arXiv subjects
Publications and source records attributed to Shuo Zhang.
We prove an exact sequence relating the Lagrangian Floer homology of a collection of Lagrangian spheres $\{L_i\}$ and the fixed-point Floer homology of iterated Dehn twists along them, making progress toward a conjecture of Seidel.
Recent advances in applying Graph Neural Networks (GNNs) to molecular science have showcased the power of learning three-dimensional (3D) structure representations with GNNs. However, most existing GNNs suffer from the limitations of insufficient modeling of diverse interactions, computational expensive operations, and ignorance of vectorial values. Here, we tackle these limitations by proposing a novel GNN model, Physics-aware Multiplex Graph Neural Network (PaxNet), to efficiently and accurately learn the representations of 3D molecules for both small organic compounds and macromolecule complexes. PaxNet separates the modeling of local and non-local interactions inspired by molecular mechanics, and reduces the expensive angle-related computations. Besides scalar properties, PaxNet can also predict vectorial properties by learning an associated vector for each atom. To evaluate the performance of PaxNet, we compare it with state-of-the-art baselines in two tasks. On small molecule dataset for predicting quantum chemical properties, PaxNet reduces the prediction error by 15% and uses 73% less memory than the best baseline. On macromolecule dataset for predicting protein-ligand binding affinities, PaxNet outperforms the best baseline while reducing the memory consumption by 33% and the inference time by 85%. Thus, PaxNet provides a universal, robust and accurate method for large-scale machine learning of molecules. Our code is available at https://github.com/zetayue/Physics-aware-Multiplex-GNN.
Molecular sciences address a wide range of problems involving molecules of different types and sizes and their complexes. Recently, geometric deep learning, especially Graph Neural Networks, has shown promising performance in molecular science applications. However, most existing works often impose targeted inductive biases to a specific molecular system, and are inefficient when applied to macromolecules or large-scale tasks, thereby limiting their applications to many real-world problems. To address these challenges, we present PAMNet, a universal framework for accurately and efficiently learning the representations of three-dimensional (3D) molecules of varying sizes and types in any molecular system. Inspired by molecular mechanics, PAMNet induces a physics-informed bias to explicitly model local and non-local interactions and their combined effects. As a result, PAMNet can reduce expensive operations, making it time and memory efficient. In extensive benchmark studies, PAMNet outperforms state-of-the-art baselines regarding both accuracy and efficiency in three diverse learning tasks: small molecule properties, RNA 3D structures, and protein-ligand binding affinities. Our results highlight the potential for PAMNet in a broad range of molecular science applications.
Semi-structured data, such as Infobox tables, often include temporal information about entities, either implicitly or explicitly. Can current NLP systems reason about such information in semi-structured tables? To tackle this question, we introduce the task of temporal question answering on semi-structured tables. We present a dataset, TempTabQA, which comprises 11,454 question-answer pairs extracted from 1,208 Wikipedia Infobox tables spanning more than 90 distinct domains. Using this dataset, we evaluate several state-of-the-art models for temporal reasoning. We observe that even the top-performing LLMs lag behind human performance by more than 13.5 F1 points. Given these results, our dataset has the potential to serve as a challenging benchmark to improve the temporal reasoning capabilities of NLP models.
OBJECTIVES: Quantitative MRI techniques such as T2 and T1$ρ$ mapping are beneficial in evaluating cartilage and meniscus. We aimed to evaluate the MIXTURE (Multi-Interleaved X-prepared Turbo-Spin Echo with IntUitive RElaxometry) sequences that provide morphologic images with clinical turbo spin-echo (TSE) contrasts and additional parameter maps versus reference TSE sequences in an in-situ model of human cartilage defects. MATERIALS AND METHODS: Prospectively, standardized cartilage defects of 8mm, 5mm, and 3mm diameter were created in the lateral femora of 10 human cadaveric knee specimens (81$\pm$10 years, nine male/one female). Using a clinical 3T MRI scanner and knee coil, MIXTURE sequences combining (i) proton-density weighted fat-saturated (PD-w FS) images and T2 maps and (ii) T1-weighted images and T1$ρ$ maps were acquired before and after defect creation, alongside the corresponding 2D TSE and 3D TSE reference sequences. Defect delineability, bone texture, and cartilage relaxation times were quantified. Inter-sequence comparisons were made using appropriate parametric and non-parametric tests. RESULTS: Overall, defect delineability and texture features were not significantly different between the MIXTURE and reference sequences. After defect creation, relaxation times increased significantly in the central femur (for T2) and all regions combined (for T1$ρ$). CONCLUSION: MIXTURE sequences permit time-efficient simultaneous morphologic and quantitative joint assessment based on clinical image contrasts. While providing T2 or T1$ρ$ maps in clinically feasible scan time, morphologic image features, i.e., cartilage defect delineability and bone texture, were comparable between MIXTURE and corresponding reference sequences.
HEX-P is a probe-class mission concept that will combine high spatial resolution X-ray imaging ($<10"$ FWHM) and broad spectral coverage (0.2-80 keV) with an effective area far superior to current facilities' (including XMM-Newton and NuSTAR). These capabilities will enable revolutionary new insights into a variety of important astrophysical problems. We present scientific objectives and simulations of HEX-P observations of the Galactic Center (GC) and Bulge. We demonstrate the unique and powerful capabilities of the HEX-P observatory for studying both X-ray point sources and diffuse X-ray emission. HEX-P will be uniquely equipped to explore a variety of major topics in Galactic astrophysics, allowing us to (1) investigate broad-band properties of X-ray flares emitted from the supermassive black hole (BH) at Sgr A* and probe the associated particle acceleration and emission mechanisms; (2) identify hard X-ray sources detected by NuSTAR and determine X-ray point source populations in different regions and luminosity ranges; (3) determine the distribution of compact object binaries in the nuclear star cluster and the composition of the Galactic Ridge X-ray emission; (4) identify X-ray transients and measure fundamental parameters such as BH spin; (5) find hidden pulsars in the GC; (6) search for BH-OB binaries and hard X-ray flares from young stellar objects in young massive clusters; (7) measure white dwarf (WD) masses of magnetic CVs to deepen our understanding of CV evolution and the origin of WD magnetic fields; (8) explore primary particle accelerators in the GC in synergy with future TeV and neutrino observatories; (9) map out cosmic-ray distributions by observing non-thermal X-ray filaments; (10) explore past X-ray outbursts from Sgr A* through X-ray reflection components from giant molecular clouds.
Submodular maximization is one of the central topics in combinatorial optimization. It has found numerous applications in the real world. Streaming algorithms for submodule maximization have gained attention in recent years, allowing for real-time processing of large data sets by looking at each piece of data only once. However, most of the state-of-the-art algorithms are subject to monotone cardinality constraint. There remain non-negligible gaps with respect to approximation ratios between cardinality and other constraints like $d$-knapsack in non-monotone submodular maximization. In this paper, we propose deterministic algorithms with improved approximation ratios for non-monotone submodular maximization. Specifically, for the cardinality constraint, we provide a deterministic $1/6-ε$ approximation algorithm with $O(\frac{k\log k}ε)$ memory and sublinear query time, while the previous best algorithm is randomized with a $0.1921$ approximation ratio. To the best of our knowledge, this is the first deterministic streaming algorithm for the cardinality constraint. For the $d$-knapsack constraint, we provide a deterministic $\frac{1}{4(d+1)}-ε$ approximation algorithm with $O(\frac{b\log b}ε)$ memory and $O(\frac{\log b}ε)$ query time per element. To the best of our knowledge, there is currently no streaming algorithm for this constraint.
Task-oriented dialogue systems (TDSs) are assessed mainly in an offline setting or through human evaluation. The evaluation is often limited to single-turn or is very time-intensive. As an alternative, user simulators that mimic user behavior allow us to consider a broad set of user goals to generate human-like conversations for simulated evaluation. Employing existing user simulators to evaluate TDSs is challenging as user simulators are primarily designed to optimize dialogue policies for TDSs and have limited evaluation capabilities. Moreover, the evaluation of user simulators is an open challenge. In this work, we propose a metaphorical user simulator for end-to-end TDS evaluation, where we define a simulator to be metaphorical if it simulates user's analogical thinking in interactions with systems. We also propose a tester-based evaluation framework to generate variants, i.e., dialogue systems with different capabilities. Our user simulator constructs a metaphorical user model that assists the simulator in reasoning by referring to prior knowledge when encountering new items. We estimate the quality of simulators by checking the simulated interactions between simulators and variants. Our experiments are conducted using three TDS datasets. The proposed user simulator demonstrates better consistency with manual evaluation than an agenda-based simulator and a seq2seq model on three datasets; our tester framework demonstrates efficiency and has been tested on multiple tasks, such as conversational recommendation and e-commerce dialogues.
Introduction: Quantitative MRI techniques such as T2 and T1\r{ho} mapping are beneficial in evaluating knee joint pathologies; however, long acquisition times limit their clinical adoption. MIXTURE (Multi-Interleaved X-prepared Turbo-Spin Echo with IntUitive RElaxometry) provides a versatile turbo spin-echo (TSE) sequence platform for simultaneous morphologic and quantitative joint imaging yet lacks comparative evaluation in basic and translational research contexts. Methods: Two MIXTURE sequences were designed along clinical requirements: (i) MIX1, combining proton density (PD)-weighted fat-saturated (FS) images and quantitative T2 mapping (acquisition time: 4:59 min), and (ii) MIX2, combining T1-weighted images with quantitative T1\r{ho} mapping (6:38 min). MIXTURE sequences and their reference 2D and 3D TSE counterparts were acquired from ten human cadaveric knee joints using a clinical 3T MRI scanner and knee coil. Contrast, contrast-to-noise ratios, and coefficients of variation were comparatively evaluated using parametric tests. Clinical radiologists (n=3) assessed diagnostic quality as a function of sequence and anatomic structure using 5-point Likert scales and ordinal regression. The significance level was set to α=0.01. Results: MIX1 and MIX2 had at least equal diagnostic quality compared to the 2D and 3D TSE sequences of the same image weighting. Contrast, contrast-to-noise ratios, and coefficients of variation were largely similar for the PD-weighted FS and T1-weighted images. Discussion: In clinically feasible scan times, the MIXTURE sequence platform yields (i) morphologic images of diagnostic quality and adjustable TSE-based contrasts and (ii) quantitative parameter mapping with additional insights on soft tissue composition and ultrastructure.
Evaluating open-domain dialogue systems is challenging for reasons such as the one-to-many problem, i.e., many appropriate responses other than just the golden response. As of now, automatic evaluation methods need better consistency with humans, while reliable human evaluation can be time- and cost-intensive. To this end, we propose the Reference-Assisted Dialogue Evaluation (RADE) approach under the multi-task learning framework, which leverages the pre-created utterance as reference other than the gold response to relief the one-to-many problem. Specifically, RADE explicitly compares reference and the candidate response to predict their overall scores. Moreover, an auxiliary response generation task enhances prediction via a shared encoder. To support RADE, we extend three datasets with additional rated responses other than just a golden response by human annotation. Experiments on our three datasets and two existing benchmarks demonstrate the effectiveness of our method, where Pearson, Spearman, and Kendall correlations with human evaluation outperform state-of-the-art baselines.
The atomic exchange effect will lead to a significant increase in the probability density of $β$ decays below a few keV. This effect is very important for scientific experiments that performed by low-energy electron spectroscopy measurements. However, the atomic exchange effect involves multi-electron interactions, especially for a system with 82 electrons such as lead. Different parameters will lead to different trends in the energy spectrum predicted by the theory, so it is urgent to carry out experimental measurements to provide parameter limits for the theory. The probability increase brought about by the atomic exchange effect is most obvious near 0keV, and the $β$ energy spectrum is accurately measured near this energy point, so as to provide constraints for the physical model of atomic exchange. However, it is extremely difficult to measure the $β$ energy spectrum at 0keV due to the limitations of electronic noise and internal conversion effects. The excited decay path of $^{210}$Pb was taken as the observation object,by measuring the total energy spectrum of $β$ rays and cascaded gamma rays, the precise measurement of the $β$ energy spectrum near 0keV has been completed. The analysis of the $β$ energy spectrum of $^{210}$Pb gives the following conclusions. The experimental results first verified the theory that the exchange effect causes the probability increase at the low energy end near 0keV. At the same time, the experimental results are higher than the existing predictions of the atomic exchange effect. At least for Pb element, all the electron shells have played a role in improving the probability density of the low end of the $β$ energy spectrum. This discovery will promote the theoretical calculation of the $β$ energy spectrum of $^{214}$Pb, at the same time, it also indicates that the reactor neutrinos have a higher probability density at the omnipotent end.
Biological functions of RNAs are determined by their three-dimensional (3D) structures. Thus, given the limited number of experimentally determined RNA structures, the prediction of RNA structures will facilitate elucidating RNA functions and RNA-targeted drug discovery, but remains a challenging task. In this work, we propose a Graph Neural Network (GNN)-based scoring function trained only with the atomic types and coordinates on limited solved RNA 3D structures for distinguishing accurate structural models. The proposed Physics-aware Multiplex Graph Neural Network (PaxNet) separately models the local and non-local interactions inspired by molecular mechanics. Furthermore, PaxNet contains an attention-based fusion module that learns the individual contribution of each interaction type for the final prediction. We rigorously evaluate the performance of PaxNet on two benchmarks and compare it with several state-of-the-art baselines. The results show that PaxNet significantly outperforms all the baselines overall, and demonstrate the potential of PaxNet for improving the 3D structure modeling of RNA and other macromolecules. Our code is available at https://github.com/zetayue/Physics-aware-Multiplex-GNN.
To learn accurate representations of molecules, it is essential to consider both chemical and geometric features. To encode geometric information, many descriptors have been proposed in constrained circumstances for specific types of molecules and do not have the properties to be ``robust": 1. Invariant to rotations and translations; 2. Injective when embedding molecular structures. In this work, we propose a universal and robust Directional Node Pair (DNP) descriptor based on the graph representations of 3D molecules. Our DNP descriptor is robust compared to previous ones and can be applied to multiple molecular types. To combine the DNP descriptor and chemical features in molecules, we construct the Robust Molecular Graph Convolutional Network (RoM-GCN) which is capable to take both node and edge features into consideration when generating molecule representations. We evaluate our model on protein and small molecule datasets. Our results validate the superiority of the DNP descriptor in incorporating 3D geometric information of molecules. RoM-GCN outperforms all compared baselines.
Information Synchronization of semi-structured data across languages is challenging. For instance, Wikipedia tables in one language should be synchronized across languages. To address this problem, we introduce a new dataset InfoSyncC and a two-step method for tabular synchronization. InfoSync contains 100K entity-centric tables (Wikipedia Infoboxes) across 14 languages, of which a subset (3.5K pairs) are manually annotated. The proposed method includes 1) Information Alignment to map rows and 2) Information Update for updating missing/outdated information for aligned tables across multilingual tables. When evaluated on InfoSync, information alignment achieves an F1 score of 87.91 (en <-> non-en). To evaluate information updation, we perform human-assisted Wikipedia edits on Infoboxes for 603 table pairs. Our approach obtains an acceptance rate of 77.28% on Wikipedia, showing the effectiveness of the proposed method.
We present an X-ray spectrum of the diffuse X-ray background (DXRB) between 1.5 and 120 keV, as measured with the Low-Energy Detector (LE) and the High-Energy Detector (HE) aboard the Insight-HXMT satellite, based on 'blank-sky' observations. LE covers a nominal energy range of 1-15 keV and HE 20-250 keV, but calibration issues and data quality narrowed the energy range for this work. The LE background was directly measured with `blind' detector modules, while the HE background was derived from Earth-occultation data. With the LE data alone, the measured DXRB spectrum can be well described by a power law; fitting the LE and HE data jointly, however, a spectral cut-off must be introduced in the model to account for the measurements above 30 keV. Modelling the combined spectrum with a cut-off power law, the best-fit photon index is 1.40, normalisation $9.57$~$\rm ph~cm^{-2}~s^{-1}~keV^{-1}~sr^{-1} $ (at 1 keV), and cut-off energy 55 keV, after correcting for the effects of the Earth albedo and atmospheric emission (which are significant in the HE band). Based on the best-fit cut-off power law, we derived the spectral energy distribution (SED) of the DXRB. The shape of the SED is in general agreement with the published measurements, but the overall normalization is lower by varying amounts, except for the HEAO-1 result, with which our result is in good agreement.
Explanations in conventional recommender systems have demonstrated benefits in helping the user understand the rationality of the recommendations and improving the system's efficiency, transparency, and trustworthiness. In the conversational environment, multiple contextualized explanations need to be generated, which poses further challenges for explanations. To better measure explainability in conversational recommender systems (CRS), we propose ten evaluation perspectives based on concepts from conventional recommender systems together with the characteristics of CRS. We assess five existing CRS benchmark datasets using these metrics and observe the necessity of improving the explanation quality of CRS. To achieve this, we conduct manual and automatic approaches to extend these dialogues and construct a new CRS dataset, namely Explainable Recommendation Dialogues (E-ReDial). It includes 756 dialogues with over 2,000 high-quality rewritten explanations. We compare two baseline approaches to perform explanation generation based on E-ReDial. Experimental results suggest that models trained on E-ReDial can significantly improve explainability while introducing knowledge into the models can further improve the performance. GPT-3 in the in-context learning setting can generate more realistic and diverse movie descriptions. In contrast, T5 training on E-ReDial can better generate clear reasons for recommendations based on user preferences. E-ReDial is available at https://github.com/Superbooming/E-ReDial.
Recent years have seen increasing concerns about the unsafe response generation of large-scale dialogue systems, where agents will learn offensive or biased behaviors from the real-world corpus. Some methods are proposed to address the above issue by detecting and replacing unsafe training examples in a pipeline style. Though effective, they suffer from a high annotation cost and adapt poorly to unseen scenarios as well as adversarial attacks. Besides, the neglect of providing safe responses (e.g. simply replacing with templates) will cause the information-missing problem of dialogues. To address these issues, we propose an unsupervised pseudo-label sampling method, TEMP, that can automatically assign potential safe responses. Specifically, our TEMP method groups responses into several clusters and samples multiple labels with an adaptively sharpened sampling strategy, inspired by the observation that unsafe samples in the clusters are usually few and distribute in the tail. Extensive experiments in chitchat and task-oriented dialogues show that our TEMP outperforms state-of-the-art models with weak supervision signals and obtains comparable results under unsupervised learning settings.
Different with conventional reconfigurable intelligent surface (RIS), simultaneous transmitting and reflecting RIS (STAR-RIS) can reflect and transmit the signals to the receiver. In this paper, to serve more ground users and increase the deployment flexibility, we investigate an unmanned aerial vehicle equipped with a STAR-RIS (STAR-RIS-UAV) aided wireless communications for multi-user networks. Energy splitting (ES) and mode switching (MS) protocols are considered to control the reflection and transmission coefficients of STAR-RIS elements. To maximize the sum rate of the STAR-RIS-UAV aided coordinated multipoint cellular system for multi-user networks, the corresponding beamforming vectors as well as transmitted and reflected coefficients matrices are optimized. Specifically, instead of adopting the alternating optimization, we design an iteration method to optimize all variables for both ES and MS protocols at the same time. Simulation results reveal that STAR-RIS-UAV aided wireless communication system has a much higher sum rate than the system with conventional RIS or without RIS. Furthermore, the proposed structure is more flexible than a fixed STAR-RIS and could greatly promote the sum rate.