arXiv subjects

Dapeng Liu

Publications and source records attributed to Dapeng Liu.

26 records · Page 2Linked to original sources

arXiv2022

Achieving high-temperature ferromagnetism by means of magnetic ions dimerization

Magnetic two-dimensional materials have potential application in next-generation electronic devices and have stimulated extensive interest in condensed matter physics and material fields. However, how to realize high-temperature ferromagnetism in two-dimensional materials remains a great challenge in physics. Herein, we propose an effective approach that the dimerization of magnetic ions in two-dimensional materials can enhance the exchange coupling and stabilize the ferromagnetism. Manganese carbonitride Mn$_2$N$_6$C$_6$ with a planar monolayer structure is taken as an example to clarify the method, in which two Mn atoms are gathered together to form a ferromagnetic dimer of Mn atoms and further these dimers are coupled together to form the overall ferromagnetism of the two-dimensional material. In Mn$_2$N$_6$C$_6$ monolayer, the near-room-temperature ferromagnetism with the Curie temperature of 272.3 K is determined by solving Heisenberg model using Monte Carlo simulations method.

cond-mat.mtrl-sci↗

arXiv2022

High-temperature ferromagnetism in two-dimensional material MnSn originated from interlayer coupling

MnSn monolayer synthesized recently is a novel two-dimensional ferromagnetic material with a hexagonal lattice, in which three Mn atom come together to form a trimer, making it remarkably different from other magnetic two-dimensional materials. Most impressively, there happens a sharp increase of Curie temperature from 54 K to 225 K when the number of layers increase from 1 to 3. However, no quantitative explanation is reported in previous studies. Herein, by means of first-principle calculations method and Monte carlo method, we demonstrate that strong interlayer ferromagnetic coupling is the essential role in enhancing its critical temperature, which act as a magnetic field to stabilize the ferromagnetism in the MnSn multilayers.

cond-mat.mtrl-sci↗

arXiv2022

Cross-Task Knowledge Distillation in Multi-Task Recommendation

Multi-task learning (MTL) has been widely used in recommender systems, wherein predicting each type of user feedback on items (e.g, click, purchase) are treated as individual tasks and jointly trained with a unified model. Our key observation is that the prediction results of each task may contain task-specific knowledge about user's fine-grained preference towards items. While such knowledge could be transferred to benefit other tasks, it is being overlooked under the current MTL paradigm. This paper, instead, proposes a Cross-Task Knowledge Distillation framework that attempts to leverage prediction results of one task as supervised signals to teach another task. However, integrating MTL and KD in a proper manner is non-trivial due to several challenges including task conflicts, inconsistent magnitude and requirement of synchronous optimization. As countermeasures, we 1) introduce auxiliary tasks with quadruplet loss functions to capture cross-task fine-grained ranking information and avoid task conflicts, 2) design a calibrated distillation approach to align and distill knowledge from auxiliary tasks, and 3) propose a novel error correction mechanism to enable and facilitate synchronous training of teacher and student models. Comprehensive experiments are conducted to verify the effectiveness of our framework in real-world datasets.

cs.IR↗

arXiv2021

Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback

The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few minutes to several days. It is hard to design an appropriate online learning system under these non-identical delay for different types of ads and users. In this paper, we propose to tackle the delayed feedback problem in online advertising by "Following the Prophet" (FTP for short). The key insight is that, if the feedback came instantly for all the logged samples, we could get a model without delayed feedback, namely the "prophet". Although the prophet cannot be obtained during online learning, we show that we could predict the prophet's predictions by an aggregation policy on top of a set of multi-task predictions, where each task captures the feedback patterns of different periods. We propose the objective and optimization approach for the policy, and use the logged data to imitate the prophet. Extensive experiments on three real-world advertising datasets show that our method outperforms the previous state-of-the-art baselines.

cs.LG↗

arXiv2021

Convolutional Normalizing Flows for Deep Gaussian Processes

Deep Gaussian processes (DGPs), a hierarchical composition of GP models, have successfully boosted the expressive power of their single-layer counterpart. However, it is impossible to perform exact inference in DGPs, which has motivated the recent development of variational inference-based methods. Unfortunately, either these methods yield a biased posterior belief or it is difficult to evaluate their convergence. This paper introduces a new approach for specifying flexible, arbitrarily complex, and scalable approximate posterior distributions. The posterior distribution is constructed through a normalizing flow (NF) which transforms a simple initial probability into a more complex one through a sequence of invertible transformations. Moreover, a novel convolutional normalizing flow (CNF) is developed to improve the time efficiency and capture dependency between layers. Empirical evaluation shows that CNF DGP outperforms the state-of-the-art approximation methods for DGPs.

cs.LG↗

arXiv2021

Decision Making for Autonomous Driving via Augmented Adversarial Inverse Reinforcement Learning

Making decisions in complex driving environments is a challenging task for autonomous agents. Imitation learning methods have great potentials for achieving such a goal. Adversarial Inverse Reinforcement Learning (AIRL) is one of the state-of-art imitation learning methods that can learn both a behavioral policy and a reward function simultaneously, yet it is only demonstrated in simple and static environments where no interactions are introduced. In this paper, we improve and stabilize AIRL's performance by augmenting it with semantic rewards in the learning framework. Additionally, we adapt the augmented AIRL to a more practical and challenging decision-making task in a highly interactive environment in autonomous driving. The proposed method is compared with four baselines and evaluated by four performance metrics. Simulation results show that the augmented AIRL outperforms all the baseline methods, and its performance is comparable with that of the experts on all of the four metrics.

cs.AI↗

arXiv2020

Field-aware Calibration: A Simple and Empirically Strong Method for Reliable Probabilistic Predictions

It is often observed that the probabilistic predictions given by a machine learning model can disagree with averaged actual outcomes on specific subsets of data, which is also known as the issue of miscalibration. It is responsible for the unreliability of practical machine learning systems. For example, in online advertising, an ad can receive a click-through rate prediction of 0.1 over some population of users where its actual click rate is 0.15. In such cases, the probabilistic predictions have to be fixed before the system can be deployed. In this paper, we first introduce a new evaluation metric named field-level calibration error that measures the bias in predictions over the sensitive input field that the decision-maker concerns. We show that existing post-hoc calibration methods have limited improvements in the new field-level metric and other non-calibration metrics such as the AUC score. To this end, we propose Neural Calibration, a simple yet powerful post-hoc calibration method that learns to calibrate by making full use of the field-aware information over the validation set. We present extensive experiments on five large-scale datasets. The results showed that Neural Calibration significantly improves against uncalibrated predictions in common metrics such as the negative log-likelihood, Brier score and AUC, as well as the proposed field-level calibration error.

cs.LG↗

arXiv2010

Mapping XML Data to Relational Data: A DOM-Based Approach

XML has emerged as the standard for representing and exchanging data on the World Wide Web. It is critical to have efficient mechanisms to store and query XML data to exploit the full power of this new technology. Several researchers have proposed to use relational databases to store and query XML data. While several algorithms of schema mapping and query mapping have been proposed, the problem of mapping XML data to relational data, i.e., mapping an XML INSERT statement to a sequence of SQL INSERT statements, has not been addressed thoroughly in the literature. In this paper, we propose an efficient linear algorithm for mapping XML data to relational data. This algorithm is based on our previous proposed inlining algorithm for mapping DTDs to relational schemas and can be easily adapted to other inlining algorithms.

cs.DB↗