Author name cluster

Xike Xie

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

13 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference

Yuan Feng
Junlin Lv
Yukun Cao
Xike Xie
S. Kevin Zhou

Large Language Models have excelled in various domains but face efficiency challenges due to the growing Key-Value (KV) cache required for long-sequence inference. Recent efforts aim to reduce KV cache size by evicting vast non-critical cache elements during runtime while preserving generation quality. However, these methods typically allocate compression budgets uniformly across all attention heads, ignoring the unique attention patterns of each head. In this paper, we establish a theoretical loss upper bound between pre- and post-eviction attention output, explaining the optimization target of prior cache eviction methods, while guiding the optimization of adaptive budget allocation. Base on this, we propose {\it Ada-KV}, the first head-wise adaptive budget allocation strategy. It offers plug-and-play benefits, enabling seamless integration with prior cache eviction methods. Extensive evaluations on 13 datasets from Ruler and 16 datasets from LongBench, all conducted under both question-aware and question-agnostic scenarios, demonstrate substantial quality improvements over existing methods. Our code is available at https: //github. com/FFY0/AdaKV.

PDF Details

NeurIPS Conference 2025 Conference Paper

DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion

Jin Li
Zezhong Ding
Xike Xie

Knowledge graphs (KGs) are vital for enabling knowledge reasoning across various domains. Recent KG reasoning methods that integrate both global and local information have achieved promising results. However, existing methods often suffer from score over-smoothing, which blurs the distinction between correct and incorrect answers and hinders reasoning effectiveness. To address this, we propose DuetGraph, a **coarse-to-fine** KG reasoning mechanism with **dual-pathway** global-local fusion. DuetGraph tackles over-smoothing by segregating—rather than stacking—the processing of local (via message passing) and global (via attention) information into two distinct pathways, preventing mutual interference and preserving representational discrimination. In addition, DuetGraph introduces a **coarse-to-fine** optimization, which partitions entities into high- and low-score subsets. This strategy narrows the candidate space and sharpens the score gap between the two subsets, which alleviates over-smoothing and enhances inference quality. Extensive experiments on various datasets demonstrate that DuetGraph achieves state-of-the-art (SOTA) performance, with up to an **8. 7\%** improvement in reasoning quality and a **1. 8$\times$** acceleration in training efficiency.

PDF Details

ICML Conference 2025 Conference Paper

Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams

Yuan Feng
Yukun Cao
Hairu Wang 0002
Xike Xie
S. Kevin Zhou

Sketches, probabilistic structures for estimating item frequencies in infinite data streams with limited space, are widely used across various domains. Recent studies have shifted the focus from handcrafted sketches to neural sketches, leveraging memory-augmented neural networks (MANNs) to enhance the streaming compression capabilities and achieve better space-accuracy trade-offs. However, existing neural sketches struggle to scale across different data domains and space budgets due to inflexible MANN configurations. In this paper, we introduce a scalable MANN architecture that brings to life the Lego sketch, a novel sketch with superior scalability and accuracy. Much like assembling creations with modular Lego bricks, the Lego sketch dynamically coordinates multiple memory bricks to adapt to various space budgets and diverse data domains. Theoretical analysis and empirical studies demonstrate its scalability and superior space-accuracy trade-offs, outperforming existing handcrafted and neural sketches.

Details

IJCAI Conference 2025 Conference Paper

Prototype-based Optimal Transport for Out-of-Distribution Detection

Ao Ke
Wenlong Chen
Chuanwen Feng
Yukun Cao
Xike Xie
S. Kevin Zhou
Lei Feng

Detecting Out-of-Distribution (OOD) inputs is crucial for improving the reliability of deep neural networks in the real-world deployment. In this paper, inspired by the inherent distribution shift between in-distribution (ID) and OOD data, we propose a novel method that leverages optimal transport to measure the distribution discrepancy between test inputs and ID prototypes. The resulting transport costs are used to quantify the individual contribution of each test input to the overall discrepancy, serving as a desirable measure for OOD detection. To address the issue that solely relying on the transport costs to ID prototypes is inadequate for identifying OOD inputs closer to ID data, we generate virtual outliers to approximate the OOD region via linear extrapolation. By combining the transport costs to ID prototypes with the costs to virtual outliers, the detection of OOD data near ID data is emphasized, thereby enhancing the distinction between ID and OOD inputs. Extensive evaluations demonstrate the superiority of our method over state-of-the-art methods.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Attacks on Continual Semantic Segmentation by Perturbing Incremental Samples

Zhidong Yu
Wei Yang
Xike Xie
Zhenbo Shi

As an essential computer vision task, Continual Semantic Segmentation (CSS) has received a lot of attention. However, security issues regarding this task have not been fully studied. To bridge this gap, we study the problem of attacks in CSS in this paper. We first propose a new task, namely, attacks on incremental samples in CSS, and reveal that the attacks on incremental samples corrupt the performance of CSS in both old and new classes. Moreover, we present an adversarial sample generation method based on class shift, namely Class Shift Attack (CS-Attack), which is an offline and easy-to-implement approach for CSS. CS-Attack is able to significantly degrade the performance of models on both old and new classes without knowledge of the incremental learning approach, which undermines the original purpose of the incremental learning, i.e., learning new classes while retaining old knowledge. Experiments show that on the popular datasets Pascal VOC, ADE20k, and Cityscapes, our approach easily degrades the performance of currently popular CSS methods, which reveals the importance of security in CSS.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Mayfly: a Neural Data Structure for Graph Stream Summarization

Yuan Feng
Yukun Cao
Hairu Wang 0002
Xike Xie
S. Kevin Zhou

A graph is a structure made up of vertices and edges used to represent complex relationships between entities, while a graph stream is a continuous flow of graph updates that convey evolving relationships between entities. The massive volume and high dynamism of graph streams promote research on data structures of graph summarization, which provides a concise and approximate view of graph streams with sub-linear space and linear construction time, enabling real-time graph analytics in various domains, such as social networking, financing, and cybersecurity. In this work, we propose the Mayfly, the first neural data structure for summarizing graph streams. The Mayfly replaces handcrafted data structures with better accuracy and adaptivity. To cater to practical applications, Mayfly incorporates two offline training phases. During the larval phase, the Mayfly learns basic summarization abilities from automatically and synthetically constituted meta-tasks, and in the metamorphosis phase, it rapidly adapts to real graph streams via meta-tasks. With specific configurations of information pathways, the Mayfly enables flexible support for miscellaneous graph queries, including edge, node, and connectivity queries. Extensive empirical studies show that the Mayfly significantly outperforms its handcrafted competitors.

Details

IJCAI Conference 2024 Conference Paper

Partial Optimal Transport Based Out-of-Distribution Detection for Open-Set Semi-Supervised Learning

Yilong Ren
Chuanwen Feng
Xike Xie
S. Kevin Zhou

Semi-supervised learning (SSL) is a machine learning paradigm that utilizes both labeled and unlabeled data to enhance the performance of learning tasks. However, SSL methods operate under the assumption that the label spaces of labeled and unlabeled data are identical, which may not hold in open-world applications. In such scenarios, the unlabeled data may contain novel categories that were not presented in the labeled training data, essentially outliers. This specific challenge is referred to as the Open-set Semi-supervised Learning (OSSL) problem. In OSSL, a pivotal concern is the detection of out-of-distribution (OOD) samples within unlabeled data. Existing methods often struggle to provide effective OOD detection strategies, especially when dealing with datasets comprising a large number of training categories. In response to this challenge, we model the OOD detection problem in OSSL as a partial optimal transport (POT) problem. With POT theory, we devise a mass score function to measure the likelihood of a sample being an outlier, which enables a binary classifier for OOD detection. Further, we put forward an OOD loss, enabling the seamless integration of the binary classifier and off-the-shelf SSL methods under OSSL settings, all within an end-to-end training framework. We extensively evaluate our proposal under various datasets and OSSL configurations, consistently demonstrating the superior performance of our proposal. Codes are available at https: //github. com/ryl0427/Code_for_POT_OSSL.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Prompt Learning with Extended Kalman Filter for Pre-trained Language Models

Quan Li
Xike Xie
Chao Wang
S. Kevin Zhou

Prompt learning has gained popularity as a means to leverage the knowledge embedded in pre-trained language models (PLMs) for NLP tasks while using a limited number of trainable parameters. While it has shown promise in tasks like sentiment classification and natural language inference, generating suitable prompts for PLMs, as opposed to human prompts, remains a challenge. In this paper, we introduce an abstraction of the prompt learning process using an extended Kalman filter. Our approach, called Conditional Extended Kalman Filter based on Neural Networks (CEKFNN), effectively infers more appropriate prompt tokens by enhancing the classic extended Kalman filter with PLM's contextual representation power. Specifically, CEKFNN learns transition and emission functions from PLM embeddings of input sentences to infer latent prompt tokens. We refine CEKFNN using an alternate-training approach, retraining a PLM's emission function with prompt tokens inferred by prompt models (PMs), as well as the initial and transition functions. PLM's output labels assist in PMs' training. When updating the pre-trained language model (PLM), we use an adapter approach with few trainable parameters, leaving PLM parameters frozen. We evaluate CEKFNN across open-source PLMs, demonstrating performance improvements over state-of-the-art methods while using a limited number of trainable parameters. It shows that CEKFNN performs on-par or better than fine-tuning, which requires updating all parameters in the PLM.

PDF Details DOI

AAAI Conference 2024 Conference Paper

TIKP: Text-to-Image Knowledge Preservation for Continual Semantic Segmentation

Zhidong Yu
Wei Yang
Xike Xie
Zhenbo Shi

Continual Semantic Segmentation (CSS) is an emerging trend, where catastrophic forgetting has been a perplexing problem. In this paper, we propose a Text-to-Image Knowledge Preservation (TIKP) framework to address this issue. TIKP applies Text-to-Image techniques to CSS by automatically generating prompts and content adaptation. It extracts associations between the labels of seen data and constructs text-level prompts based on these associations, which are preserved and maintained at each incremental step. During training, these prompts generate correlated images to mitigate the catastrophic forgetting. Particularly, as the generated images may have different distributions from the original data, TIKP transfers the knowledge by a content adaption loss, which determines the role played by the generated images in incremental training based on the similarity. In addition, for the classifier, we use the previous model from a different perspective: misclassifying new classes into old objects instead of the background. We propose a knowledge distillation loss based on wrong labels, enabling us to attribute varying weights to individual objects during the distillation process. Extensive experiments conducted in the same setting show that TIKP outperforms state-of-the-art methods by a large margin on benchmark datasets.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Meta-Sketch: A Neural Data Structure for Estimating Item Frequencies of Data Streams

Yukun Cao
Yuan Feng
Xike Xie

To estimate item frequencies of data streams with limited space, sketches are widely used in real applications, including real-time web analytics, network monitoring, and self-driving. Sketches can be viewed as a model which maps the identifier of a stream item to the corresponding frequency domain. Starting from the premise, we envision a neural data structure, which we term the meta-sketch, to go beyond the basic structure of conventional sketches. The meta-sketch learns basic sketching abilities from meta-tasks constituted with synthetic datasets following Zipf distributions in the pre-training phase, and can be fast adapted to real (skewed) distributions in the adaption phase. Extensive experiments demonstrate the performance gains of the meta-sketch and offer insights into our proposals.

PDF Details DOI

IJCAI Conference 2020 Conference Paper

Inductive Link Prediction for Nodes Having Only Attribute Information

Yu Hao
Xin Cao
Yixiang Fang
Xike Xie
Sibo Wang

Predicting the link between two nodes is a fundamental problem for graph data analytics. In attributed graphs, both the structure and attribute information can be utilized for link prediction. Most existing studies focus on transductive link prediction where both nodes are already in the graph. However, many real-world applications require inductive prediction for new nodes having only attribute information. It is more challenging since the new nodes do not have structure information and cannot be seen during the model training. To solve this problem, we propose a model called DEAL, which consists of three components: two node embedding encoders and one alignment mechanism. The two encoders aim to output the attribute-oriented node embedding and the structure-oriented node embedding, and the alignment mechanism aligns the two types of embeddings to build the connections between the attributes and links. Our model DEAL is versatile in the sense that it works for both inductive and transductive link prediction. Extensive experiments on several benchmark datasets show that our proposed model significantly outperforms existing inductive link prediction methods, and also outperforms the state-of-the-art methods on transductive link prediction.

PDF Details DOI

AAAI Conference 2020 Conference Paper

RiskOracle: A Minute-Level Citywide Traffic Accident Forecasting Framework

Zhengyang Zhou
Yang Wang
Xike Xie
Lianliang Chen
Hengchang Liu

Real-time trafﬁc accident forecasting is increasingly important for public safety and urban management (e. g. , real-time safe route planning and emergency response deployment). Previous works on accident forecasting are often performed on hour levels, utilizing existed neural networks with static region-wise correlations taken into account. However, it is still challenging when the granularity of forecasting step improves as the highly dynamic nature of road network and inherent rareness of accident records in one training sample, which leads to biased results and zero-inﬂated issue. In this work, we propose a novel framework RiskOracle, to improve the prediction granularity to minute levels. Specifically, we ﬁrst transform the zero-risk values in labels to ﬁt the training network. Then, we propose the Differential Timevarying Graph neural network (DTGN) to capture the immediate changes of trafﬁc status and dynamic inter-subregion correlations. Furthermore, we adopt multi-task and region selection schemes to highlight citywide most-likely accident subregions, bridging the gap between biased risk values and sporadic accident distribution. Extensive experiments on two real-world datasets demonstrate the effectiveness and scalability of our RiskOracle framework.

PDF Details

IJCAI Conference 2018 Conference Paper

Real-time Traffic Pattern Analysis and Inference with Sparse Video Surveillance Information

Yang Wang
Yiwei Xiao
Xike Xie
Ruoyu Chen
Hengchang Liu

Recent advances in video surveillance systems enable a new paradigm for intelligent urban traffic management systems. Since surveillance cameras are usually sparsely located to cover key regions of the road under surveillance, it is a big challenge to perform a complete real-time traffic pattern analysis based on incomplete sparse surveillance information. As a result, existing works mostly focus on predicting traffic volumes with historical records available at a particular location and may not provide a complete picture of real-time traffic patterns. To this end, in this paper, we go beyond existing works and tackle the challenges of traffic flow analysis from three perspectives. First, we train the transition probabilities to capture vehicles' movement patterns. The transition probabilities are trained from third-party vehicle GPS data, and thus can work in the area even if there is no camera. Second, we exploit the Multivariate Normal Distribution model together with the transferred probabilities to estimate the unobserved traffic patterns. Third, we propose an algorithm for real-time traffic inference with surveillance as a complement source of information. Finally, experiments on real-world data show the effectiveness of our approach.

PDF Details