthesis process. The proposed environment for drug discovery provides a highly challenging test-bed for RL algorithms owing to the large state space and high-dimensional continuous action space with hierarchical actions. PGFS achieves state-of-the-art performance in generating structures with high QED and penalized clogP. Moreover, we validate PGFS in an in-silico proof-of-concept associated with three HIV targets. Finally, we describe how the end-to-end training conceptualized in this study represents an important paradigm in radically expanding the synthesizable chemical space and automating the drug discovery process.

cs.LG↗

arXiv2020

Domain Conditioned Adaptation Network

Tremendous research efforts have been made to thrive deep domain adaptation (DA) by seeking domain-invariant features. Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while integrating a totally shared convolutional architecture for source and target. However, we argue that such strongly-shared convolutional layers might be harmful for domain-specific feature learning when source and target data distribution differs to a large extent. In this paper, we relax a shared-convnets assumption made by previous DA methods and propose a Domain Conditioned Adaptation Network (DCAN), which aims to excite distinct convolutional channels with a domain conditioned channel attention mechanism. As a result, the critical low-level domain-dependent knowledge could be explored appropriately. As far as we know, this is the first work to explore the domain-wise convolutional channel activation for deep DA networks. Moreover, to effectively align high-level feature distributions across two domains, we further deploy domain conditioned feature correction blocks after task-specific layers, which will explicitly correct the domain discrepancy. Extensive experiments on three cross-domain benchmarks demonstrate the proposed approach outperforms existing methods by a large margin, especially on very tough cross-domain learning tasks.

cs.CV↗

arXiv2020

Investigating Class-level Difficulty Factors in Multi-label Classification Problems

This work investigates the use of class-level difficulty factors in multi-label classification problems for the first time. Four class-level difficulty factors are proposed: frequency, visual variation, semantic abstraction, and class co-occurrence. Once computed for a given multi-label classification dataset, these difficulty factors are shown to have several potential applications including the prediction of class-level performance across datasets and the improvement of predictive performance through difficulty weighted optimisation. Significant improvements to mAP and AUC performance are observed for two challenging multi-label datasets (WWW Crowd and Visual Genome) with the inclusion of difficulty weighted optimisation. The proposed technique does not require any additional computational complexity during training or inference and can be extended over time with inclusion of other class-level difficulty factors.

cs.CV↗

arXiv2020

Correlated states in twisted double bilayer graphene

Electron-electron interactions play an important role in graphene and related systems and can induce exotic quantum states, especially in a stacked bilayer with a small twist angle. For bilayer graphene where the two layers are twisted by a "magic angle", flat band and strong many-body effects lead to correlated insulating states and superconductivity. In contrast to monolayer graphene, the band structure of untwisted bilayer graphene can be further tuned by a displacement field, providing an extra degree of freedom to control the flat band that should appear when two bilayers are stacked on top of each other. Here, we report the discovery and characterization of such displacement-field tunable electronic phases in twisted double bilayer graphene. We observe insulating states at a half-filled conduction band in an intermediate range of displacement fields. Furthermore, the resistance gap in the correlated insulator increases with respect to the in-plane magnetic fields and we find that the g factor according to spin Zeeman effect is ~2, indicating spin polarization at half filling. These results establish the twisted double bilayer graphene as an easily tunable platform for exploring quantum many-body states.

cond-mat.supr-con↗

arXiv2020

PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices

Model compression techniques on Deep Neural Network (DNN) have been widely acknowledged as an effective way to achieve acceleration on a variety of platforms, and DNN weight pruning is a straightforward and effective method. There are currently two mainstreams of pruning methods representing two extremes of pruning regularity: non-structured, fine-grained pruning can achieve high sparsity and accuracy, but is not hardware friendly; structured, coarse-grained pruning exploits hardware-efficient structures in pruning, but suffers from accuracy drop when the pruning rate is high. In this paper, we introduce PCONV, comprising a new sparsity dimension, -- fine-grained pruning patterns inside the coarse-grained structures. PCONV comprises two types of sparsities, Sparse Convolution Patterns (SCP) which is generated from intra-convolution kernel pruning and connectivity sparsity generated from inter-convolution kernel pruning. Essentially, SCP enhances accuracy due to its special vision properties, and connectivity sparsity increases pruning rate while maintaining balanced workload on filter computation. To deploy PCONV, we develop a novel compiler-assisted DNN inference framework and execute PCONV models in real-time without accuracy compromise, which cannot be achieved in prior work. Our experimental results show that, PCONV outperforms three state-of-art end-to-end DNN frameworks, TensorFlow-Lite, TVM, and Alibaba Mobile Neural Network with speedup up to 39.2x, 11.4x, and 6.3x, respectively, with no accuracy loss. Mobile devices can achieve real-time inference on large-scale DNNs.

cs.LG↗

arXiv2020

Spin coating TPB film on acrylics and measurement of its wavelength shifting efficiency

Scintillation light from liquid noble gas in a neutrino or dark matter experiment lies typically within the vacuum ultraviolet (VUV) region and might be strongly absorbed by surrounding materials such as light guides or photomultiplier. Tetraphenyl butadiene (TPB) is a fluorescent material and acts as a wavelength shifter (WLS) which can turn the UV light to the visible light around a peak wavelength of 425 nm, enabling the light signals to be detected easily for physics study. Compared with a traditional TPB coating method using vapor deposition, we propose an alternative technique with a spin coating procedure in order to facilitate the development of neutrino and dark matter detectors. This article introduces how to fabricate the TPB film on acrylics using the spin coating method, reports measurement of sample film thickness and roughness, shows the reemission spectrum, and quantifies the wavelength shifting efficiency (WLSE).

physics.ins-det↗

arXiv2020

GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation

Molecular graph generation is a fundamental problem for drug discovery and has been attracting growing attention. The problem is challenging since it requires not only generating chemically valid molecular structures but also optimizing their chemical properties in the meantime. Inspired by the recent progress in deep generative models, in this paper we propose a flow-based autoregressive model for graph generation called GraphAF. GraphAF combines the advantages of both autoregressive and flow-based approaches and enjoys: (1) high model flexibility for data density estimation; (2) efficient parallel computation for training; (3) an iterative sampling process, which allows leveraging chemical domain knowledge for valency checking. Experimental results show that GraphAF is able to generate 68% chemically valid molecules even without chemical knowledge rules and 100% valid molecules with chemical rules. The training process of GraphAF is two times faster than the existing state-of-the-art approach GCPN. After fine-tuning the model for goal-directed property optimization with reinforcement learning, GraphAF achieves state-of-the-art performance on both chemical property optimization and constrained property optimization.

cs.LG↗

arXiv2020

BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method

Accelerating DNN execution on various resource-limited computing platforms has been a long-standing problem. Prior works utilize l1-based group lasso or dynamic regularization such as ADMM to perform structured pruning on DNN models to leverage the parallel computing architectures. However, both of the pruning dimensions and pruning methods lack universality, which leads to degraded performance and limited applicability. To solve the problem, we propose a new block-based pruning framework that comprises a general and flexible structured pruning dimension as well as a powerful and efficient reweighted regularization method. Our framework is universal, which can be applied to both CNNs and RNNs, implying complete support for the two major kinds of computation-intensive layers (i.e., CONV and FC layers). To complete all aspects of the pruning-for-acceleration task, we also integrate compiler-based code optimization into our framework that can perform DNN inference in a real-time manner. To the best of our knowledge, it is the first time that the weight pruning framework achieves universal coverage for both CNNs and RNNs with real-time mobile acceleration and no accuracy compromise.

cs.LG↗

arXiv2020

An End-to-End Neighborhood-based Interaction Model for Knowledge-enhanced Recommendation

This paper studies graph-based recommendation, where an interaction graph is constructed from historical records and is lever-aged to alleviate data sparsity and cold start problems. We reveal an early summarization problem in existing graph-based models, and propose Neighborhood Interaction (NI) model to capture each neighbor pair (between user-side and item-side) distinctively. NI model is more expressive and can capture more complicated structural patterns behind user-item interactions. To further enrich node connectivity and utilize high-order structural information, we incorporate extra knowledge graphs (KGs) and adopt graph neural networks (GNNs) in NI, called Knowledge-enhanced NeighborhoodInteraction (KNI). Compared with the state-of-the-art recommendation methods,e.g., feature-based, meta path-based, and KG-based models, our KNI achieves superior performance in click-through rate prediction (1.1%-8.4% absolute AUC improvements) and out-performs by a wide margin in top-N recommendation on 4 real-world datasets.

cs.IR↗

arXiv2020

InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization

This paper studies learning the representations of whole graphs in both unsupervised and semi-supervised scenarios. Graph-level representations are critical in a variety of real-world applications such as predicting the properties of molecules and community analysis in social networks. Traditional graph kernel based methods are simple, yet effective for obtaining fixed-length representations for graphs but they suffer from poor generalization due to hand-crafted designs. There are also some recent methods based on language models (e.g. graph2vec) but they tend to only consider certain substructures (e.g. subtrees) as graph representatives. Inspired by recent progress of unsupervised representation learning, in this paper we proposed a novel method called InfoGraph for learning graph-level representations. We maximize the mutual information between the graph-level representation and the representations of substructures of different scales (e.g., nodes, edges, triangles). By doing so, the graph-level representations encode aspects of the data that are shared across different scales of substructures. Furthermore, we further propose InfoGraph*, an extension of InfoGraph for semi-supervised scenarios. InfoGraph* maximizes the mutual information between unsupervised graph representations learned by InfoGraph and the representations learned by existing supervised methods. As a result, the supervised encoder learns from unlabeled data while preserving the latent semantic space favored by the current supervised task. Experimental results on the tasks of graph classification and molecular property prediction show that InfoGraph is superior to state-of-the-art baselines and InfoGraph* can achieve performance competitive with state-of-the-art semi-supervised models.

cs.LG↗

arXiv2019

Precision measurements on $δ_\text{CP}$ in MOMENT

As it is very promising to expect a discovery of CP violation in the leptonic sector, the precision measurement of the Dirac CP phase $δ_\text{CP}$ is going to be one of the key interests in the future neutrino oscillation experiments. In this work, we examine the physics reach of the proposed medium baseline muon decay experiment MOMENT. In order to identify potential bottlenecks and opportunities to improve CP precision in MOMENT, we investigate the effect of statistical error, systematic uncertainties, fraction of the muon beam polarity, and adjusting the baseline length to match the first or second oscillation maximum on the precision measurement of $δ_\text{CP}$. We also simulate superbeam experiments T2K, NO$ν$A, T2HK, DUNE and T2HKK in comparison and complementary to MOMENT. To reach the precision of $δ_\text{CP}$ at 12$^\circ$ or better at 1$σ$ confidence level, we find it sufficient to combine the data of MOMENT, DUNE and T2HK.

hep-ph↗

arXiv2019

Non-standard interactions versus planet-scale neutrino oscillations

The low-energy threshold and the large detector size of Precision IceCube Next Generation Upgrade (PINGU) can make the study on neutrino oscillations with a planet-scale baseline possible. In this task, we consider the configuration that neutrinos are produced at CERN and detected in the PINGU detector, as a benchmark. We discuss its sensitivity of measuring the size of non-standard interactions (NSIs) in matter, which can be described by the parameter $ε_{αβ}$ ($α$ and $β$ are flavors of neutrinos). We find that the CERN-PINGU configuration improves $\tildeε_{μμ}\equivε_{μμ}-ε_{ττ}$ and $ε_{μτ}$ significantly compared to the next-generation accelerator neutrino experiments. Most of degeneracy problems in the precision measurements can be resolved, except the one for $\tildeε_{μμ}\sim-0.035$. Moreover, we point out that this configuration can also be used to detect the CP violation brought by NSIs. Finally, we compare the physics potential in this configuration to that for DUNE, T2HK and P2O, and find that the CERN-PINGU configuration can significantly improve the sensitivity to NSIs.

hep-ph↗

arXiv2019

Deep geometric knowledge distillation with graphs

In most cases deep learning architectures are trained disregarding the amount of operations and energy consumption. However, some applications, like embedded systems, can be resource-constrained during inference. A popular approach to reduce the size of a deep learning architecture consists in distilling knowledge from a bigger network (teacher) to a smaller one (student). Directly training the student to mimic the teacher representation can be effective, but it requires that both share the same latent space dimensions. In this work, we focus instead on relative knowledge distillation (RKD), which considers the geometry of the respective latent spaces, allowing for dimension-agnostic transfer of knowledge. Specifically we introduce a graph-based RKD method, in which graphs are used to capture the geometry of latent spaces. Using classical computer vision benchmarks, we demonstrate the ability of the proposed method to efficiently distillate knowledge from the teacher to the student, leading to better accuracy for the same budget as compared to existing RKD alternatives.

cs.LG↗

arXiv2019

Probabilistic Logic Neural Networks for Reasoning

Knowledge graph reasoning, which aims at predicting the missing facts through reasoning with the observed facts, is critical to many applications. Such a problem has been widely explored by traditional logic rule-based approaches and recent knowledge graph embedding methods. A principled logic rule-based approach is the Markov Logic Network (MLN), which is able to leverage domain knowledge with first-order logic and meanwhile handle their uncertainty. However, the inference of MLNs is usually very difficult due to the complicated graph structures. Different from MLNs, knowledge graph embedding methods (e.g. TransE, DistMult) learn effective entity and relation embeddings for reasoning, which are much more effective and efficient. However, they are unable to leverage domain knowledge. In this paper, we propose the probabilistic Logic Neural Network (pLogicNet), which combines the advantages of both methods. A pLogicNet defines the joint distribution of all possible triplets by using a Markov logic network with first-order logic, which can be efficiently optimized with the variational EM algorithm. In the E-step, a knowledge graph embedding model is used for inferring the missing triplets, while in the M-step, the weights of logic rules are updated based on both the observed and predicted triplets. Experiments on multiple knowledge graphs prove the effectiveness of pLogicNet over many competitive baselines.

cs.LG↗

arXiv2019

Identifying Candidate Spaces for Advert Implantation

Virtual advertising is an important and promising feature in the area of online advertising. It involves integrating adverts onto live or recorded videos for product placements and targeted advertisements. Such integration of adverts is primarily done by video editors in the post-production stage, which is cumbersome and time-consuming. Therefore, it is important to automatically identify candidate spaces in a video frame, wherein new adverts can be implanted. The candidate space should match the scene perspective, and also have a high quality of experience according to human subjective judgment. In this paper, we propose the use of a bespoke neural net that can assist the video editors in identifying candidate spaces. We benchmark our approach against several deep-learning architectures on a large-scale image dataset of candidate spaces of outdoor scenes. Our work is the first of its kind in this area of multimedia and augmented reality applications, and achieves the best results.

cs.CV↗