Jie Yin

NeurIPS Conference 2025 Conference Paper

MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning

• Han Wu
• Jie Yin

Few-shot knowledge graph relational learning seeks to perform reasoning over relations given only a limited number of training examples. While existing approaches largely adopt a meta-learning framework for enabling fast adaptation to new relations, they suffer from two key pitfalls. First, they learn relation meta-knowledge in isolation, failing to capture common relational patterns shared across tasks. Second, they struggle to effectively incorporate local, task-specific contexts crucial for rapid adaptation. To address these limitations, we propose MoEMeta, a novel meta-learning framework that disentangles globally shared knowledge from task-specific contexts to enable both effective model generalization and rapid adaptation. MoEMeta introduces two key innovations: (i) a mixture-of-experts (MoE) model that learns globally shared relational prototypes to enhance generalization, and (ii) a task-tailored adaptation mechanism that captures local contexts for fast task-specific adaptation. By balancing global generalization with local adaptability, MoEMeta significantly advances few-shot relational learning. Extensive experiments and analyses on three KG benchmarks show that MoEMeta consistently outperforms existing baselines, achieving state-of-the-art performance.

NeurIPS Conference 2025 Conference Paper

Results of the Big ANN: NeurIPS’23 competition

• Harsha Vardhan simhadri
• Martin Aumüller
• Matthijs Douze
• Dmitry Baranchuk
• Amir Ingber
• Edo Liberty
• George Williams
• Ben Landrum

The 2023 Big ANN Challenge, held at NeurIPS 2023, focused on advancing the state-of-the-art in indexing data structures and search algorithms for practical variants of Approximate Nearest Neighbor (ANN) search that reflect its the growing complexity and diversity of workloads. Unlike prior challenges that emphasized scaling up classical ANN search (Simhadri et al. , NeurIPS 2021), this competition addressed sparse, filtered, out-of-distribution, and streaming variants of ANNS. Participants developed and submitted innovative solutions that were evaluated on new standard datasets with constrained computational resources. The results showcased significant improvements in search accuracy and efficiency, with notable contributions from both academic and industrial teams. This paper summarizes the competition tracks, datasets, evaluation metrics, and the innovative approaches of the top-performing submissions, providing insights into the current advancements and future directions in the field of approximate nearest neighbor search.

IROS Conference 2025 Conference Paper

Towards Robust Sensor-Fusion Ground SLAM: A Comprehensive Benchmark and A Resilient Framework

• Deteng Zhang
• Junjie Zhang
• Yan Sun
• Tao Li
• Hao Yin
• Hongzhao Xie
• Jie Yin

Considerable advancements have been achieved in SLAM methods tailored for structured environments, yet their robustness under challenging corner cases remains a critical limitation. Although multi-sensor fusion approaches integrating diverse sensors have shown promising performance improvements, the research community faces two key barriers: On one hand, the lack of standardized and configurable benchmarks that systematically evaluate SLAM algorithms under diverse degradation scenarios hinders comprehensive performance assessment. While on the other hand, existing SLAM frameworks primarily focus on fusing a limited set of sensor types, without effectively addressing adaptive sensor selection strategies for varying environmental conditions. To bridge these gaps, we make three key contributions: First, we introduce M3DGR dataset: a sensor-rich benchmark with systematically induced degradation patterns including visual challenge, LiDAR degeneracy, wheel slippage and GNSS denial. Second, we conduct a comprehensive evaluation of forty SLAM systems on M3DGR, providing critical insights into their robustness and limitations under challenging real-world conditions. Third, we develop a resilient modular multi-sensor fusion framework named Ground-Fusion++, which demonstrates robust performance by coupling GNSS, RGB-D, LiDAR, IMU (Inertial Measurement Unit) and wheel odometry. Codes 1 and datasets 2 are publicly available.

IROS Conference 2024 Conference Paper

Disentangled Acoustic Fields For Multimodal Physical Scene Understanding

• Jie Yin
• Andrew Luo
• Yilun Du
• Anoop Cherian
• Tim K. Marks
• Jonathan Le Roux
• Chuang Gan 0001

We study the problem of multimodal physical scene understanding, where an embodied agent needs to find fallen objects by inferring object properties, direction, and distance of an impact sound source. Previous works adopt feed-forward neural networks to directly regress the variables from sound, leading to poor generalization and domain adaptation issues. In this paper, we illustrate that learning a disentangled model of acoustic formation, referred to as disentangled acoustic field (DAF), to capture the sound generation and propagation process, enables the embodied agent to construct a spatial uncertainty map over where the objects may have fallen. We demonstrate that our analysis-by-synthesis framework can jointly infer sound properties by explicitly decomposing and factorizing the latent space of the disentangled model. We further show that the spatial uncertainty map can significantly improve the success rate for the localization of fallen objects by proposing multiple plausible exploration locations.

ICRA Conference 2024 Conference Paper

Ground-Fusion: A Low-cost Ground SLAM System Robust to Corner Cases

• Jie Yin
• Ang Li
• Wei Xi
• Wenxian Yu
• Danping Zou

We introduce Ground-Fusion, a low-cost sensor fusion simultaneous localization and mapping (SLAM) system for ground vehicles. Our system features efficient initialization, effective sensor anomaly detection and handling, real-time dense color mapping, and robust localization in diverse environments. We tightly integrate RGB-D images, inertial measurements, wheel odometer and GNSS signals within a factor graph to achieve accurate and reliable localization both indoors and outdoors. To ensure successful initialization, we propose an efficient strategy that comprises three different methods: stationary, visual, and dynamic, tailored to handle diverse cases. Furthermore, we develop mechanisms to detect sensor anomalies and degradation, handling them adeptly to maintain system accuracy. Our experimental results on both public and self-collected datasets demonstrate that Ground-Fusion outperforms existing low-cost SLAM systems in corner cases. We release the code and datasets at https://github.com/SJTU-ViSYS/Ground-Fusion.

IJCAI Conference 2024 Conference Paper

Navigating Continual Test-time Adaptation with Symbiosis Knowledge

• Xu Yang
• Moqi Li
• Jie Yin
• Kun Wei
• Cheng Deng

Continual test-time domain adaptation seeks to adapt the source pre-trained model to a continually changing target domain without incurring additional data acquisition or labeling costs. Unfortunately, existing mainstream methods may result in a detrimental cycle. This is attributed to noisy pseudo-labels caused by the domain shift, which immediately negatively impacts the model's knowledge. The long-term accumulation of these negative effects exacerbates the model's difficulty in generalizing to future domain shifts and contributes to catastrophic forgetting. To address these challenges, this paper introduces a Dual-stream Network that independently optimizes different parameters in each stream to capture symbiotic knowledge from continual domains, thereby ensuring generalization while enhancing instantaneous discrimination. Furthermore, to prevent catastrophic forgetting, a weighted soft parameter alignment method is designed to leverage knowledge from the source model. Finally, efforts are made to calibrate and explore reliable supervision signals to mitigate instantaneous negative optimization. These include label calibration with prior knowledge, label selection using self-adaptive confidence thresholds, and a soft-weighted contrastive module for capturing potential semantics. Extensive experimental results demonstrate that our method achieves state-of-the-art performance on several benchmark datasets.

IS Journal 2019 Journal Article

Introduction to the Special Issue on AI for Disaster Management and Resilience

• Yu-Ru Lin
• Carlos Castillo
• Jie Yin

The articles in this special section provide a forum on the burgeoning topic of artificial intelligence (AI) for disaster management and resilience.

IJCAI Conference 2017 Conference Paper

User Profile Preserving Social Network Embedding

• Daokun Zhang
• Jie Yin
• Xingquan Zhu
• Chengqi Zhang

This paper addresses social network embedding, which aims to embed social network nodes, including user profile information, into a latent low-dimensional space. Most of the existing works on network embedding only consider network structure, but ignore user-generated content that could be potentially helpful in learning a better joint network representation. Different from rich node content in citation networks, user profile information in social networks is useful but noisy, sparse, and incomplete. To properly utilize this information, we propose a new algorithm called User Profile Preserving Social Network Embedding (UPP-SNE), which incorporates user profile with network structure to jointly learn a vector representation of a social network. The theme of UPP-SNE is to embed user profile information via a nonlinear mapping into a consistent subspace, where network structure is seamlessly encoded to jointly learn informative node representations. Extensive experiments on four real-world social networks show that compared to state-of-the-art baselines, our method learns better social network representations and achieves substantial performance gains in node classification and clustering tasks.

AAAI Conference 2016 Conference Paper

Submodular Asymmetric Feature Selection in Cascade Object Detection

• Baosheng Yu
• Meng Fang
• Dacheng Tao
• Jie Yin

A cascade classifier has turned out to be effective in slidingwindow based real-time object detection. In a cascade classifier, node learning is the key process, which includes feature selection and classifier design. Previous algorithms fail to effectively tackle the asymmetry and intersection problems existing in cascade classification, thereby limiting the performance of object detection. In this paper, we improve current feature selection algorithm by addressing both asymmetry and intersection problems. We formulate asymmetric feature selection as a submodular function maximization problem. We then propose a new algorithm SAFS with formal performance guarantee to solve this problem. We use face detection as a case study and perform experiments on two real-world face detection datasets. The experimental results demonstrate that our algorithm SAFS outperforms the state-of-art feature selection algorithms in cascade object detection, such as FFS and LACBoost.

IJCAI Conference 2015 Conference Paper

Using Social Media to Enhance Emergency Situation Awareness: Extended Abstract

• Jie Yin
• Sarvnaz Karimi
• Andrew Lampert
• Mark Cameron
• Bella Robinson
• Robert Power

Social media platforms, such as Twitter, offer a rich source of real-time information about real-world events, particularly during mass emergencies. Sifting valuable information from social media provides useful insight into time-critical situations for emergency officers to understand the impact of hazards and act on emergency responses in a timely manner. This work focuses on analyzing Twitter messages generated during natural disasters, and shows how natural language processing and data mining techniques can be utilized to extract situation awareness information from Twitter. We present key relevant approaches that we have investigated including burst detection, tweet filtering and classification, online clustering, and geotagging.

AAAI Conference 2014 Conference Paper

Active Learning for Crowdsourcing Using Knowledge Transfer

• Meng Fang
• Jie Yin
• Dacheng Tao

This paper studies the active learning problem in crowdsourcing settings, where multiple imperfect annotators with varying levels of expertise are available for labeling the data in a given task. Annotations collected from these labelers may be noisy and unreliable, and the quality of labeled data needs to be maintained for data mining tasks. Previous solutions have attempted to estimate individual users’ reliability based on existing knowledge in each task, but for this to be effective each task requires a large quantity of labeled data to provide accurate estimates. In practice, annotation budgets for a given task are limited, so each instance can be presented to only a few users, each of whom can only label a few examples. To overcome data scarcity we propose a new probabilistic model that transfers knowledge from abundant unlabeled data in auxiliary domains to help estimate labelers’ expertise. Based on this model we present a novel active learning algorithm that: a) simultaneously selects the most informative example and b) queries its label from the labeler with the best expertise. Experiments on both text and image datasets demonstrate that our proposed method outperforms other stateof-the-art active learning methods.

IS Journal 2012 Journal Article

Using Social Media to Enhance Emergency Situation Awareness

• Jie Yin
• Andrew Lampert
• Mark Cameron
• Bella Robinson
• Robert Power

The described system uses natural language processing and data mining techniques to extract situation awareness information from Twitter messages generated during various disasters and crises.

IJCAI Conference 2011 Conference Paper

Similarity-Based Approach for Positive and Unlabeled Learning

• Yanshan Xiao
• Bo Liu
• Jie Yin
• Longbing Cao
• Chengqi Zhang
• Zhifeng Hao

Positive and unlabelled learning (PU learning) has been investigated to deal with the situation where only the positive examples and the unlabelled examples are available. Most of the previous works focus on identifying some negative examples from the unlabelled data, so that the supervised learning methods can be applied to build a classifier. However, for the remaining unlabelled data, which can not be explicitly identified as positive or negative (we call them ambiguous examples), they either exclude them from the training phase or simply enforce them to either class. Consequently, their performance may be constrained. This paper proposes a novel approach, called similarity-based PU learning (SPUL) method, by associating the ambiguous examples with two similarity weights, which indicate the similarity of an ambiguous example towards the positive class and the negative class, respectively. The local similarity-based and global similarity-based mechanisms are proposed to generate the similarity weights. The ambiguous examples and their similarity-weights are thereafter incorporated into an SVM-based learning phase to build a more accurate classifier. Extensive experiments on real-world datasets have shown that SPUL outperforms state-of-the-art PU learning methods.

IJCAI Conference 2009 Conference Paper

• Derek Hao Hu
• Xian-Xing Zhang
• Jie Yin
• Vincent Wenchen Zheng
• Qiang Yang

Detecting abnormal activities from sensor readings is an important research problem in activity recognition. A number of different algorithms have been proposed in the past to tackle this problem. Many of the previous state-based approaches suffer from the problem of failing to decide the appropriate number of states, which are difficult to find through a trial-and-error approach, in real-world applications. In this paper, we propose an accurate and flexible framework for abnormal activity recognition from sensor readings that involves less human tuning of model parameters. Our approach first applies a Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM), which supports an infinite number of states, to automatically find an appropriate number of states. We incorporate a Fisher Kernel into the One-Class Support Vector Machine (OCSVM) model to filter out the activities that are likely to be normal. Finally, we derive an abnormal activity model from the normal activity models to reduce false positive rate in an unsupervised manner. Our main contribution is that our proposed HDP-HMM models can decide the appropriate number of states automatically, and that by incorporating a Fisher Kernel into the OCSVM model, we can combine the advantages from generative model and discriminative model. We demonstrate the effectiveness of our approach by using several real-world datasets to test our algorithm’s performance.

IJCAI Conference 2009 Conference Paper

• Jie Yin
• Derek Hao Hu
• Qiang Yang

Event detection is a critical task in sensor networks for a variety of real-world applications. Many realworld events often exhibit complex spatio-temporal patterns whereby they manifest themselves via observations over time and space proximities. These spatio-temporal events cannot be handled well by many of the previous approaches. In this paper, we propose a new Spatio-Temporal Event Detection (STED) algorithm in sensor networks based on a dynamic conditional random field (DCRF) model. Our STED method handles the uncertainty of sensor data explicitly and permits neighborhood interactions in both observations and event labels. Experiments on both real data and synthetic data demonstrate that our STED method can provide accurate event detection in near real time even for large-scale sensor networks.

AAAI Conference 2005 Conference Paper

Activity Recognition through Goal-Based Segmentation

• Jie Yin
• Qiang Yang

A major issue in activity recognition in a sensor network is how to automatically segment the low-level signal sequences in order to optimize the probabilistic recognition models for goals and activities. Past efforts have relied on segmenting the signal sequences by hand, which is both time-consuming and error-prone. In our view, segments should correspond to atomic human activities that enable a goal-recognizer to operate optimally; the two are intimately related. In this paper, we present a novel method for building probabilistic activity models at the same time as we segment signal sequences into motion patterns. We model each motion pattern as a linear dynamic model and the transitions between motion patterns as a Markov process conditioned on goals. Our EM learning algorithm simultaneously learns the motion-pattern boundaries and probabilistic models for goals and activities, which in turn can be used to accurately recognize activities in an online phase. A major advantage of our algorithm is that it can reduce the human effort in segmenting and labeling signal sequences. We demonstrate the effectiveness of our algorithm using the data collected in a real wireless environment.

AAAI Conference 2004 Conference Paper

High-Level Goal Recognition in a Wireless LAN

• Jie Yin

Plan recognition has traditionally been developed for logically encoded application domains with a focus on logical reasoning. In this paper, we present an integrated plan-recognition model that combines low-level sensory readings with high-level goal inference. A twolevel architecture is proposed to infer a user’s goals in a complex indoor environment using an RF-based wireless network. The novelty of our work derives from our ability to infer a user’s goals from sequences of signal trajectory, and the ability for us to make a tradeoff between model accuracy and inference efficiency. The model relies on a dynamic Bayesian network to infer a user’s actions from raw signals, and an N-gram model to infer the users’ goals from actions. We present a method for constructing the model from the past data and demonstrate the effectiveness of our proposed solution through empirical studies using some real data that we have collected.