arXiv subjects

Rui Zhang

Publications and source records attributed to Rui Zhang.

At least 829 records · Page 46Linked to original sources

arXiv2022

On the Opportunity of Causal Learning in Recommendation Systems: Foundation, Estimation, Prediction and Challenges

Recently, recommender system (RS) based on causal inference has gained much attention in the industrial community, as well as the states of the art performance in many prediction and debiasing tasks. Nevertheless, a unified causal analysis framework has not been established yet. Many causal-based prediction and debiasing studies rarely discuss the causal interpretation of various biases and the rationality of the corresponding causal assumptions. In this paper, we first provide a formal causal analysis framework to survey and unify the existing causal-inspired recommendation methods, which can accommodate different scenarios in RS. Then we propose a new taxonomy and give formal causal definitions of various biases in RS from the perspective of violating the assumptions adopted in causal analysis. Finally, we formalize many debiasing and prediction tasks in RS, and summarize the statistical and machine learning-based causal estimation methods, expecting to provide new research opportunities and perspectives to the causal RS community.

cs.IR↗

arXiv2022

Neural Program Synthesis with Query

Aiming to find a program satisfying the user intent given input-output examples, program synthesis has attracted increasing interest in the area of machine learning. Despite the promising performance of existing methods, most of their success comes from the privileged information of well-designed input-output examples. However, providing such input-output examples is unrealistic because it requires the users to have the ability to describe the underlying program with a few input-output examples under the training distribution. In this work, we propose a query-based framework that trains a query neural network to generate informative input-output examples automatically and interactively from a large query space. The quality of the query depends on the amount of the mutual information between the query and the corresponding program, which can guide the optimization of the query framework. To estimate the mutual information more accurately, we introduce the functional space (F-space) which models the relevance between the input-output examples and the programs in a differentiable way. We evaluate the effectiveness and generalization of the proposed query-based framework on the Karel task and the list processing task. Experimental results show that the query-based framework can generate informative input-output examples which achieve and even outperform well-designed input-output examples.

cs.LG↗

arXiv2022

A Benchmark and Comprehensive Survey on Knowledge Graph Entity Alignment via Representation Learning

In the last few years, the interest in knowledge bases has grown exponentially in both the research community and the industry due to their essential role in AI applications. Entity alignment is an important task for enriching knowledge bases. This paper provides a comprehensive tutorial-type survey on representative entity alignment techniques that use the new approach of representation learning. We present a framework for capturing the key characteristics of these techniques, propose two datasets to address the limitation of existing benchmark datasets, and conduct extensive experiments using the proposed datasets. The framework gives a clear picture of how the techniques work. The experiments yield important results about the empirical performance of the techniques and how various factors affect the performance. One important observation not stressed by previous work is that techniques making good use of attribute triples and relation predicates as features stand out as winners.

cs.AI↗

arXiv2022

Intelligent Reflecting Surface Aided Wireless Networks: From Single-Reflection to Multi-Reflection Design and Optimization

Intelligent reflecting surface (IRS) has emerged as a promising technique for wireless communication networks. By dynamically tuning the reflection amplitudes/phase shifts of a large number of passive elements, IRS enables flexible wireless channel control and configuration, and thereby enhances the wireless signal transmission rate and reliability significantly. Despite the vast literature on designing and optimizing assorted IRS-aided wireless systems, prior works have mainly focused on enhancing wireless links with single signal reflection only by one or multiple IRSs, which may be insufficient to boost the wireless link capacity under some harsh propagation conditions (e.g., indoor environment with dense blockages/obstructions). This issue can be tackled by employing two or more IRSs to assist each wireless link and jointly exploiting their single as well as multiple signal reflections over them. However, the resultant double-/multi-IRS aided wireless systems face more complex design issues as well as new practical challenges for implementation as compared to the conventional single-IRS counterpart, in terms of IRS reflection optimization, channel acquisition, as well as IRS deployment and association/selection. As such, a new paradigm for designing multi-IRS cooperative passive beamforming and joint active/passive beam routing arises which calls for innovative design approaches and optimization methods. In this paper, we give a tutorial overview of multi-IRS aided wireless networks, with an emphasis on addressing the new challenges due to multi-IRS signal reflection and routing. Moreover, we point out important directions worthy of research and investigation in the future.

cs.IT↗

arXiv2022

Resource allocation for text semantic communications

Semantic communications have shown its great potential to improve the transmission reliability, especially in the low signal-to-noise regime. However, resource allocation for semantic communications still remains unexplored, which is a critical issue in guaranteeing the semantic transmission reliability and the communication efficiency. To fill this gap, we investigate the spectral efficiency in the semantic domain and rethink the semantic-aware resource allocation issue. Specifically, taking text semantic communication as an example, the semantic spectral efficiency (S-SE) is defined for the first time, and is used to optimize resource allocation in terms of channel assignment and the number of transmitted semantic symbols. Additionally, for fair comparison of semantic and conventional communication systems, a transform method is developed to convert the conventional bit-based spectral efficiency to the S-SE. Simulation results demonstrate the validity and feasibility of the proposed resource allocation method, as well as the superiority of semantic communications in terms of the S-SE.

eess.SP↗

arXiv2022

DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization

Transformer-based models have achieved state-of-the-art performance on short-input summarization. However, they still struggle with summarizing longer text. In this paper, we present DYLE, a novel dynamic latent extraction approach for abstractive long-input summarization. DYLE jointly trains an extractor and a generator and treats the extracted text snippets as the latent variable, allowing dynamic snippet-level attention weights during decoding. To provide adequate supervision, we propose simple yet effective heuristics for oracle extraction as well as a consistency loss term, which encourages the extractor to approximate the averaged dynamic weights predicted by the generator. We evaluate our method on different long-document and long-dialogue summarization tasks: GovReport, QMSum, and arXiv. Experiment results show that DYLE outperforms all existing methods on GovReport and QMSum, with gains up to 6.1 ROUGE, while yielding strong results on arXiv. Further analysis shows that the proposed dynamic weights provide interpretability of our generation process.

cs.CL↗

arXiv2022

ReLoop: A Self-Correction Continual Learning Loop for Recommender Systems

Deep learning-based recommendation has become a widely adopted technique in various online applications. Typically, a deployed model undergoes frequent re-training to capture users' dynamic behaviors from newly collected interaction logs. However, the current model training process only acquires users' feedbacks as labels, but fail to take into account the errors made in previous recommendations. Inspired by the intuition that humans usually reflect and learn from mistakes, in this paper, we attempt to build a self-correction learning loop (dubbed ReLoop) for recommender systems. In particular, a new customized loss is employed to encourage every new model version to reduce prediction errors over the previous model version during training. Our ReLoop learning framework enables a continual self-correction process in the long run and thus is expected to obtain better performance over existing training strategies. Both offline experiments and an online A/B test have been conducted to validate the effectiveness of ReLoop.

cs.IR↗

arXiv2022

Nematic fluctuations in the non-superconducting iron pnictide BaFe$_{1.9-x}$Ni$_{0.1}$Cr$_{x}$As$_{2}$

The main driven force of the electronic nematic phase in iron-based superconductors is still under debate. Here, we report a comprehensive study on the nematic fluctuations in a non-superconducting iron pnictide system BaFe$_{1.9-x}$Ni$_{0.1}$Cr$_{x}$As$_{2}$ by electronic transport, angle-resolved photoemission spectroscopy (ARPES) and inelastic neutron scattering (INS) measurements. Previous neutron diffraction and transport measurements suggested that the collinear antiferromagnetism persists to $x=0.8$, with similar Néel temperature $T_N$ and structural transition temperature $T_s$ around 32 K, but the charge carriers change from electron type to hole type around $x=$ 0.5. In this study, we have found that the in-plane resistivity anisotropy also highly depends on the Cr dopings and the type of charge carriers. While ARPES measurements suggest possibly weak orbital anisotropy onset near $T_s$ for both $x=0.05$ and $x=0.5$ compounds, INS experiments reveal clearly different onset temperatures of low-energy spin excitation anisotropy, which is likely related to the energy scale of spin nematicity. These results suggest that the interplay between the local spins on Fe atoms and the itinerant electrons on Fermi surfaces is crucial to the nematic fluctuations of iron pnictides, where the orbital degree of freedom may behave differently from the spin degree of freedom, and the transport properties are intimately related to the spin dynamics.

cond-mat.supr-con↗

arXiv2022

Solving The Long-Tailed Problem via Intra- and Inter-Category Balance

Benchmark datasets for visual recognition assume that data is uniformly distributed, while real-world datasets obey long-tailed distribution. Current approaches handle the long-tailed problem to transform the long-tailed dataset to uniform distribution by re-sampling or re-weighting strategies. These approaches emphasize the tail classes but ignore the hard examples in head classes, which result in performance degradation. In this paper, we propose a novel gradient harmonized mechanism with category-wise adaptive precision to decouple the difficulty and sample size imbalance in the long-tailed problem, which are correspondingly solved via intra- and inter-category balance strategies. Specifically, intra-category balance focuses on the hard examples in each category to optimize the decision boundary, while inter-category balance aims to correct the shift of decision boundary by taking each category as a unit. Extensive experiments demonstrate that the proposed method consistently outperforms other approaches on all the datasets.

cs.CV↗

arXiv2022

Multi-Level Interaction Reranking with User Behavior History

As the final stage of the multi-stage recommender system (MRS), reranking directly affects users' experience and satisfaction, thus playing a critical role in MRS. Despite the improvement achieved in the existing work, three issues are yet to be solved. First, users' historical behaviors contain rich preference information, such as users' long and short-term interests, but are not fully exploited in reranking. Previous work typically treats items in history equally important, neglecting the dynamic interaction between the history and candidate items. Second, existing reranking models focus on learning interactions at the item level while ignoring the fine-grained feature-level interactions. Lastly, estimating the reranking score on the ordered initial list before reranking may lead to the early scoring problem, thereby yielding suboptimal reranking performance. To address the above issues, we propose a framework named Multi-level Interaction Reranking (MIR). MIR combines low-level cross-item interaction and high-level set-to-list interaction, where we view the candidate items to be reranked as a set and the users' behavior history in chronological order as a list. We design a novel SLAttention structure for modeling the set-to-list interactions with personalized long-short term interests. Moreover, feature-level interactions are incorporated to capture the fine-grained influence among items. We design MIR in such a way that any permutation of the input items would not change the output ranking, and we theoretically prove it. Extensive experiments on three public and proprietary datasets show that MIR significantly outperforms the state-of-the-art models using various ranking and utility metrics.

cs.IR↗

arXiv2022

Self Supervised Lesion Recognition For Breast Ultrasound Diagnosis

Previous deep learning based Computer Aided Diagnosis (CAD) system treats multiple views of the same lesion as independent images. Since an ultrasound image only describes a partial 2D projection of a 3D lesion, such paradigm ignores the semantic relationship between different views of a lesion, which is inconsistent with the traditional diagnosis where sonographers analyze a lesion from at least two views. In this paper, we propose a multi-task framework that complements Benign/Malignant classification task with lesion recognition (LR) which helps leveraging relationship among multiple views of a single lesion to learn a complete representation of the lesion. To be specific, LR task employs contrastive learning to encourage representation that pulls multiple views of the same lesion and repels those of different lesions. The task therefore facilitates a representation that is not only invariant to the view change of the lesion, but also capturing fine-grained features to distinguish between different lesions. Experiments show that the proposed multi-task framework boosts the performance of Benign/Malignant classification as two sub-tasks complement each other and enhance the learned representation of ultrasound images.

eess.IV↗

arXiv2022

Neural Re-ranking in Multi-stage Recommender Systems: A Review

As the final stage of the multi-stage recommender system (MRS), re-ranking directly affects user experience and satisfaction by rearranging the input ranking lists, and thereby plays a critical role in MRS. With the advances in deep learning, neural re-ranking has become a trending topic and been widely applied in industrial applications. This review aims at integrating re-ranking algorithms into a broader picture, and paving ways for more comprehensive solutions for future research. For this purpose, we first present a taxonomy of current methods on neural re-ranking. Then we give a description of these methods along with the historic development according to their objectives. The network structure, personalization, and complexity are also discussed and compared. Next, we provide benchmarks of the major neural re-ranking models and quantitatively analyze their re-ranking performance. Finally, the review concludes with a discussion on future prospects of this field. A list of papers discussed in this review, the benchmark datasets, our re-ranking library LibRerank, and detailed parameter settings are publicly available at https://github.com/LibRerank-Community/LibRerank.

cs.IR↗

arXiv2022

Efficient Non-parametric Bayesian Hawkes Processes

In this paper, we develop an efficient nonparametric Bayesian estimation of the kernel function of Hawkes processes. The non-parametric Bayesian approach is important because it provides flexible Hawkes kernels and quantifies their uncertainty. Our method is based on the cluster representation of Hawkes processes. Utilizing the finite support assumption of the Hawkes process, we efficiently sample random branching structures and thus, we split the Hawkes process into clusters of Poisson processes. We derive two algorithms -- a block Gibbs sampler and a maximum a posteriori estimator based on expectation maximization -- and we show that our methods have a linear time complexity, both theoretically and empirically. On synthetic data, we show our methods to be able to infer flexible Hawkes triggering kernels. On two large-scale Twitter diffusion datasets, we show that our methods outperform the current state-of-the-art in goodness-of-fit and that the time complexity is linear in the size of the dataset. We also observe that on diffusions related to online videos, the learned kernels reflect the perceived longevity for different content types such as music or pets videos.

cs.LG↗

arXiv2022

Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents

Text summarization helps readers capture salient information from documents, news, interviews, and meetings. However, most state-of-the-art pretrained language models (LM) are unable to efficiently process long text for many summarization tasks. In this paper, we propose Summ$^N$, a simple, flexible, and effective multi-stage framework for input texts that are longer than the maximum context length of typical pretrained LMs. Summ$^N$ first splits the data samples and generates a coarse summary in multiple stages and then produces the final fine-grained summary based on it. Our framework can process input text of arbitrary length by adjusting the number of stages while keeping the LM input size fixed. Moreover, it can deal with both single-source documents and dialogues, and it can be used on top of different backbone abstractive summarization models. To the best of our knowledge, Summ$^N$ is the first multi-stage split-then-summarize framework for long input summarization. Our experiments demonstrate that Summ$^N$ outperforms previous state-of-the-art methods by improving ROUGE scores on three long meeting summarization datasets AMI, ICSI, and QMSum, two long TV series datasets from SummScreen, and a long document summarization dataset GovReport. Our data and code are available at https://github.com/psunlpgroup/Summ-N.

cs.CL↗

arXiv2022

Heading-error-free optical atomic magnetometry in the Earth-field range

Alkali-metal atomic magnetometry is widely used due to its high sensitivity and cryogen-free operation. However, when operating in geomagnetic field, it suffers from heading errors originating from nonlinear Zeeman (NLZ) splittings and magnetic resonance asymmetries, which lead to difficulties in mobile-platform measurements. We demonstrate an alignment based $^{87}$Rb magnetometer, which, with only a single magnetic resonance peak and well-separated hyperfine transition frequencies, is insensitive or even immune to NLZ-related heading errors. It is shown that the magnetometer can be implemented for practical measurements in the geomagnetic environments and the photon-shot-noise-limited sensitivity reaches $9\,{\rm{fT}}/\sqrt{\rm{Hz}}$ at room temperature.

physics.atom-ph↗

arXiv2022

How to Deploy Intelligent Reflecting Surfaces in Wireless Network: BS-side, User-side, or Both Sides?

The performance of wireless communication systems is fundamentally constrained by the random and uncontrollable wireless channel. By leveraging the recent advance in digitally-controlled metasurface, intelligent reflecting surface (IRS) has emerged as a promising solution to enhance the wireless network performance by smartly reconfiguring the radio propagation environment. Despite the substantial research on IRS-aided communications, this article addresses the important issue of how to deploy IRSs in a wireless network to achieve its optimum performance. We first compare the two conventional strategies of deploying IRS at the side of base station or distributed users in terms of various communication performance metrics, and then propose a new hybrid IRS deployment strategy by combining their complementary advantages. Moreover, the main challenges in optimizing IRS deployment as well as their promising solutions are discussed. A case study is also presented to compare the performance of different IRS deployment strategies and draw useful insights for practical design.

cs.IT↗

arXiv2022

"Adversarial Examples" for Proof-of-Learning

In S&P '21, Jia et al. proposed a new concept/mechanism named proof-of-learning (PoL), which allows a prover to demonstrate ownership of a machine learning model by proving integrity of the training procedure. It guarantees that an adversary cannot construct a valid proof with less cost (in both computation and storage) than that made by the prover in generating the proof. A PoL proof includes a set of intermediate models recorded during training, together with the corresponding data points used to obtain each recorded model. Jia et al. claimed that an adversary merely knowing the final model and training dataset cannot efficiently find a set of intermediate models with correct data points. In this paper, however, we show that PoL is vulnerable to ``adversarial examples''! Specifically, in a similar way as optimizing an adversarial example, we could make an arbitrarily-chosen data point ``generate'' a given model, hence efficiently generating intermediate models with correct data points. We demonstrate, both theoretically and empirically, that we are able to generate a valid proof with significantly less cost than generating a proof by the prover.

cs.CR↗

arXiv2022

Contrastive Learning with Positive-Negative Frame Mask for Music Representation

Self-supervised learning, especially contrastive learning, has made an outstanding contribution to the development of many deep learning research fields. Recently, researchers in the acoustic signal processing field noticed its success and leveraged contrastive learning for better music representation. Typically, existing approaches maximize the similarity between two distorted audio segments sampled from the same music. In other words, they ensure a semantic agreement at the music level. However, those coarse-grained methods neglect some inessential or noisy elements at the frame level, which may be detrimental to the model to learn the effective representation of music. Towards this end, this paper proposes a novel Positive-nEgative frame mask for Music Representation based on the contrastive learning framework, abbreviated as PEMR. Concretely, PEMR incorporates a Positive-Negative Mask Generation module, which leverages transformer blocks to generate frame masks on the Log-Mel spectrogram. We can generate self-augmented negative and positive samples by masking important components or inessential components, respectively. We devise a novel contrastive learning objective to accommodate both self-augmented positives/negatives sampled from the same music. We conduct experiments on four public datasets. The experimental results of two music-related downstream tasks, music classification, and cover song identification, demonstrate the generalization ability and transferability of music representation learned by PEMR.

cs.SD↗