Searcharxiv⌕ Search

arXiv subjects

Yue Liu

Publications and source records attributed to Yue Liu.

At least 253 records · Page 14Linked to original sources
arXiv2023

At Which Training Stage Does Code Data Help LLMs Reasoning?

Large Language Models (LLMs) have exhibited remarkable reasoning capabilities and become the foundation of language technologies. Inspired by the great success of code data in training LLMs, we naturally wonder at which training stage introducing code data can really help LLMs reasoning. To this end, this paper systematically explores the impact of code data on LLMs at different stages. Concretely, we introduce the code data at the pre-training stage, instruction-tuning stage, and both of them, respectively. Then, the reasoning capability of LLMs is comprehensively and fairly evaluated via six reasoning tasks in five domains. We critically analyze the experimental results and provide conclusions with insights. First, pre-training LLMs with the mixture of code and text can significantly enhance LLMs' general reasoning capability almost without negative transfer on other tasks. Besides, at the instruction-tuning stage, code data endows LLMs the task-specific reasoning capability. Moreover, the dynamic mixing strategy of code and text data assists LLMs to learn reasoning capability step-by-step during training. These insights deepen the understanding of LLMs regarding reasoning ability for their application, such as scientific question answering, legal support, etc. The source code and model parameters are released at the link:~\url{https://github.com/yingweima2022/CodeLLM}.

cs.CL↗
arXiv2023

Constructing Synthetic Treatment Groups without the Mean Exchangeability Assumption

The purpose of this work is to transport the information from multiple randomized controlled trials to the target population where we only have the control group data. Previous works rely critically on the mean exchangeability assumption. However, as pointed out by many current studies, the mean exchangeability assumption might be violated. Motivated by the synthetic control method, we construct a synthetic treatment group for the target population by a weighted mixture of treatment groups of source populations. We estimate the weights by minimizing the conditional maximum mean discrepancy between the weighted control groups of source populations and the target population. We establish the asymptotic normality of the synthetic treatment group estimator based on the sieve semiparametric theory. Our method can serve as a novel complementary approach when the mean exchangeability assumption is violated. Experiments are conducted on synthetic and real-world datasets to demonstrate the effectiveness of our methods.

stat.ML↗
arXiv2023

AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model

We present Any-Modality Augmented Language Model (AnyMAL), a unified model that reasons over diverse input modality signals (i.e. text, image, video, audio, IMU motion sensor), and generates textual responses. AnyMAL inherits the powerful text-based reasoning abilities of the state-of-the-art LLMs including LLaMA-2 (70B), and converts modality-specific signals to the joint textual space through a pre-trained aligner module. To further strengthen the multimodal LLM's capabilities, we fine-tune the model with a multimodal instruction set manually collected to cover diverse topics and tasks beyond simple QAs. We conduct comprehensive empirical analysis comprising both human and automatic evaluations, and demonstrate state-of-the-art performance on various multimodal tasks.

cs.LG↗
arXiv2023

TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification

Audiovisual data is everywhere in this digital age, which raises higher requirements for the deep learning models developed on them. To well handle the information of the multi-modal data is the key to a better audiovisual modal. We observe that these audiovisual data naturally have temporal attributes, such as the time information for each frame in the video. More concretely, such data is inherently multi-modal according to both audio and visual cues, which proceed in a strict chronological order. It indicates that temporal information is important in multi-modal acoustic event modeling for both intra- and inter-modal. However, existing methods deal with each modal feature independently and simply fuse them together, which neglects the mining of temporal relation and thus leads to sub-optimal performance. With this motivation, we propose a Temporal Multi-modal graph learning method for Acoustic event Classification, called TMac, by modeling such temporal information via graph learning techniques. In particular, we construct a temporal graph for each acoustic event, dividing its audio data and video data into multiple segments. Each segment can be considered as a node, and the temporal relationships between nodes can be considered as timestamps on their edges. In this case, we can smoothly capture the dynamic information in intra-modal and inter-modal. Several experiments are conducted to demonstrate TMac outperforms other SOTA models in performance. Our code is available at https://github.com/MGitHubL/TMac.

cs.SD↗
arXiv2023

The Shackles of Peer Review: Unveiling the Flaws in the Ivory Tower

This essay delves into the ethical dilemmas encountered within the academic peer review process and investigates the prevailing deficiencies in this system. It highlights how established scholars often adhere to mainstream theories not out of genuine belief, but to safeguard their own reputations. This practice perpetuates intellectual conformity, fuels confirmation bias, and stifles dissenting voices. Furthermore, as the number of incorrect papers published by influential scientists increases, it inadvertently encourages more researchers to follow suit, tacitly endorsing incorrect viewpoints. By examining historical instances of suppressed ideas later proven valuable, this essay calls for a reevaluation of academia's commitment to genuine innovation and progress which is usually achieved by applications of fundamental principles in from textbooks.

physics.soc-ph↗
arXiv2023

A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resource

Graph clustering, which aims to divide nodes in the graph into several distinct clusters, is a fundamental yet challenging task. Benefiting from the powerful representation capability of deep learning, deep graph clustering methods have achieved great success in recent years. However, the corresponding survey paper is relatively scarce, and it is imminent to make a summary of this field. From this motivation, we conduct a comprehensive survey of deep graph clustering. Firstly, we introduce formulaic definition, evaluation, and development in this field. Secondly, the taxonomy of deep graph clustering methods is presented based on four different criteria, including graph type, network architecture, learning paradigm, and clustering method. Thirdly, we carefully analyze the existing methods via extensive experiments and summarize the challenges and opportunities from five perspectives, including graph data quality, stability, scalability, discriminative capability, and unknown cluster number. Besides, the applications of deep graph clustering methods in six domains, including computer vision, natural language processing, recommendation systems, social network analyses, bioinformatics, and medical science, are presented. Last but not least, this paper provides open resource supports, including 1) a collection (\url{https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering}) of state-of-the-art deep graph clustering methods (papers, codes, and datasets) and 2) a unified framework (\url{https://github.com/Marigoldwu/A-Unified-Framework-for-Deep-Attribute-Graph-Clustering}) of deep graph clustering. We hope this work can serve as a quick guide and help researchers overcome challenges in this vibrant field.

cs.LG↗
arXiv2023

On the global existence for the modified Camassa-Holm equation via the inverse scattering method

In this paper, we address the existence of global solutions to the Cauchy problem of the modified Camassa-Holm (mCH) equation, which is known as a model for the unidirectional propagation of shallow water waves. Based on the spectral analysis of the Lax pair, we apply the inverse scattering transform to rigorously analyze the mCH equation with zero background. By connecting the Cauchy problem to the Riemann-Hilbert (RH) problem, we establish a bijective map between potential and reflection coefficients within the $L^2$-Sobolev space framework. Utilizing a reconstruction formula and estimates on the time-dependent RH problem, we obtain a unique global solution to the Cauchy problem for the mCH equation.

math.AP↗
arXiv2023

ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection

Effective feature fusion of multispectral images plays a crucial role in multi-spectral object detection. Previous studies have demonstrated the effectiveness of feature fusion using convolutional neural networks, but these methods are sensitive to image misalignment due to the inherent deffciency in local-range feature interaction resulting in the performance degradation. To address this issue, a novel feature fusion framework of dual cross-attention transformers is proposed to model global feature interaction and capture complementary information across modalities simultaneously. This framework enhances the discriminability of object features through the query-guided cross-attention mechanism, leading to improved performance. However, stacking multiple transformer blocks for feature enhancement incurs a large number of parameters and high spatial complexity. To handle this, inspired by the human process of reviewing knowledge, an iterative interaction mechanism is proposed to share parameters among block-wise multimodal transformers, reducing model complexity and computation cost. The proposed method is general and effective to be integrated into different detection frameworks and used with different backbones. Experimental results on KAIST, FLIR, and VEDAI datasets show that the proposed method achieves superior performance and faster inference, making it suitable for various practical scenarios. Code will be available at https://github.com/chanchanchan97/ICAFusion.

cs.CV↗
arXiv2023

Reinforcement Graph Clustering with Unknown Cluster Number

Deep graph clustering, which aims to group nodes into disjoint clusters by neural networks in an unsupervised manner, has attracted great attention in recent years. Although the performance has been largely improved, the excellent performance of the existing methods heavily relies on an accurately predefined cluster number, which is not always available in the real-world scenario. To enable the deep graph clustering algorithms to work without the guidance of the predefined cluster number, we propose a new deep graph clustering method termed Reinforcement Graph Clustering (RGC). In our proposed method, cluster number determination and unsupervised representation learning are unified into a uniform framework by the reinforcement learning mechanism. Concretely, the discriminative node representations are first learned with the contrastive pretext task. Then, to capture the clustering state accurately with both local and global information in the graph, both node and cluster states are considered. Subsequently, at each state, the qualities of different cluster numbers are evaluated by the quality network, and the greedy action is executed to determine the cluster number. In order to conduct feedback actions, the clustering-oriented reward function is proposed to enhance the cohesion of the same clusters and separate the different clusters. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method. The source code of RGC is shared at https://github.com/yueliu1999/RGC and a collection (papers, codes and, datasets) of deep graph clustering is shared at https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering on Github.

cs.LG↗
arXiv2023

On the transverse stability of smooth solitary waves in a two-dimensional Camassa-Holm equation

We consider the propagation of smooth solitary waves in a two-dimensional generalization of the Camassa--Holm equation. We show that transverse perturbations to one-dimensional solitary waves behave similarly to the KP-II theory. This conclusion follows from our two main results: (i) the double eigenvalue of the linearized equations related to the translational symmetry breaks under a transverse perturbation into a pair of the asymptotically stable resonances and (ii) small-amplitude solitary waves are linearly stable with respect to transverse perturbations.

math.AP↗
arXiv2023

Measurement-altered Ising quantum criticality

Quantum critical systems constitute appealing platforms for the exploration of novel measurement-induced phenomena due to their innate sensitivity to perturbations. We study the impact of measurement on paradigmatic Ising quantum critical chains using an explicit protocol, whereby correlated ancilla are entangled with the critical chain and then projectively measured. Using a perturbative analytic framework supported by extensive numerical simulations, we demonstrate that measurements can qualitatively alter long-distance correlations in a manner dependent on the choice of entangling gate, ancilla measurement basis, measurement outcome, and nature of ancilla correlations. We derive numerous quantitative predictions for the behavior of correlations in select measurement outcomes, and also identify two strategies for detecting measurement-altered Ising criticality in measurement-averaged quantities. First, averaging the square of the order-parameter expectation value over measurement outcomes retains memory of order parameter condensation germinated in fixed measurement outcomes -- even though on average the order parameter itself vanishes. Second, we show that, in certain cases, observables can be averaged separately over measurement outcomes residing in distinct symmetry sectors, and that these `symmetry-resolved averages' reveal measurement effects even when considering standard linearly averaged observables. We identify complementary regimes in which symmetry-resolved averages and post-selection can be pursued reasonably efficiently in experiment, with the former generically outperforming the latter in the limit of sufficiently weak ancilla-critical chain entanglement. Our framework naturally adapts to more exotic quantum critical points and highlights opportunities for potential experimental realization in NISQ hardware and in Rydberg arrays.

cond-mat.stat-mech↗
arXiv2023

A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal

Knowledge graph reasoning (KGR), aiming to deduce new facts from existing facts based on mined logic rules underlying knowledge graphs (KGs), has become a fast-growing research direction. It has been proven to significantly benefit the usage of KGs in many AI applications, such as question answering, recommendation systems, and etc. According to the graph types, existing KGR models can be roughly divided into three categories, i.e., static models, temporal models, and multi-modal models. Early works in this domain mainly focus on static KGR, and recent works try to leverage the temporal and multi-modal information, which are more practical and closer to real-world. However, no survey papers and open-source repositories comprehensively summarize and discuss models in this important direction. To fill the gap, we conduct a first survey for knowledge graph reasoning tracing from static to temporal and then to multi-modal KGs. Concretely, the models are reviewed based on bi-level taxonomy, i.e., top-level (graph types) and base-level (techniques and scenarios). Besides, the performances, as well as datasets, are summarized and presented. Moreover, we point out the challenges and potential opportunities to enlighten the readers. The corresponding open-source repository is shared on GitHub https://github.com/LIANGKE23/Awesome-Knowledge-Graph-Reasoning.

cs.AI↗
arXiv2023

Dink-Net: Neural Clustering on Large Graphs

Deep graph clustering, which aims to group the nodes of a graph into disjoint clusters with deep neural networks, has achieved promising progress in recent years. However, the existing methods fail to scale to the large graph with million nodes. To solve this problem, a scalable deep graph clustering method (Dink-Net) is proposed with the idea of dilation and shrink. Firstly, by discriminating nodes, whether being corrupted by augmentations, representations are learned in a self-supervised manner. Meanwhile, the cluster centres are initialized as learnable neural parameters. Subsequently, the clustering distribution is optimized by minimizing the proposed cluster dilation loss and cluster shrink loss in an adversarial manner. By these settings, we unify the two-step clustering, i.e., representation learning and clustering optimization, into an end-to-end framework, guiding the network to learn clustering-friendly features. Besides, Dink-Net scales well to large graphs since the designed loss functions adopt the mini-batch data to optimize the clustering distribution even without performance drops. Both experimental results and theoretical analyses demonstrate the superiority of our method. Compared to the runner-up, Dink-Net achieves 9.62% NMI improvement on the ogbn-papers100M dataset with 111 million nodes and 1.6 billion edges. The source code is released at https://github.com/yueliu1999/Dink-Net. Besides, a collection (papers, codes, and datasets) of deep graph clustering is shared at https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering.

cs.LG↗
arXiv2023

Analytical reconstructions of full-scan multiple source-translation computed tomography under large field of views

This paper is to investigate the high-quality analytical reconstructions of multiple source-translation computed tomography (mSTCT) under an extended field of view (FOV). Under the larger FOVs, the previously proposed backprojection filtration (BPF) algorithms for mSTCT, including D-BPF and S-BPF (their differences are different derivate directions along the detector and source, respectively), make some errors and artifacts in the reconstructed images due to a backprojection weighting factor and the half-scan mode, which deviates from the intention of mSTCT imaging. In this paper, to achieve reconstruction with as little error as possible under the extremely extended FOV, we combine the full-scan mSTCT (F-mSTCT) geometry with the previous BPF algorithms to study the performance and derive a suitable redundancy-weighted function for F-mSTCT. The experimental results indicate FS-BPF can get high-quality, stable images under the extremely extended FOV of imaging a large object, though it requires more projections than FD-BPF. Finally, for different practical requirements in extending FOV imaging, we give suggestions on algorithm selection.

cs.CV↗
arXiv2023

QB4AIRA: A Question Bank for AI Risk Assessment

The rapid advancement of Artificial Intelligence (AI), represented by ChatGPT, has raised concerns about responsible AI development and utilization. Existing frameworks lack a comprehensive synthesis of AI risk assessment questions. To address this, we introduce QB4AIRA, a novel question bank developed by refining questions from five globally recognized AI risk frameworks, categorized according to Australia's AI ethics principles. QB4AIRA comprises 293 prioritized questions covering a wide range of AI risk areas, facilitating effective risk assessment. It serves as a valuable resource for stakeholders in assessing and managing AI risks, while paving the way for new risk frameworks and guidelines. By promoting responsible AI practices, QB4AIRA contributes to responsible AI deployment, mitigating potential risks and harms.

cs.SE↗
arXiv2023

Uncorrelated Amplitude and Frequency Variations of the Harmonics in SX Phoenicis Star XX Cygni

Harmonics are quite common in pulsating stars, and they are always considered to mimic the behaviors of their independent parent pulsation modes and not taken as the key information for asteroseismology. Here, we report an SX Phoenicis star XX Cygni, whose periodogram is dominated by the fundamental frequency $f_{0} = 7.41481 \pm 0.00004\ \mathrm{cd}^{-1}$ and its 19 harmonics. According to the analysis of the archival data from \TESS, we find that both the amplitudes and frequencies of the fundamental mode and the harmonics vary within TESS Sectors 14-17 and 54-57, which might be caused by the contamination by neighbouring stars. What is more interesting is that, the harmonics show significantly uncorrelated amplitude and frequency variations over time. Some possible origins and interesting issues are proposed to scheme the further research of this hidden corner in current asteroseismology.

astro-ph.SR↗
arXiv2023

Structure Guided Multi-modal Pre-trained Transformer for Knowledge Graph Reasoning

Multimodal knowledge graphs (MKGs), which intuitively organize information in various modalities, can benefit multiple practical downstream tasks, such as recommendation systems, and visual question answering. However, most MKGs are still far from complete, which motivates the flourishing of MKG reasoning models. Recently, with the development of general artificial architectures, the pretrained transformer models have drawn increasing attention, especially for multimodal scenarios. However, the research of multimodal pretrained transformer (MPT) for knowledge graph reasoning (KGR) is still at an early stage. As the biggest difference between MKG and other multimodal data, the rich structural information underlying the MKG still cannot be fully leveraged in existing MPT models. Most of them only utilize the graph structure as a retrieval map for matching images and texts connected with the same entity. This manner hinders their reasoning performances. To this end, we propose the graph Structure Guided Multimodal Pretrained Transformer for knowledge graph reasoning, termed SGMPT. Specifically, the graph structure encoder is adopted for structural feature encoding. Then, a structure-guided fusion module with two different strategies, i.e., weighted summation and alignment constraint, is first designed to inject the structural information into both the textual and visual features. To the best of our knowledge, SGMPT is the first MPT model for multimodal KGR, which mines the structural information underlying the knowledge graph. Extensive experiments on FB15k-237-IMG and WN18-IMG, demonstrate that our SGMPT outperforms existing state-of-the-art models, and prove the effectiveness of the designed strategies.

cs.AI↗
arXiv2023

Homomorphism of independent random variable convolution and matrix multiplication

A map is given showing that convolutions of independent random variables over a finite group and matrix multiplications of doubly stochastic matrices are homomorphic. As an application, a short proof is given to the theorem that the limiting distributions of stochastic processes with stationary independent increments over a finite group are always uniform.

math.PR↗