arXiv subjects

Mingsheng Shang

Publications and source records attributed to Mingsheng Shang.

28 records · Page 2Linked to original sources

arXiv2025

IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval

We introduce IFIR, the first comprehensive benchmark designed to evaluate instruction-following information retrieval (IR) in expert domains. IFIR includes 2,426 high-quality examples and covers eight subsets across four specialized domains: finance, law, healthcare, and science literature. Each subset addresses one or more domain-specific retrieval tasks, replicating real-world scenarios where customized instructions are critical. IFIR enables a detailed analysis of instruction-following retrieval capabilities by incorporating instructions at different levels of complexity. We also propose a novel LLM-based evaluation method to provide a more precise and reliable assessment of model performance in following instructions. Through extensive experiments on 15 frontier retrieval models, including those based on LLMs, our results reveal that current models face significant challenges in effectively following complex, domain-specific instructions. We further provide in-depth analyses to highlight these limitations, offering valuable insights to guide future advancements in retriever development.

cs.CL↗

arXiv2024

Self-Supervised Spatial-Temporal Normality Learning for Time Series Anomaly Detection

Time Series Anomaly Detection (TSAD) finds widespread applications across various domains such as financial markets, industrial production, and healthcare. Its primary objective is to learn the normal patterns of time series data, thereby identifying deviations in test samples. Most existing TSAD methods focus on modeling data from the temporal dimension, while ignoring the semantic information in the spatial dimension. To address this issue, we introduce a novel approach, called Spatial-Temporal Normality learning (STEN). STEN is composed of a sequence Order prediction-based Temporal Normality learning (OTN) module that captures the temporal correlations within sequences, and a Distance prediction-based Spatial Normality learning (DSN) module that learns the relative spatial relations between sequences in a feature space. By synthesizing these two modules, STEN learns expressive spatial-temporal representations for the normal patterns hidden in the time series data. Extensive experiments on five popular TSAD benchmarks show that STEN substantially outperforms state-of-the-art competing methods. Our code is available at https://github.com/mala-lab/STEN.

cs.LG↗

arXiv2022

Zero Stability Well Predicts Performance of Convolutional Neural Networks

The question of what kind of convolutional neural network (CNN) structure performs well is fascinating. In this work, we move toward the answer with one more step by connecting zero stability and model performance. Specifically, we found that if a discrete solver of an ordinary differential equation is zero stable, the CNN corresponding to that solver performs well. We first give the interpretation of zero stability in the context of deep learning and then investigate the performance of existing first- and second-order CNNs under different zero-stable circumstances. Based on the preliminary observation, we provide a higher-order discretization to construct CNNs and then propose a zero-stable network (ZeroSNet). To guarantee zero stability of the ZeroSNet, we first deduce a structure that meets consistency conditions and then give a zero stable region of a training-free parameter. By analyzing the roots of a characteristic equation, we theoretically obtain the optimal coefficients of feature maps. Empirically, we present our results from three aspects: We provide extensive empirical evidence of different depth on different datasets to show that the moduli of the characteristic equation's roots are the keys for the performance of CNNs that require historical features; Our experiments show that ZeroSNet outperforms existing CNNs which is based on high-order discretization; ZeroSNets show better robustness against noises on the input. The source code is available at \url{https://github.com/LongJin-lab/ZeroSNet}.

cs.LG↗

arXiv2021

Activated Gradients for Deep Neural Networks

Deep neural networks often suffer from poor performance or even training failure due to the ill-conditioned problem, the vanishing/exploding gradient problem, and the saddle point problem. In this paper, a novel method by acting the gradient activation function (GAF) on the gradient is proposed to handle these challenges. Intuitively, the GAF enlarges the tiny gradients and restricts the large gradient. Theoretically, this paper gives conditions that the GAF needs to meet, and on this basis, proves that the GAF alleviates the problems mentioned above. In addition, this paper proves that the convergence rate of SGD with the GAF is faster than that without the GAF under some assumptions. Furthermore, experiments on CIFAR, ImageNet, and PASCAL visual object classes confirm the GAF's effectiveness. The experimental results also demonstrate that the proposed method is able to be adopted in various deep neural networks to improve their performance. The source code is publicly available at https://github.com/LongJin-lab/Activated-Gradients-for-Deep-Neural-Networks.

cs.CV↗

arXiv2020

TempNodeEmb:Temporal Node Embedding considering temporal edge influence matrix

Understanding the evolutionary patterns of real-world evolving complex systems such as human interactions, transport networks, biological interactions, and computer networks has important implications in our daily lives. Predicting future links among the nodes in such networks reveals an important aspect of the evolution of temporal networks. To analyse networks, they are mapped to adjacency matrices, however, a single adjacency matrix cannot represent complex relationships (e.g. temporal pattern), and therefore, some approaches consider a simplified representation of temporal networks but in high-dimensional and generally sparse matrices. As a result, adjacency matrices cannot be directly used by machine learning models for making network or node level predictions. To overcome this problem, automated frameworks are proposed for learning low-dimensional vectors for nodes or edges, as state-of-the-art techniques in predicting temporal patterns in networks such as link prediction. However, these models fail to consider temporal dimensions of the networks. This gap motivated us to propose in this research a new node embedding technique which exploits the evolving nature of the networks considering a simple three-layer graph neural network at each time step, and extracting node orientation by Given's angle method. To prove our proposed algorithm's efficiency, we evaluated the efficiency of our proposed algorithm against six state-of-the-art benchmark network embedding models, on four real temporal networks data, and the results show our model outperforms other methods in predicting future links in temporal networks.

cs.LG↗

arXiv2016

Identifying emerging influential Nodes in evolving networks: Exploiting strength of weak nodes

Identifying emerging influential or popular node/item in future on network is a current interest of the researchers. Most of previous works focus on identifying leaders in time evolving networks on the basis of network structure or node's activity separate way. In this paper, we have proposed a hybrid model which considers both, node's structural centrality and recent activity of nodes together. We consider that the node is active when it is receiving more links in a given recent time window, rather than in the whole past life of the node. Furthermore our model is flexible to implement structural rank such as PageRank and webpage click information as activity of the node. For testing the performance of our model, we adopt the PageRank algorithm and linear preferential attachment based model as the baseline methods. Experiments on three real data sets (i.e Movielens, Netflix and Facebook wall post data set), we found that our model shows better performance in terms of finding the emerging influential nodes that were not popular in past.

cs.SI↗

arXiv2015

Group-based ranking method for online rating systems with spamming attacks

Ranking problem has attracted much attention in real systems. How to design a robust ranking method is especially significant for online rating systems under the threat of spamming attacks. By building reputation systems for users, many well-performed ranking methods have been applied to address this issue. In this Letter, we propose a group-based ranking method that evaluates users' reputations based on their grouping behaviors. More specifically, users are assigned with high reputation scores if they always fall into large rating groups. Results on three real data sets indicate that the present method is more accurate and robust than correlation-based method in the presence of spamming attacks.

cs.IR↗

arXiv2012

Variability of Contact Process in Complex Networks

We study numerically how the structures of distinct networks influence the epidemic dynamics in contact process. We first find that the variability difference between homogeneous and heterogeneous networks is very narrow, although the heterogeneous structures can induce the lighter prevalence. Contrary to non-community networks, strong community structures can cause the secondary outbreak of prevalence and two peaks of variability appeared. Especially in the local community, the extraordinarily large variability in early stage of the outbreak makes the prediction of epidemic spreading hard. Importantly, the bridgeness plays a significant role in the predictability, meaning the further distance of the initial seed to the bridgeness, the less accurate the predictability is. Also, we investigate the effect of different disease reaction mechanisms on variability, and find that the different reaction mechanisms will result in the distinct variabilities at the end of epidemic spreading.

physics.soc-ph↗

arXiv2011

Empirical analysis of web-based user-object bipartite networks

Understanding the structure and evolution of web-based user-object networks is a significant task since they play a crucial role in e-commerce nowadays. This Letter reports the empirical analysis on two large-scale web sites, audioscrobbler.com and del.icio.us, where users are connected with music groups and bookmarks, respectively. The degree distributions and degree-degree correlations for both users and objects are reported. We propose a new index, named collaborative clustering coefficient, to quantify the clustering behavior based on the collaborative selection. Accordingly, the clustering properties and clustering-degree correlations are investigated. We report some novel phenomena well characterizing the selection mechanism of web users and outline the relevance of these phenomena to the information recommendation problem.

physics.data-an↗

arXiv2011

The reinforcing influence of recommendations on global diversification

Recommender systems are promising ways to filter the overabundant information in modern society. Their algorithms help individuals to explore decent items, but it is unclear how they allocate popularity among items. In this paper, we simulate successive recommendations and measure their influence on the dispersion of item popularity by Gini coefficient. Our result indicates that local diffusion and collaborative filtering reinforce the popularity of hot items, widening the popularity dispersion. On the other hand, the heat conduction algorithm increases the popularity of the niche items and generates smaller dispersion of item popularity. Simulations are compared to mean-field predictions. Our results suggest that recommender systems have reinforcing influence on global diversification.

physics.soc-ph↗