arXiv subjects

Yao Ma

Publications and source records attributed to Yao Ma.

At least 91 records · Page 5Linked to original sources

arXiv2024

Revealing Hidden Regions in Wide-Angle and Forward Scattering

We discuss a class of Feynman Integrals containing hidden regions that are not straightforwardly identified using the geometric, or Newton polytope, approach to the method of regions. Using Landau singularity analysis and existing analytic results, we study the appearance of such regions in wide-angle and forward scattering and discuss how they can be exposed in both the momentum and parametric representations. We demonstrate that in the strict on-shell limit such integrals contain Landau singularities that prevent their direct numerical evaluation in parameter space and describe how they can be re-parameterised and dissected to circumvent this problem.

hep-th↗

arXiv2024

Dissecting polytopes: Landau singularities and asymptotic expansions in $2\to 2$ scattering

Parametric representations of Feynman integrals have a key property: many, frequently all, of the Landau singularities appear as endpoint divergences. This leads to a geometric interpretation of the singularities as faces of Newton polytopes, which facilitates algorithmic evaluation by sector decomposition and asymptotic expansion by the method of regions. Here we identify cases where some singularities appear instead as pinches in parametric space for general kinematics, and we then extend the applicability of sector decomposition and the method of regions algorithms to such integrals, by dissecting the Newton polytope on the singular locus. We focus on $2\to 2$ massless scattering, where we show that pinches in parameter space occur starting from three loops in particular nonplanar graphs due to cancellation between terms of opposite sign in the second Symanzik polynomial. While the affected integrals cannot be evaluated by standard sector decomposition, we show how they can be computed by first linearising the graph polynomial and then splitting the integration domain at the singularity, so as to turn it into an endpoint divergence. Furthermore, we demonstrate that obtaining the correct asymptotic expansion of such integrals by the method of regions requires the introduction of new regions, which can be systematically identified as facets of the dissected polytope. In certain instances, these hidden regions exclusively govern the leading power behaviour of the integral. In momentum space, we find that in the on-shell expansion for wide-angle scattering the new regions are characterised by having two or more connected hard subgraphs, while in the Regge limit they are characterised by Glauber modes.

hep-th↗

arXiv2024

A Survey on Safe Multi-Modal Learning System

In the rapidly evolving landscape of artificial intelligence, multimodal learning systems (MMLS) have gained traction for their ability to process and integrate information from diverse modality inputs. Their expanding use in vital sectors such as healthcare has made safety assurance a critical concern. However, the absence of systematic research into their safety is a significant barrier to progress in this field. To bridge the gap, we present the first taxonomy that systematically categorizes and assesses MMLS safety. This taxonomy is structured around four fundamental pillars that are critical to ensuring the safety of MMLS: robustness, alignment, monitoring, and controllability. Leveraging this taxonomy, we review existing methodologies, benchmarks, and the current state of research, while also pinpointing the principal limitations and gaps in knowledge. Finally, we discuss unique challenges in MMLS safety. In illuminating these challenges, we aim to pave the way for future research, proposing potential directions that could lead to significant advancements in the safety protocols of MMLS.

cs.CY↗

arXiv2024

LPFormer: An Adaptive Graph Transformer for Link Prediction

Link prediction is a common task on graph-structured data that has seen applications in a variety of domains. Classically, hand-crafted heuristics were used for this task. Heuristic measures are chosen such that they correlate well with the underlying factors related to link formation. In recent years, a new class of methods has emerged that combines the advantages of message-passing neural networks (MPNN) and heuristics methods. These methods perform predictions by using the output of an MPNN in conjunction with a "pairwise encoding" that captures the relationship between nodes in the candidate link. They have been shown to achieve strong performance on numerous datasets. However, current pairwise encodings often contain a strong inductive bias, using the same underlying factors to classify all links. This limits the ability of existing methods to learn how to properly classify a variety of different links that may form from different factors. To address this limitation, we propose a new method, LPFormer, which attempts to adaptively learn the pairwise encodings for each link. LPFormer models the link factors via an attention module that learns the pairwise encoding that exists between nodes by modeling multiple factors integral to link prediction. Extensive experiments demonstrate that LPFormer can achieve SOTA performance on numerous datasets while maintaining efficiency. The code is available at The code is available at https://github.com/HarryShomer/LPFormer.

cs.LG↗

arXiv2024

Addressing Shortcomings in Fair Graph Learning Datasets: Towards a New Benchmark

Fair graph learning plays a pivotal role in numerous practical applications. Recently, many fair graph learning methods have been proposed; however, their evaluation often relies on poorly constructed semi-synthetic datasets or substandard real-world datasets. In such cases, even a basic Multilayer Perceptron (MLP) can outperform Graph Neural Networks (GNNs) in both utility and fairness. In this work, we illustrate that many datasets fail to provide meaningful information in the edges, which may challenge the necessity of using graph structures in these problems. To address these issues, we develop and introduce a collection of synthetic, semi-synthetic, and real-world datasets that fulfill a broad spectrum of requirements. These datasets are thoughtfully designed to include relevant graph structures and bias information crucial for the fair evaluation of models. The proposed synthetic and semi-synthetic datasets offer the flexibility to create data with controllable bias parameters, thereby enabling the generation of desired datasets with user-defined bias values with ease. Moreover, we conduct systematic evaluations of these proposed datasets and establish a unified evaluation approach for fair graph learning models. Our extensive experimental results with fair graph learning methods across our datasets demonstrate their effectiveness in benchmarking the performance of these methods. Our datasets and the code for reproducing our experiments are available at https://github.com/XweiQ/Benchmark-GraphFairness.

cs.LG↗

arXiv2024

PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming

Solving large-scale linear programming (LP) problems is an important task in various areas such as communication networks, power systems, finance and logistics. Recently, two distinct approaches have emerged to expedite LP solving: (i) First-order methods (FOMs); (ii) Learning to optimize (L2O). In this work, we propose an FOM-unrolled neural network (NN) called PDHG-Net, and propose a two-stage L2O method to solve large-scale LP problems. The new architecture PDHG-Net is designed by unrolling the recently emerged PDHG method into a neural network, combined with channel-expansion techniques borrowed from graph neural networks. We prove that the proposed PDHG-Net can recover PDHG algorithm, thus can approximate optimal solutions of LP instances with a polynomial number of neurons. We propose a two-stage inference approach: first use PDHG-Net to generate an approximate solution, and then apply PDHG algorithm to further improve the solution. Experiments show that our approach can significantly accelerate LP solving, achieving up to a 3$\times$ speedup compared to FOMs for large-scale LP problems.

cs.LG↗

arXiv2024

Structure-based Drug Design Benchmark: Do 3D Methods Really Dominate?

Currently, the field of structure-based drug design is dominated by three main types of algorithms: search-based algorithms, deep generative models, and reinforcement learning. While existing works have typically focused on comparing models within a single algorithmic category, cross-algorithm comparisons remain scarce. In this paper, to fill the gap, we establish a benchmark to evaluate the performance of sixteen models across these different algorithmic foundations by assessing the pharmaceutical properties of the generated molecules and their docking affinities with specified target proteins. We highlight the unique advantages of each algorithmic approach and offer recommendations for the design of future SBDD models. We emphasize that 1D/2D ligand-centric drug design methods can be used in SBDD by treating the docking function as a black-box oracle, which is typically neglected. The empirical results show that 1D/2D methods achieve competitive performance compared with 3D-based methods that use the 3D structure of the target protein explicitly. Also, AutoGrow4, a 2D molecular graph-based genetic algorithm, dominates SBDD in terms of optimization ability. The relevant code is available in https://github.com/zkysfls/2024-sbdd-benchmark.

cs.LG↗

arXiv2024

Position: Graph Foundation Models are Already Here

Graph Foundation Models (GFMs) are emerging as a significant research topic in the graph domain, aiming to develop graph models trained on extensive and diverse data to enhance their applicability across various tasks and domains. Developing GFMs presents unique challenges over traditional Graph Neural Networks (GNNs), which are typically trained from scratch for specific tasks on particular datasets. The primary challenge in constructing GFMs lies in effectively leveraging vast and diverse graph data to achieve positive transfer. Drawing inspiration from existing foundation models in the CV and NLP domains, we propose a novel perspective for the GFM development by advocating for a ``graph vocabulary'', in which the basic transferable units underlying graphs encode the invariance on graphs. We ground the graph vocabulary construction from essential aspects including network analysis, expressiveness, and stability. Such a vocabulary perspective can potentially advance the future GFM design in line with the neural scaling laws. All relevant resources with GFM design can be found here.

cs.LG↗

arXiv2024

Revisiting the Message Passing in Heterophilous Graph Neural Networks

Graph Neural Networks (GNNs) have demonstrated strong performance in graph mining tasks due to their message-passing mechanism, which is aligned with the homophily assumption that adjacent nodes exhibit similar behaviors. However, in many real-world graphs, connected nodes may display contrasting behaviors, termed as heterophilous patterns, which has attracted increased interest in heterophilous GNNs (HTGNNs). Although the message-passing mechanism seems unsuitable for heterophilous graphs due to the propagation of class-irrelevant information, it is still widely used in many existing HTGNNs and consistently achieves notable success. This raises the question: why does message passing remain effective on heterophilous graphs? To answer this question, in this paper, we revisit the message-passing mechanisms in heterophilous graph neural networks and reformulate them into a unified heterophilious message-passing (HTMP) mechanism. Based on HTMP and empirical analysis, we reveal that the success of message passing in existing HTGNNs is attributed to implicitly enhancing the compatibility matrix among classes. Moreover, we argue that the full potential of the compatibility matrix is not completely achieved due to the existence of incomplete and noisy semantic neighborhoods in real-world heterophilous graphs. To bridge this gap, we introduce a new approach named CMGNN, which operates within the HTMP mechanism to explicitly leverage and improve the compatibility matrix. A thorough evaluation involving 10 benchmark datasets and comparative analysis against 13 well-established baselines highlights the superior performance of the HTMP mechanism and CMGNN method.

cs.LG↗

arXiv2024

Insights into neutron star equation of state by machine learning

Due to its powerful capability and high efficiency in big data analysis, machine learning has been applied in various fields. We construct a neural network platform to constrain the behaviors of the equation of state of nuclear matter with respect to the properties of nuclear matter at saturation density and the properties of neutron stars. It is found that the neural network is able to give reasonable predictions of parameter space and provide new hints into the constraints of hadron interactions. As a specific example, we take the relativistic mean field approximation in a widely accepted Walecka-type model to illustrate the feasibility and efficiency of the platform. The results show that the neural network can indeed estimate the parameters of the model at a certain precision such that both the properties of nuclear matter around saturation density and global properties of neutron stars can be saturated. The optimization of the present modularly designed neural network and extension to other effective models are straightforward.

nucl-th↗

arXiv2024

Quark structure of isoscalar- and isovector-scalar mesons and nuclear matter property

It was found that the isoscalar-scalar and isovector-scalar mesons play significant roles in nuclear matter physics. However, the underlying structures of these resonances are not yet well understood. We construct a three-flavor baryonic extended linear sigma model including both the two- and four-quark constitutes of scalar mesons with respect to the axial transformation and study the nuclear matter properties with relativistic mean field method. The nuclear matter properties at saturation density and hadron spectrums are well reproduced with this model simultaneously and, only the two-quark component of the scalar mesons couple to baryon fields and dominates the nuclear force. A plateau-like structure is found in the symmetry energy of nuclear matter due to the multi-meson couplings, and it's crucial for understanding the neutron skin thickness of $^{208}\rm Pb$ and the tidal deformation of neutron star from GW170817. At high density regions, the vector mesons are found to be rather crucial, especially the ones coupling with four-quark configurations. This model can be easily extended to study neutron stars, even with hyperons in their interior.

nucl-th↗

arXiv2024

Doubly heavy tetraquark states in the constituent quark model using diffusion Monte Carlo method

We use the diffusion Monte Carlo method to calculate the doubly heavy tetraquark $T_{cc}$ system in two kinds of constituent quark models, the pure constituent quark model AL1/AP1 and the chiral constituent quark model. When the discrete configurations are complete and no spatial clustering is preseted, the AL1/AP1 model gives an energy of $T_{cc}$ close to the $DD^*$ threshold, and the chiral constituent quark model yields a deeply bound state. We further calculate all doubly heavy tetraquark systems with $J^P=0^+,1^+,2^+$, and provide the binding energies of systems with bound states. The $I(J^P)=0(0^+)$ $bc\bar{n}\bar{n}$, $0(1^+)$ $bb\bar{n}\bar{n}$, $0(1^+)$ $bc\bar{n}\bar{n}$, $\frac{1}{2}(1^+)$ $bb\bar{s}\bar{n}$ systems have bound states in all three models. Since the DMC method has almost no restriction on the spatial part, the resulting bound states have greater binding energies than those obtained in previous works.

hep-ph↗

arXiv2024

Deciphering Crypto Twitter

Cryptocurrency is a fast-moving space, with a continuous influx of new projects every year. However, an increasing number of incidents in the space, such as hacks and security breaches, threaten the growth of the community and the development of technology. This dynamic and often tumultuous landscape is vividly mirrored and shaped by discussions within Crypto Twitter, a key digital arena where investors, enthusiasts, and skeptics converge, revealing real-time sentiments and trends through social media interactions. We present our analysis on a Twitter dataset collected during a formative period of the cryptocurrency landscape. We collected 40 million tweets using cryptocurrency-related keywords and performed a nuanced analysis that involved grouping the tweets by semantic similarity and constructing a tweet and user network. We used sentence-level embeddings and autoencoders to create K-means clusters of tweets and identified six groups of tweets and their topics to examine different cryptocurrency-related interests and the change in sentiment over time. Moreover, we discovered sentiment indicators that point to real-life incidents in the crypto world, such as the FTX incident of November 2022. We also constructed and analyzed different networks of tweets and users in our dataset by considering the reply and quote relationships and analyzed the largest components of each network. Our networks reveal a structure of bot activity in Crypto Twitter and suggest that they can be detected and handled using a network-based approach. Our work sheds light on the potential of social media signals to detect and understand crypto events, benefiting investors, regulators, and curious observers alike, as well as the potential for bot detection in Crypto Twitter using a network-based approach.

cs.CE↗

arXiv2024

Precedence-Constrained Winter Value for Effective Graph Data Valuation

Data valuation is essential for quantifying data's worth, aiding in assessing data quality and determining fair compensation. While existing data valuation methods have proven effective in evaluating the value of Euclidean data, they face limitations when applied to the increasingly popular graph-structured data. Particularly, graph data valuation introduces unique challenges, primarily stemming from the intricate dependencies among nodes and the exponential growth in value estimation costs. To address the challenging problem of graph data valuation, we put forth an innovative solution, Precedence-Constrained Winter (PC-Winter) Value, to account for the complex graph structure. Furthermore, we develop a variety of strategies to address the computational challenges and enable efficient approximation of PC-Winter. Extensive experiments demonstrate the effectiveness of PC-Winter across diverse datasets and tasks.

cs.LG↗

arXiv2024

Hill Function-based Model of Transcriptional Response: Impact of Nonspecific Binding and RNAP Interactions

Hill function is one of the widely used gene transcription regulation models. Its attribute of fitting may result in a lack of an underlying physical picture, yet the fitting parameters can provide information about biochemical reactions, such as the number of transcription factors (TFs) and the binding energy between regulatory elements. However, it remains unclear when and how much biochemical information can Hill function provide in addition to fitting. Here, started from the interactions between TFs and RNA polymerase during transcription regulation and both of their association-dissociation reactions at specific/nonspecific sites on DNA, the regulatory effect of TFs was deduced as fold change. We found that, for weak promoter, fold change can degrade into the regulatory factor (Freg) which is closely correlated with Hill function. By directly comparing and fitting with Hill function, the fitting parameters and corresponding biochemical reaction parameters in Freg were analyzed and discussed, where the single TF and multiple TFs that with cooperativity and basic logic effects were considered. We concluded the strength of promoter and interactions between TFs determine whether Hill function can reflect the corresponding biochemical information. Our findings highlight the role of Hill function in modeling/fitting for transcriptional regulation, which also benefits the preparation of synthetic regulatory elements.

q-bio.MN↗

arXiv2024

Fast Graph Condensation with Structure-based Neural Tangent Kernel

The rapid development of Internet technology has given rise to a vast amount of graph-structured data. Graph Neural Networks (GNNs), as an effective method for various graph mining tasks, incurs substantial computational resource costs when dealing with large-scale graph data. A data-centric manner solution is proposed to condense the large graph dataset into a smaller one without sacrificing the predictive performance of GNNs. However, existing efforts condense graph-structured data through a computational intensive bi-level optimization architecture also suffer from massive computation costs. In this paper, we propose reforming the graph condensation problem as a Kernel Ridge Regression (KRR) task instead of iteratively training GNNs in the inner loop of bi-level optimization. More specifically, We propose a novel dataset condensation framework (GC-SNTK) for graph-structured data, where a Structure-based Neural Tangent Kernel (SNTK) is developed to capture the topology of graph and serves as the kernel function in KRR paradigm. Comprehensive experiments demonstrate the effectiveness of our proposed model in accelerating graph condensation while maintaining high prediction performance. The source code is available on https://github.com/WANGLin0126/GCSNTK.

cs.LG↗

arXiv2024

Overcoming Pitfalls in Graph Contrastive Learning Evaluation: Toward Comprehensive Benchmarks

The rise of self-supervised learning, which operates without the need for labeled data, has garnered significant interest within the graph learning community. This enthusiasm has led to the development of numerous Graph Contrastive Learning (GCL) techniques, all aiming to create a versatile graph encoder that leverages the wealth of unlabeled data for various downstream tasks. However, the current evaluation standards for GCL approaches are flawed due to the need for extensive hyper-parameter tuning during pre-training and the reliance on a single downstream task for assessment. These flaws can skew the evaluation away from the intended goals, potentially leading to misleading conclusions. In our paper, we thoroughly examine these shortcomings and offer fresh perspectives on how GCL methods are affected by hyper-parameter choices and the choice of downstream tasks for their evaluation. Additionally, we introduce an enhanced evaluation framework designed to more accurately gauge the effectiveness, consistency, and overall capability of GCL methods.

cs.LG↗

arXiv2024

Active Learning for Graphs with Noisy Structures

Graph Neural Networks (GNNs) have seen significant success in tasks such as node classification, largely contingent upon the availability of sufficient labeled nodes. Yet, the excessive cost of labeling large-scale graphs led to a focus on active learning on graphs, which aims for effective data selection to maximize downstream model performance. Notably, most existing methods assume reliable graph topology, while real-world scenarios often present noisy graphs. Given this, designing a successful active learning framework for noisy graphs is highly needed but challenging, as selecting data for labeling and obtaining a clean graph are two tasks naturally interdependent: selecting high-quality data requires clean graph structure while cleaning noisy graph structure requires sufficient labeled data. Considering the complexity mentioned above, we propose an active learning framework, GALClean, which has been specifically designed to adopt an iterative approach for conducting both data selection and graph purification simultaneously with best information learned from the prior iteration. Importantly, we summarize GALClean as an instance of the Expectation-Maximization algorithm, which provides a theoretical understanding of its design and mechanisms. This theory naturally leads to an enhanced version, GALClean+. Extensive experiments have demonstrated the effectiveness and robustness of our proposed method across various types and levels of noisy graphs.

cs.LG↗