arXiv subjects

Wei Lin

Publications and source records attributed to Wei Lin.

At least 199 records · Page 11Linked to original sources

arXiv2024

Enhancing CTR Prediction through Sequential Recommendation Pre-training: Introducing the SRP4CTR Framework

Understanding user interests is crucial for Click-Through Rate (CTR) prediction tasks. In sequential recommendation, pre-training from user historical behaviors through self-supervised learning can better comprehend user dynamic preferences, presenting the potential for direct integration with CTR tasks. Previous methods have integrated pre-trained models into downstream tasks with the sole purpose of extracting semantic information or well-represented user features, which are then incorporated as new features. However, these approaches tend to ignore the additional inference costs to the downstream tasks, and they do not consider how to transfer the effective information from the pre-trained models for specific estimated items in CTR prediction. In this paper, we propose a Sequential Recommendation Pre-training framework for CTR prediction (SRP4CTR) to tackle the above problems. Initially, we discuss the impact of introducing pre-trained models on inference costs. Subsequently, we introduced a pre-trained method to encode sequence side information concurrently.During the fine-tuning process, we incorporate a cross-attention block to establish a bridge between estimated items and the pre-trained model at a low cost. Moreover, we develop a querying transformer technique to facilitate the knowledge transfer from the pre-trained model to industrial CTR models. Offline and online experiments show that our method outperforms previous baseline models.

cs.IR↗

arXiv2024

Decision Focused Causal Learning for Direct Counterfactual Marketing Optimization

Marketing optimization plays an important role to enhance user engagement in online Internet platforms. Existing studies usually formulate this problem as a budget allocation problem and solve it by utilizing two fully decoupled stages, i.e., machine learning (ML) and operation research (OR). However, the learning objective in ML does not take account of the downstream optimization task in OR, which causes that the prediction accuracy in ML may be not positively related to the decision quality. Decision Focused Learning (DFL) integrates ML and OR into an end-to-end framework, which takes the objective of the downstream task as the decision loss function and guarantees the consistency of the optimization direction between ML and OR. However, deploying DFL in marketing is non-trivial due to multiple technological challenges. Firstly, the budget allocation problem in marketing is a 0-1 integer stochastic programming problem and the budget is uncertain and fluctuates a lot in real-world settings, which is beyond the general problem background in DFL. Secondly, the counterfactual in marketing causes that the decision loss cannot be directly computed and the optimal solution can never be obtained, both of which disable the common gradient-estimation approaches in DFL. Thirdly, the OR solver is called frequently to compute the decision loss during model training in DFL, which produces huge computational cost and cannot support large-scale training data. In this paper, we propose a decision focused causal learning framework (DFCL) for direct counterfactual marketing optimization, which overcomes the above technological challenges. Both offline experiments and online A/B testing demonstrate the effectiveness of DFCL over the state-of-the-art methods. Currently, DFCL has been deployed in several marketing scenarios in Meituan, one of the largest online food delivery platform in the world.

cs.LG↗

arXiv2024

Towards Multimodal In-Context Learning for Vision & Language Models

State-of-the-art Vision-Language Models (VLMs) ground the vision and the language modality primarily via projecting the vision tokens from the encoder to language-like tokens, which are directly fed to the Large Language Model (LLM) decoder. While these models have shown unprecedented performance in many downstream zero-shot tasks (eg image captioning, question answers, etc), still little emphasis has been put on transferring one of the core LLM capability of In-Context Learning (ICL). ICL is the ability of a model to reason about a downstream task with a few examples demonstrations embedded in the prompt. In this work, through extensive evaluations, we find that the state-of-the-art VLMs somewhat lack the ability to follow ICL instructions. In particular, we discover that even models that underwent large-scale mixed modality pre-training and were implicitly guided to make use of interleaved image and text information (intended to consume helpful context from multiple images) under-perform when prompted with few-shot demonstrations (in an ICL way), likely due to their lack of direct ICL instruction tuning. To enhance the ICL abilities of the present VLM, we propose a simple yet surprisingly effective multi-turn curriculum-based learning methodology with effective data mixes, leading up to a significant 21.03% (and 11.3% on average) ICL performance boost over the strongest VLM baselines and a variety of ICL benchmarks. Furthermore, we also contribute new benchmarks for ICL evaluation in VLMs and discuss their advantages over the prior art.

cs.CV↗

arXiv2024

Enhancing Vehicle Re-identification and Matching for Weaving Analysis

Vehicle weaving on highways contributes to traffic congestion, raises safety issues, and underscores the need for sophisticated traffic management systems. Current tools are inadequate in offering precise and comprehensive data on lane-specific weaving patterns. This paper introduces an innovative method for collecting non-overlapping video data in weaving zones, enabling the generation of quantitative insights into lane-specific weaving behaviors. Our experimental results confirm the efficacy of this approach, delivering critical data that can assist transportation authorities in enhancing traffic control and roadway infrastructure.

cs.CV↗

arXiv2024

Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache

Large Language Models (LLMs) demonstrate substantial potential across a diverse array of domains via request serving. However, as trends continue to push for expanding context sizes, the autoregressive nature of LLMs results in highly dynamic behavior of the attention layers, showcasing significant differences in computational characteristics and memory requirements from the non-attention layers. This presents substantial challenges for resource management and performance optimization in service systems. Existing static model parallelism and resource allocation strategies fall short when dealing with this dynamicity. To address the issue, we propose Infinite-LLM, a novel LLM serving system designed to effectively handle dynamic context lengths. Infinite-LLM disaggregates attention layers from an LLM's inference process, facilitating flexible and independent resource scheduling that optimizes computational performance and enhances memory utilization jointly. By leveraging a pooled GPU memory strategy across a cluster, Infinite-LLM not only significantly boosts system throughput but also supports extensive context lengths. Evaluated on a dataset with context lengths ranging from a few to 2000K tokens across a cluster with 32 A100 GPUs, Infinite-LLM demonstrates throughput improvement of 1.35-3.4x compared to state-of-the-art methods, enabling efficient and elastic LLM deployment.

cs.DC↗

arXiv2024

Unified Dual-Intent Translation for Joint Modeling of Search and Recommendation

Recommendation systems, which assist users in discovering their preferred items among numerous options, have served billions of users across various online platforms. Intuitively, users' interactions with items are highly driven by their unchanging inherent intents (e.g., always preferring high-quality items) and changing demand intents (e.g., wanting a T-shirt in summer but a down jacket in winter). However, both types of intents are implicitly expressed in recommendation scenario, posing challenges in leveraging them for accurate intent-aware recommendations. Fortunately, in search scenario, often found alongside recommendation on the same online platform, users express their demand intents explicitly through their query words. Intuitively, in both scenarios, a user shares the same inherent intent and the interactions may be influenced by the same demand intent. It is therefore feasible to utilize the interaction data from both scenarios to reinforce the dual intents for joint intent-aware modeling. But the joint modeling should deal with two problems: 1) accurately modeling users' implicit demand intents in recommendation; 2) modeling the relation between the dual intents and the interactive items. To address these problems, we propose a novel model named Unified Dual-Intents Translation for joint modeling of Search and Recommendation (UDITSR). To accurately simulate users' demand intents in recommendation, we utilize real queries from search data as supervision information to guide its generation. To explicitly model the relation among the triplet , we propose a dual-intent translation propagation mechanism to learn the triplet in the same semantic space via embedding translations. Extensive experiments demonstrate that UDITSR outperforms SOTA baselines both in search and recommendation tasks.

cs.IR↗

arXiv2024

Comparison Visual Instruction Tuning

Comparing two images in terms of Commonalities and Differences (CaD) is a fundamental human capability that forms the basis of advanced visual reasoning and interpretation. It is essential for the generation of detailed and contextually relevant descriptions, performing comparative analysis, novelty detection, and making informed decisions based on visual data. However, surprisingly, little attention has been given to these fundamental concepts in the best current mimic of human visual intelligence - Large Multimodal Models (LMMs). We develop and contribute a new two-phase approach CaD-VI for collecting synthetic visual instructions, together with an instruction-following dataset CaD-Inst containing 349K image pairs with CaD instructions collected using CaD-VI. Our approach significantly improves the CaD spotting capabilities in LMMs, advancing the SOTA on a diverse set of related tasks by up to 17.5%. It is also complementary to existing difference-only instruction datasets, allowing automatic targeted refinement of those resources increasing their effectiveness for CaD tuning by up to 10%. Additionally, we propose an evaluation benchmark with 7.5K open-ended QAs to assess the CaD understanding abilities of LMMs.

cs.CV↗

arXiv2024

A Statistical Theory of Regularization-Based Continual Learning

We provide a statistical analysis of regularization-based continual learning on a sequence of linear regression tasks, with emphasis on how different regularization terms affect the model performance. We first derive the convergence rate for the oracle estimator obtained as if all data were available simultaneously. Next, we consider a family of generalized $\ell_2$-regularization algorithms indexed by matrix-valued hyperparameters, which includes the minimum norm estimator and continual ridge regression as special cases. As more tasks are introduced, we derive an iterative update formula for the estimation error of generalized $\ell_2$-regularized estimators, from which we determine the hyperparameters resulting in the optimal algorithm. Interestingly, the choice of hyperparameters can effectively balance the trade-off between forward and backward knowledge transfer and adjust for data heterogeneity. Moreover, the estimation error of the optimal algorithm is derived explicitly, which is of the same order as that of the oracle estimator. In contrast, our lower bounds for the minimum norm estimator and continual ridge regression show their suboptimality. A byproduct of our theoretical analysis is the equivalence between early stopping and generalized $\ell_2$-regularization in continual learning, which may be of independent interest. Finally, we conduct experiments to complement our theory.

cs.LG↗

arXiv2024

Llumnix: Dynamic Scheduling for Large Language Model Serving

Inference serving for large language models (LLMs) is the key to unleashing their potential in people's daily lives. However, efficient LLM serving remains challenging today because the requests are inherently heterogeneous and unpredictable in terms of resource and latency requirements, as a result of the diverse applications and the dynamic execution nature of LLMs. Existing systems are fundamentally limited in handling these characteristics and cause problems such as severe queuing delays, poor tail latencies, and SLO violations. We introduce Llumnix, an LLM serving system that reacts to such heterogeneous and unpredictable requests by runtime rescheduling across multiple model instances. Similar to context switching across CPU cores in modern operating systems, Llumnix reschedules requests to improve load balancing and isolation, mitigate resource fragmentation, and differentiate request priorities and SLOs. Llumnix implements the rescheduling with an efficient and scalable live migration mechanism for requests and their in-memory states, and exploits it in a dynamic scheduling policy that unifies the multiple rescheduling scenarios elegantly. Our evaluations show that Llumnix improves tail latencies by an order of magnitude, accelerates high-priority requests by up to 1.5x, and delivers up to 36% cost savings while achieving similar tail latencies, compared against state-of-the-art LLM serving systems. Llumnix is publicly available at https://github.com/AlibabaPAI/llumnix.

cs.AR↗

arXiv2024

Learning Hamiltonian neural Koopman operator and simultaneously sustaining and discovering conservation law

Accurately finding and predicting dynamics based on the observational data with noise perturbations is of paramount significance but still a major challenge presently. Here, for the Hamiltonian mechanics, we propose the Hamiltonian Neural Koopman Operator (HNKO), integrating the knowledge of mathematical physics in learning the Koopman operator, and making it automatically sustain and even discover the conservation laws. We demonstrate the outperformance of the HNKO and its extension using a number of representative physical systems even with hundreds or thousands of freedoms. Our results suggest that feeding the prior knowledge of the underlying system and the mathematical theory appropriately to the learning framework can reinforce the capability of machine learning in solving physical problems.

math-ph↗

arXiv2024

From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems

Modeling complex systems using standard neural ordinary differential equations (NODEs) often faces some essential challenges, including high computational costs and susceptibility to local optima. To address these challenges, we propose a simulation-free framework, called Fourier NODEs (FNODEs), that effectively trains NODEs by directly matching the target vector field based on Fourier analysis. Specifically, we employ the Fourier analysis to estimate temporal and potential high-order spatial gradients from noisy observational data. We then incorporate the estimated spatial gradients as additional inputs to a neural network. Furthermore, we utilize the estimated temporal gradient as the optimization objective for the output of the neural network. Later, the trained neural network generates more data points through an ODE solver without participating in the computational graph, facilitating more accurate estimations of gradients based on Fourier analysis. These two steps form a positive feedback loop, enabling accurate dynamics modeling in our framework. Consequently, our approach outperforms state-of-the-art methods in terms of training time, dynamics prediction, and robustness. Finally, we demonstrate the superior performance of our framework using a number of representative complex systems.

cs.LG↗

arXiv2024

Switched Flow Matching: Eliminating Singularities via Switching ODEs

Continuous-time generative models, such as Flow Matching (FM), construct probability paths to transport between one distribution and another through the simulation-free learning of the neural ordinary differential equations (ODEs). During inference, however, the learned model often requires multiple neural network evaluations to accurately integrate the flow, resulting in a slow sampling speed. We attribute the reason to the inherent (joint) heterogeneity of source and/or target distributions, namely the singularity problem, which poses challenges for training the neural ODEs effectively. To address this issue, we propose a more general framework, termed Switched FM (SFM), that eliminates singularities via switching ODEs, as opposed to using a uniform ODE in FM. Importantly, we theoretically show that FM cannot transport between two simple distributions due to the existence and uniqueness of initial value problems of ODEs, while these limitations can be well tackled by SFM. From an orthogonal perspective, our framework can seamlessly integrate with the existing advanced techniques, such as minibatch optimal transport, to further enhance the straightness of the flow, yielding a more efficient sampling process with reduced costs. We demonstrate the effectiveness of the newly proposed SFM through several numerical examples.

cs.LG↗

arXiv2024

FESSNC: Fast Exponentially Stable and Safe Neural Controller

In order to stabilize nonlinear systems modeled by stochastic differential equations, we design a Fast Exponentially Stable and Safe Neural Controller (FESSNC) for fast learning controllers. Our framework is parameterized by neural networks, and realizing both rigorous exponential stability and safety guarantees. Concretely, we design heuristic methods to learn the exponentially stable and the safe controllers, respectively, in light of the classic stochastic exponential stability theory and our established theorem on guaranteeing the almost-sure safety for stochastic dynamics. More significantly, to rigorously ensure the stability and the safety guarantees for the learned controllers, we develop a projection operator, projecting to the space of exponentially-stable and safe controllers. To reduce the high computation cost of solving the projection operation, approximate projection operators are delicately proposed with closed forms that map the learned controllers to the target controller space. Furthermore, we employ Hutchinson's trace estimator for a scalable unbiased estimate of the Hessian matrix that is used in the projection operator, which thus allows for computation cost reduction and therefore can accelerate the training and testing processes. More importantly, our approximate projection operations can be applied to the nonparametric control methods to improve their stability and safety performance. We empirically demonstrate the superiority of the FESSNC over the existing methods.

math.OC↗

arXiv2024

A geometric approach for stability analysis of delay systems: Applications to network dynamics

Investigating the network stability or synchronization dynamics of multi-agent systems with time delays is of significant importance in numerous real-world applications. Such investigations often rely on solving the transcendental characteristic equations (TCEs) obtained from linearization of the considered systems around specific solutions. While stability results based on the TCEs with real-valued coefficients induced by symmetric networks in time-delayed models have been extensively explored in the literature, there remains a notable gap in stability analysis for the TCEs with complexvalued coefficients arising from asymmetric networked dynamics with time delays. To address this challenge comprehensively, we propose a rigorously geometric approach. By identifying and studying the stability crossing curves in the complex plane, we are able to determine the stability region of these systems. This approach is not only suitable for analyzing the stability of models with discrete time delays but also for models with various types of delays, including distributed time delays. Additionally, it can also handle random networks. We demonstrate the efficacy of this approach in designing delayed control strategies for car-following systems, mechanical systems, and deep brain stimulation modeling, where involved are complex-valued TCEs or/and different types of delays. All these therefore highlight the broad applicability of our approach across diverse domains.

math.DS↗

arXiv2024

A general multi-wave quasi-resonance theory for lattice energy diffusion

In this letter, a multi-wave quasi-resonance framework is established to analyze energy diffusion in classical lattices, uncovering that it is fundamentally determined by the characteristics of eigenmodes. Namely, based on the presence and the absence of extended modes, lattices fall into two universality classes with qualitatively different thermalization behavior. In particular, we find that while the one with extended modes can be thermalized under arbitrarily weak perturbations in the thermodynamic limit, the other class can be thermalized only when perturbations exceed a certain threshold, revealing for the first time the possibility that a lattice cannot be thermalized, violating the hypothesis of statistical mechanics. Our study addresses conclusively the renowned Fermi-Pasta-Ulam-Tsingou problem for large systems under weak perturbations, underscoring the pivotal roles of both extended and localized modes in facilitating energy diffusion and thermalization processes.

cond-mat.stat-mech↗

arXiv2024

Practical GHz single-cavity all-fiber dual-comb laser for high-speed spectroscopy

Dual-comb spectroscopy (DCS) with few-GHz tooth spacing that provides the optimal trade-off between spectral resolution and refresh rate is a powerful tool for measuring and analyzing rapidly evolving transient events. Despite such an exciting opportunity, existing technologies compromise either the spectral resolution or refresh rate, leaving few-GHz DCS with robust design largely unmet for frontier applications. In this work, we demonstrate a novel GHz DCS by exploring the multimode interference-mediated spectral filtering effect in an all-fiber ultrashort cavity configuration. The GHz single-cavity all-fiber dual-comb source is seeded by a dual-wavelength mode-locked fiber laser operating at fundamental repetition rates of about 1.0 GHz differing by 148 kHz, which has an excellent stability in the free-running state that the Allan deviation is only 101.7 mHz for an average time of 1 second. Thanks to the large repetition rate difference between the asynchronous dichromatic pulse trains, the GHz DCS enables a refresh time as short as 6.75 us, making it promising for studying nonrepeatable transient phenomena in real time. To this end, the practicality of the present GHz DCS is validated by successfully capturing the 'shock waves' of balloon and firecracker explosions outdoors. This GHz single-cavity all-fiber dual-comb system promises a noteworthy improvement in acquisition speed and reliability without sacrificing measurement accuracy, anticipated as a practical tool for high-speed applications.

physics.optics↗

arXiv2024

Real-time Lane-wise Traffic Monitoring in Optimal ROIs

In the US, thousands of Pan, Tilt, and Zoom (PTZ) traffic cameras monitor highway conditions. There is a great interest in using these highway cameras to gather valuable road traffic data to support traffic analysis and decision-making for highway safety and efficient traffic management. However, there are too many cameras for a few human traffic operators to effectively monitor, so a fully automated solution is desired. This paper introduces a novel system that learns the locations of highway lanes and traffic directions from these camera feeds automatically. It collects real-time, lane-specific traffic data continuously, even adjusting for changes in camera angle or zoom. This facilitates efficient traffic analysis, decision-making, and improved highway safety.

cs.CV↗

arXiv2024

CARE: Large Precision Matrix Estimation for Compositional Data

High-dimensional compositional data are prevalent in many applications. The simplex constraint poses intrinsic challenges to inferring the conditional dependence relationships among the components forming a composition, as encoded by a large precision matrix. We introduce a precise specification of the compositional precision matrix and relate it to its basis counterpart, which is shown to be asymptotically identifiable under suitable sparsity assumptions. By exploiting this connection, we propose a composition adaptive regularized estimation (CARE) method for estimating the sparse basis precision matrix. We derive rates of convergence for the estimator and provide theoretical guarantees on support recovery and data-driven parameter tuning. Our theory reveals an intriguing trade-off between identification and estimation, thereby highlighting the blessing of dimensionality in compositional data analysis. In particular, in sufficiently high dimensions, the CARE estimator achieves minimax optimality and performs as well as if the basis were observed. We further discuss how our framework can be extended to handle data containing zeros, including sampling zeros and structural zeros. The advantages of CARE over existing methods are illustrated by simulation studies and an application to inferring microbial ecological networks in the human gut.

stat.ME↗