Generative modeling has transformed many fields, such as language and visual modeling, while its application in financial markets remains under-explored. As the minimal unit within a financial market is an order, order-flow modeling represents a fundamental generative financial task. However, current approaches often yield unsatisfactory fidelity in generating order flow, and their generation lacks controllability, thereby limiting their practical applications. In this paper, we formulate the challenge of controllable financial market generation, and propose a Diffusion Guided Meta Agent (DigMA) model to address it. Specifically, we employ a conditional diffusion model to capture the dynamics of the market state represented by time-evolving distribution parameters of the mid-price return rate and the order arrival rate, and we define a meta agent with financial economic priors to generate orders from the corresponding distributions. Extensive experimental results show that DigMA achieves superior controllability and generation fidelity. Moreover, we validate its effectiveness as a generative environment for downstream high-frequency trading tasks and its computational efficiency.

Time series generation models are crucial for applications like data augmentation and privacy preservation. Most existing time series generation models are typically designed to generate data from one specified domain. While leveraging data from other domain for better generalization is proved to work in other application areas, this approach remains challenging for time series modeling due to the large divergence in patterns among different real world time series categories. In this paper, we propose a multi-domain time series diffusion model with domain prompts, named TimeDP. In TimeDP, we utilize a time series semantic prototype module which defines time series prototypes to represent time series basis, each prototype vector serving as "word" representing some elementary time series feature. A prototype assignment module is applied to extract the extract domain specific prototype weights, for learning domain prompts as generation condition. During sampling, we extract ``domain prompt" with few-shot samples from the target domain and use the domain prompts as condition to generate time series samples. Experiments demonstrate that our method outperforms baselines to provide the state-of-the-art in-domain generation quality and strong unseen domain generation capability.

Recent talking avatar generation models have made strides in achieving realistic and accurate lip synchronization with the audio, but often fall short in controlling and conveying detailed expressions and emotions of the avatar, making the generated video less vivid and controllable. In this paper, we propose a text-guided approach for generating emotionally expressive 2D avatars, offering fine-grained control, improved interactivity, and generalizability to the resulting video. Our framework, named InstructAvatar, leverages a natural language interface to control the emotion as well as the facial motion of avatars. Technically, we utilize GPT-4V to design an automatic annotation pipeline, constructing an instruction-video paired training dataset. This is combined with a novel two-branch diffusion-based generator to predict avatars using both audio and text instructions simultaneously. Experimental results demonstrate that InstructAvatar produces results that align well with both conditions, and outperforms existing methods in fine-grained emotion control, lip-sync quality, and naturalness.

Vision-language retrieval-augmented generation (RAG) has become an effective approach for tackling Knowledge-Based Visual Question Answering (KB-VQA), which requires external knowledge beyond the visual content presented in images.The effectiveness of Vision-language RAG systems hinges on multimodal retrieval, which is inherently challenging due to the diverse modalities and knowledge granularities in both queries and knowledge bases.Existing methods have not fully tapped into the potential interplay between these elements.We propose a multimodal RAG system featuring a coarse-to-fine, multi-step retrieval that harmonizes multiple granularities and modalities to enhance efficacy.Our system begins with a broad initial search aligning knowledge granularity for cross-modal retrieval, followed by a multimodal fusion reranking to capture the nuanced multimodal information for top entity selection.A text reranker then filters out the most relevant fine-grained section for augmented generation.Extensive experiments on the InfoSeek and Encyclopedic-VQA benchmarks show our method achieves state-of-the-art retrieval performance and highly competitive answering results, underscoring its effectiveness in advancing KB-VQA systems.

In this work, we investigate automatic design composition from multimodal graphic elements. Although recent studies have developed various generative models for graphic design, they usually face the following limitations: they only focus on certain subtasks and are far from achieving the design composition task; they do not consider the hierarchical information of graphic designs during the generation process. To tackle these issues, we introduce the layered design principle into Large Multimodal Models (LMMs) and propose a novel approach, called LaDeCo, to accomplish this challenging task. Specifically, LaDeCo first performs layer planning for a given element set, dividing the input elements into different semantic layers according to their contents. Based on the planning results, it subsequently predicts element attributes that control the design composition in a layer-wise manner, and includes the rendered image of previously generated layers into the context. With this insightful design, LaDeCo decomposes the difficult task into smaller manageable steps, making the genera tion process smoother and clearer. The experimental results demonstrate the effectiveness of LaDeCo in design composition. Furthermore, we show that LaDeCo enables some interesting applications in graphic design, such as resolution adjustment, design decoration, design variation, etc. In addition, it even outperforms the specialized models in some design subtasks without any task-specific training.

Recent advancements in video autoencoders (Video AEs) have significantly improved the quality and efficiency of video generation. In this paper, we propose a novel and compact video autoencoder, VidTwin, that decouples video into two distinct latent spaces: Structure latent vectors, which capture overall content and global movement, and Dynamics latent vectors, which represent fine-grained details and rapid movements. Specifically, our approach leverages an Encoder-Decoder backbone, augmented with two submodules for extracting these latent spaces, respectively. The first submodule employs a Q-Former to extract low-frequency motion trends, followed by downsampling blocks to remove redundant content details. The second averages the latent vectors along the spatial dimension to capture rapid motion. Extensive experiments show that VidTwin achieves a high compression rate of 0.20% with high reconstruction quality (PSNR of 28.14 on the MCL-JCV dataset), and performs efficiently and effectively in downstream generative tasks. Moreover, our model demonstrates explainability and scalability, paving the way for future research in video latent representation and generation.

Generative models aim to simulate realistic effects of various actions across different contexts, from text generation to visual effects. Despite significant efforts to build real-world simulators, the application of generative models to virtual worlds, like financial markets, remains under-explored. In financial markets, generative models can simulate complex market effects of participants with various behaviors, enabling interaction under different market conditions, and training strategies without financial risk. This simulation relies on the finest structured data in financial market like orders thus building the finest realistic simulation. We propose Large Market Model (LMM), an order-level generative foundation model, for financial market simulation, akin to language modeling in the digital world. Our financial Market Simulation engine (MarS), powered by LMM, addresses the domain-specific need for realistic, interactive and controllable order generation. Key observations include LMM's strong scalability across data size and model complexity, and MarS's robust and practicable realism in controlled generation with market impact. We showcase MarS as a forecast tool, detection system, analysis platform, and agent training environment, thus demonstrating MarS's ``paradigm shift'' potential for a variety of financial applications. We release the code of MarS at https://github.com/microsoft/MarS/.

Model merging has emerged as an effective approach to combining multiple single-task models into a multitask model. This process typically involves computing a weighted average of the model parameters without additional training. Existing model-merging methods focus on improving average task accuracy. However, interference and conflicts between the objectives of different tasks can lead to trade-offs during the merging process. In real-world applications, a set of solutions with various trade-offs can be more informative, helping practitioners make decisions based on diverse preferences. In this paper, we introduce a novel and low-compute algorithm, Model Merging with Amortized Pareto Front (MAP). MAP efficiently identifies a Pareto set of scaling coefficients for merging multiple models, reflecting the trade-offs involved. It amortizes the substantial computational cost of evaluations needed to estimate the Pareto front by using quadratic approximation surrogate models derived from a preselected set of scaling coefficients. Experimental results on vision and natural language processing tasks demonstrate that MAP can accurately identify the Pareto front, providing practitioners with flexible solutions to balance competing task objectives. We also introduce Bayesian MAP for scenarios with a relatively low number of tasks and Nested MAP for situations with a high number of tasks, further reducing the computational cost of evaluation.

Multi-objective reinforcement learning (MORL) excels at handling rapidly changing preferences in tasks that involve multiple criteria, even for unseen preferences. However, previous dominating MORL methods typically generate a fixed policy set or preference-conditioned policy through multiple training iterations exclusively for sampled preference vectors, and cannot ensure the efficient discovery of the Pareto front. Furthermore, integrating preferences into the input of policy or value functions presents scalability challenges, in particular as the dimension of the state and preference space grow, which can complicate the learning process and hinder the algorithm's performance on more complex tasks. To address these issues, we propose a two-stage Pareto front discovery algorithm called Constrained MORL (C-MORL), which serves as a seamless bridge between constrained policy optimization and MORL. Concretely, a set of policies is trained in parallel in the initialization stage, with each optimized towards its individual preference over the multiple objectives. Then, to fill the remaining vacancies in the Pareto front, the constrained optimization steps are employed to maximize one objective while constraining the other objectives to exceed a predefined threshold. Empirically, compared to recent advancements in MORL methods, our algorithm achieves more consistent and superior performances in terms of hypervolume, expected utility, and sparsity on both discrete and continuous control tasks, especially with numerous objectives (up to nine objectives in our experiments).

People interact with the real-world largely dependent on visual signal, which are ubiquitous and illustrate detailed demonstrations. In this paper, we explore utilizing visual signals as a new interface for models to interact with the environment. Specifically, we choose videos as a representative visual signal. And by training autoregressive Transformers on video datasets in a self-supervised objective, we find that the model emerges a zero-shot capability to infer the semantics from a demonstration video, and imitate the semantics to an unseen scenario. This allows the models to perform unseen tasks by watching the demonstration video in an in-context manner, without further fine-tuning. To validate the imitation capacity, we design various evaluation metrics including both objective and subjective measures. The results show that our models can generate high-quality video clips that accurately align with the semantic guidance provided by the demonstration videos, and we also show that the imitation capacity follows the scaling law.

Recently, there is a growing interest in creating computer-aided design (CAD) models based on user intent, known as controllable CAD generation. Existing work offers limited controllability and needs separate models for different types of control, reducing efficiency and practicality. To achieve controllable generation across all CAD construction hierarchies, such as sketch-extrusion, extrusion, sketch, face, loop and curve, we propose FlexCAD, a unified model by fine-tuning large language models (LLMs). First, to enhance comprehension by LLMs, we represent a CAD model as a structured text by abstracting each hierarchy as a sequence of text tokens. Second, to address various controllable generation tasks in a unified model, we introduce a hierarchy-aware masking strategy. Specifically, during training, we mask a hierarchy-aware field in the CAD text with a mask token. This field, composed of a sequence of tokens, can be set flexibly to represent various hierarchies. Subsequently, we ask LLMs to predict this masked field. During inference, the user intent is converted into a CAD text with a mask token replacing the part the user wants to modify, which is then fed into FlexCAD to generate new CAD models. Comprehensive experiments on public dataset demonstrate the effectiveness of FlexCAD in both generation quality and controllability.

In the classical Reinforcement Learning from Human Feedback (RLHF) framework, Proximal Policy Optimization (PPO) is employed to learn from sparse, sentence-level rewards—a challenging scenario in traditional deep reinforcement learning. Despite the great successes of PPO in the alignment of state-of-the-art closed-source large language models (LLMs), its open-source implementation is still largely sub-optimal, as widely reported by numerous research studies. To address these issues, we introduce a framework that models RLHF problems as a Markov decision process (MDP), enabling the capture of fine-grained token-wise information. Furthermore, we provide theoretical insights that demonstrate the superiority of our MDP framework over the previous sentence-level bandit formulation. Under this framework, we introduce an algorithm, dubbed as Reinforced Token Optimization (RTO), which learns the token-wise reward function from preference data and performs policy optimization based on this learned token-wise reward signal. Theoretically, RTO is proven to have the capability of finding the near-optimal policy sample-efficiently. For its practical implementation, RTO innovatively integrates Direct Preference Optimization (DPO) and PPO. DPO, originally derived from sparse sentence rewards, surprisingly provides us with a token-wise characterization of response quality, which is seamlessly incorporated into our subsequent PPO training stage. We conduct extensive experiments to evaluate RTO against PPO and other direct preference learning algorithms. The results highlight the effectiveness of RTO, with the algorithm outperforming PPO by 7.5 points on the AlpacaEval 2 benchmark and by 4.1 points on Arena-Hard. Our code and models are available at https://github.com/zkshan2002/RTO.

Time-series Generation (TSG) is a prominent research area with broad applications in simulations, data augmentation, and counterfactual analysis. While existing methods have shown promise in unconditional single-domain TSG, real-world applications demand for cross-domain approaches capable of controlled generation tailored to domain-specific constraints and instance-level requirements. In this paper, we argue that text can provide semantic insights, domain information and instance-specific temporal patterns, to guide and improve TSG. We introduce “Text-Controlled TSG”, a task focused on generating realistic time series by incorporating textual descriptions. To address data scarcity in this setting, we propose a novel LLM-based Multi-Agent framework that synthesizes diverse, realistic text-to-TS datasets. Furthermore, we introduce Bridge, a hybrid text-controlled TSG framework that integrates semantic prototypes with text description for supporting domain-level guidance. This approach achieves state-of-the-art generation fidelity on 11 of 12 datasets, and improves controllability by up to 12% on MSE and 6% MAE compared to no text input generation, highlighting its potential for generating tailored time-series data.

Current approaches for training Process Reward Models (PRMs) often involve deconposing responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step’s length to a fixed size. These approaches overlook the fact that certain words don’t usually indicate true decision points. To address this, we propose AdaptiveStep, a method that divides reasoning steps based on the model’s confidence in predicting the next word, offering more information on decision-making at each step, improving downstream tasks like reward model training. Moreover, our method requires no manual annotation. Experiments with AdaptiveStep-trained PRMs in mathematical reasoning and code generation show that the outcome PRM achieves state-of-the-art Best-of-N performance, surpassing greedy search strategy with token-level value-guided decoding, while also reducing construction costs by over 30% compared to existing open-source PRMs. We also provide a thorough analysis and case study on its performance, transferability, and generalization capabilities. We provide our code on https://github.com/Lux0926/ASPRM.

Recent advancements in Retrieval-Augmented Generation (RAG) systems have significantly enhanced the capabilities of large language models (LLMs) by incorporating external knowledge retrieval. However, the sole reliance on retrieval is often inadequate for mining deep, domain-specific knowledge and for performing logical reasoning from specialized datasets. To tackle these challenges, we present an approach, which is designed to extract, comprehend, and utilize domain knowledge while constructing a coherent rationale. At the heart of our approach lie four pivotal components: a knowledge atomizer that extracts atomic questions from raw data, a query proposer that generates subsequent questions to facilitate the original inquiry, an atomic retriever that locates knowledge based on atomic knowledge alignments, and an atomic selector that determines which follow-up questions to pose guided by the retrieved information. Through this approach, we implement a knowledge-aware task decomposition strategy that adeptly extracts multifaceted knowledge from segmented data and iteratively builds the rationale in alignment with the initial query and the acquired knowledge. We conduct comprehensive experiments to demonstrate the efficacy of our approach across various benchmarks, particularly those requiring multihop reasoning steps. The results indicate a significant enhancement in performance, up to 12.6% over the second-best method, underscoring the potential of the approach in complex, knowledge-intensive applications.

Creating Computer-Aided Design (CAD) models requires significant expertise and effort. Text-to-CAD, which converts textual descriptions into CAD parametric sequences, is crucial in streamlining this process. Recent studies have utilized ground-truth parametric sequences, known as sequential signals, as supervision to achieve this goal. However, CAD models are inherently multimodal, comprising parametric sequences and corresponding rendered visual objects. Besides, the rendering process from parametric sequences to visual objects is many-to-one. Therefore, both sequential and visual signals are critical for effective training. In this work, we introduce CADFusion, a framework that uses Large Language Models (LLMs) as the backbone and alternates between two training stages: the sequential learning (SL) stage and the visual feedback (VF) stage. In the SL stage, we train LLMs using ground-truth parametric sequences, enabling the generation of logically coherent parametric sequences. In the VF stage, we reward parametric sequences that render into visually preferred objects and penalize those that do not, allowing LLMs to learn how rendered visual objects are perceived and evaluated. These two stages alternate throughout the training, ensuring balanced learning and preserving benefits of both signals. Experiments demonstrate that CADFusion significantly improves performance, both qualitatively and quantitatively.

Computer Aided Design (CAD) is indispensable across various industries. Text-based CAD editing, which automates the modification of CAD models based on textual instructions, holds great potential but remains underexplored. Existing methods primarily focus on design variation generation or text-based CAD generation, either lacking support for text-based control or neglecting existing CAD models as constraints. We introduce CAD-Editor, the first framework for text-based CAD editing. To address the challenge of demanding triplet data with accurate correspondence for training, we propose an automated data synthesis pipeline. This pipeline utilizes design variation models to generate pairs of original and edited CAD models and employs Large Vision-Language Models (LVLMs) to summarize their differences into editing instructions. To tackle the composite nature of text-based CAD editing, we propose a locate-then-infill framework that decomposes the task into two focused sub-tasks: locating regions requiring modification and infilling these regions with appropriate edits. Large Language Models (LLMs) serve as the backbone for both sub-tasks, leveraging their capabilities in natural language understanding and CAD knowledge. Experiments show that CAD-Editor achieves superior performance both quantitatively and qualitatively.

While direct policy optimization methods exist, pioneering LLMs are fine-tuned with reinforcement learning from human feedback (RLHF) to generate better responses under the supervision of a reward model learned from preference data. One major challenge of RLHF is the inaccuracy of the intermediate reward model, especially in the tasks that requires complex reasoning for the reward model to score a response. We find that the reliability of the reward model varies across responses assigned with different rewards. This motivates us to filter the samples whose rewards may be unreliable to improve the signal-to-noise ratio during policy learning, resulting in Policy Filtration for Proximal Policy Optimization (PF-PPO). To choose a proper policy filtering strategy, we use the coefficient of determination ($R^2$) between the rewards and actual scores on filtered samples as the metrics to help us find promising strategies since it measures how well the rewards filtered by PF-PPO indicate real performance. We provide extensive experiments to validate the effectiveness of PF-PPO in code generation and math reasoning tasks. In code generation, PF-PPO achieves the state-of-the-art performance of 7-billion-parameter models on HumanEval (+7.9%), MBPP (+0.7%), and LeetCode Contest (+10.0%) which is a more challenging benchmark created by us. In math reasoning, PF-PPO yields performance increase using different reward models and benchmarks (Ape210K and CMATH).

Recently, incorporating knowledge from pretrained language models (PLMs) into decision transformers (DTs) has generated significant attention in offline reinforcement learning (RL). These PLMs perform well in RL tasks, raising an intriguing question: what kind of knowledge from PLMs has been transferred to RL to achieve such good results? This work first dives into this problem by analyzing each head quantitatively and points out Markov head, a crucial component that exists in the attention heads of PLMs. It leads to extreme attention on the last-input token and performs well only in short-term environments. Furthermore, we prove that this extreme attention cannot be changed by re-training embedding layer or fine-tuning. Inspired by our analysis, we propose a general method GPT-DTMA, which equips a pretrained DT with Mixture of Attention (MoA), to enable adaptive learning and accommodate diverse attention requirements during fine-tuning. Extensive experiments demonstrate the effectiveness of GPT-DTMA: it achieves superior performance in short-term environments compared to baselines, significantly reduces the performance gap of PLMs in long-term scenarios, and the experimental results also validate our theorems.

Symbolic music generation aims to create musical notes, which can help users compose music, such as generating target instrument tracks based on provided source tracks. In practical scenarios where there’s a predefined ensemble of tracks and various composition needs, an efficient and effective generative model that can generate any target tracks based on the other tracks becomes crucial. However, previous efforts have fallen short in addressing this necessity due to limitations in their music representations and models. In this paper, we introduce a framework known as GETMusic, with ``GET'' standing for ``GEnerate music Tracks.'' This framework encompasses a novel music representation ``GETScore'' and a diffusion model ``GETDiff.'' GETScore represents musical notes as tokens and organizes tokens in a 2D structure, with tracks stacked vertically and progressing horizontally over time. At a training step, each track of a music piece is randomly selected as either the target or source. The training involves two processes: In the forward process, target tracks are corrupted by masking their tokens, while source tracks remain as the ground truth; in the denoising process, GETDiff is trained to predict the masked target tokens conditioning on the source tracks. Our proposed representation, coupled with the non-autoregressive generative model, empowers GETMusic to generate music with any arbitrary source-target track combinations.Our experiments demonstrate that the versatile GETMusic outperforms prior works proposed for certain specific composition tasks.

Due to the non-stationarity of time series, the distribution shift problem largely hinders the performance of time series forecasting. Existing solutions either rely on using certain statistics to specify the shift, or developing specific mechanisms for certain network architectures. However, the former would fail for the unknown shift beyond simple statistics, while the latter has limited compatibility on different forecasting models. To overcome these problems, we first propose a decoupled formulation for time series forecasting, with no reliance on fixed statistics and no restriction on forecasting architectures. This formulation regards the removing-shift procedure as a special transformation between a raw distribution and a desired target distribution and separates it from the forecasting. Such a formulation is further formalized into a bi-level optimization problem, to enable the joint learning of the transformation (outer loop) and forecasting (inner loop). Moreover, the special requirements of expressiveness and bi-direction for the transformation motivate us to propose instance normalization flow (IN-Flow), a novel invertible network for time series transformation. Different from the classic ''normalizing flow'' models, IN-Flow does not aim for normalizing input to the prior distribution (e.g., Gaussian distribution) for generation, but creatively transforms time series distribution by stacking normalization layers and flow-based invertible networks, which is thus named ''normalization'' flow. Finally, we have conducted extensive experiments on both synthetic data and real-world data, which demonstrate the superiority of our method.

Synthetic Electronic Health Record (EHR) time-series generation is crucial for advancing clinical machine learning models, as it helps address data scarcity by providing more training data. However, most existing approaches focus primarily on replicating statistical distributions and temporal dependencies of real-world data. We argue that fidelity to observed data alone does not guarantee better model performance, as common patterns may dominate, limiting the representation of rare but important conditions. This highlights the need for generate synthetic samples to improve performance of specific clinical models to fulfill their target outcomes. To address this, we propose TarDiff, a novel target-oriented diffusion framework that integrates task-specific influence guidance into the synthetic data generation process. Unlike conventional approaches that mimic training data distributions, TarDiff optimizes synthetic samples by quantifying their expected contribution to improving downstream model performance through influence functions. Specifically, we measure the reduction in task-specific loss induced by synthetic samples and embed this influence gradient into the reverse diffusion process, thereby steering the generation towards utility-optimized data. Evaluated on six publicly available EHR datasets, TarDiff achieves state-of-the-art performance, outperforming existing methods by up to 20.4% in AUPRC and 18.4% in AUROC. Our results demonstrate that TarDiff not only preserves temporal fidelity but also enhances downstream model performance, offering a robust solution to data scarcity and class imbalance in healthcare analytics.

As one of the most successful generative models, diffusion models have demonstrated remarkable efficacy in synthesizing high-quality images. These models learn the underlying high-dimensional data distribution in an unsupervised manner. Despite their success, diffusion models are highly data-driven and prone to inheriting the imbalances and biases present in real-world data. Some studies have attempted to address these issues by designing text prompts for known biases or using bias labels to construct unbiased data. While these methods have shown improved results, real-world scenarios often contain various unknown biases, and obtaining bias labels is particularly challenging. In this paper, we emphasize the necessity of mitigating bias in pre-trained diffusion models without relying on auxiliary bias annotations. To tackle this problem, we propose a framework, InvDiff, which aims to learn invariant semantic information for diffusion guidance. Specifically, we propose identifying underlying biases in the training data and designing a novel debiasing training objective. Then, we employ a lightweight trainable module that automatically preserves invariant semantic information and uses it to guide the diffusion model's sampling process toward unbiased outcomes simultaneously. Notably, we only need to learn a small number of parameters in the lightweight learnable module without altering the pre-trained diffusion model. Furthermore, we provide a theoretical guarantee that the implementation of InvDiff is equivalent to reducing the error upper bound of generalization. Extensive experimental results on three publicly available benchmarks demonstrate that InvDiff effectively reduces biases while maintaining the quality of image generation. Our code is available at https://github.com/Hundredl/InvDiff.

Recent advances in text-guided video editing have showcased promising results in appearance editing (e.g., stylization). However, video motion editing in the temporal dimension (e.g., from eating to waving), which distinguishes video editing from image editing, is underexplored. In this work, we present UniEdit, a tuning-free framework that supports both video motion and appearance editing by harnessing the power of a pre-trained text-to-video generator within an inversion-then-generation framework. To realize motion editing while preserving source video content, based on the insights that temporal and spatial self-attention layers encode inter-frame and intra-frame dependency, we introduce auxiliary motion-reference and reconstruction branches to produce text-guided motion and source features respectively. The obtained features are then injected into the main editing path via temporal and spatial self-attention layers. We also validate the effectiveness and flexibility of UniEdit by deploying it on three T2V generative models with different architectures. Experiments demonstrate that UniEdit covers video motion editing and various appearance editing scenarios, and surpasses the state-of-the-art methods. Our code is publicly available.

Zijian Li, Qingyan Guo, Jiawei Shao, Lei Song, Jiang Bian, Jun Zhang, Rui Wang. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Tensor decomposition is a fundamental tool for analyzing multi-dimensional data by learning low-rank factors to represent high-order interactions. While recent works on temporal tensor decomposition have made significant progress by incorporating continuous timestamps in latent factors, they still struggle with general tensor data with continuous indexes not only in the temporal mode but also in other modes, such as spatial coordinates in climate data. Moreover, the challenge of self-adapting model complexity is largely unexplored in functional temporal tensor models, with existing methods being inapplicable in this setting. To address these limitations, we propose functional Complexity-Adaptive Temporal Tensor dEcomposition (Catte). Our approach encodes continuous spatial indexes as learnable Fourier features and employs neural ODEs in latent space to learn the temporal trajectories of factors. To enable automatic adaptation of model complexity, we introduce a sparsity-inducing prior over the factor trajectories. We develop an efficient variational inference scheme with an analytical evidence lower bound, enabling sampling-free optimization. Through extensive experiments on both synthetic and real-world datasets, we demonstrate that Catte not only reveals the underlying ranks of functional temporal tensors but also significantly outperforms existing methods in prediction performance and robustness against noise.

Modeling and reconstructing multidimensional physical dynamics from sparse and off-grid observations presents a fundamental challenge in scientific research. Recently, diffusion-based generative modeling shows promising potential for physical simulation. However, current approaches typically operate on on-grid data with preset spatiotemporal resolution, but struggle with the sparsely observed and continuous nature of real-world physical dynamics. To fill the gaps, we present SDIFT, Sequential DIffusion in Functional Tucker space, a novel framework that generates full-field evolution of physical dynamics from irregular sparse observations. SDIFT leverages the functional Tucker model as the latent space representer with proven universal approximation property, and represents sparse observations as latent functions and Tucker core sequences. We then construct a sequential diffusion model with temporally augmented UNet in the functional Tucker space, denoising noise drawn from a Gaussian process to generate the sequence of core tensors. At the posterior sampling stage, we propose a Message-Passing Posterior Sampling mechanism, enabling conditional generation of the entire sequence guided by observations at limited time steps. We validate SDIFT on three physical systems spanning astronomical (supernova explosions, light-year scale), environmental (ocean sound speed fields, kilometer scale), and molecular (organic liquid, millimeter scale) domains, demonstrating significant improvements in both reconstruction accuracy and computational efficiency compared to state-of-the-art approaches.

A unified foundation model for medical time series—pretrained on open access and ethically reviewed medical corpora—offers the potential to reduce annotation burdens, minimize model customization, and enable robust transfer across clinical institutions, modalities, and tasks, particularly in data-scarce or privacy-constrained environments. However, existing time series foundation models struggle to handle medical time series data due to its inherent challenges, including irregular intervals, heterogeneous sampling rates, and frequent missingness. To address these challenges, we introduce MIRA, a unified foundation model specifically designed for medical time series forecasting. MIRA incorporates a Continuous-Time Rotary Positional Encoding that enables fine-grained modeling of variable time intervals, a frequency-specific mixture-of-experts layer that routes computation across latent frequency regimes to further promote temporal specialization, and a Continuous Dynamics Extrapolation Block based on Neural ODE that models the continuous trajectory of latent states, enabling accurate forecasting at arbitrary target timestamps. Pretrained on a large-scale and diverse medical corpus comprising over 454 billion time points collect from publicly available datasets, MIRA achieving reductions in forecasting errors by an average of 8% and 6% in out-of-distribution and in-distribution scenarios, respectively. We also introduce a comprehensive benchmark spanning multiple downstream clinical tasks, establishing a foundation for future research in medical time series modeling.

Financial markets pose fundamental challenges for asset return prediction due to their high dimensionality, non-stationarity, and persistent volatility. Despite advances in large language models and multi-agent systems, current quantitative research pipelines suffer from limited automation, weak interpretability, and fragmented coordination across key components such as factor mining and model innovation. In this paper, we propose R&D-Agent for Quantitative Finance, in short R&D-Agent(Q), the first data-centric multi-agent framework designed to automate the full-stack research and development of quantitative strategies via coordinated factor-model co-optimization. R&D-Agent(Q) decomposes the quant process into two iterative stages: a Research stage that dynamically sets goal-aligned prompts, formulates hypotheses based on domain priors, and maps them to concrete tasks, and a Development stage that employs a code-generation agent, Co-STEER, to implement task-specific code, which is then executed in real-market backtests. The two stages are connected through a feedback stage that thoroughly evaluates experimental outcomes and informs subsequent iterations, with a multi-armed bandit scheduler for adaptive direction selection. Empirically, R&D-Agent(Q) achieves up to 2× higher annualized returns than classical factor libraries using 70% fewer factors, and outperforms state-of-the-art deep time-series models on real markets. Its joint factor–model optimization delivers a strong balance between predictive accuracy and strategy robustness. Our code is available at: https://github.com/microsoft/RD-Agent.

A Computer-Aided Design (CAD) model encodes an object in two coupled forms: a \emph{parametric construction sequence} and its resulting \emph{visible geometric shape}. During iterative design, adjustments to the geometric shape inevitably require synchronized edits to the underlying parametric sequence, called \emph{geometry-driven parametric CAD editing}. The task calls for 1) preserving the original sequence’s structure, 2) ensuring each edit's semantic validity, and 3) maintaining high shape fidelity to the target shape, all under scarce editing data triplets. We present \emph{CADMorph}, an iterative \emph{plan–generate–verify} framework that orchestrates pretrained domain-specific foundation models during inference: a \emph{parameter-to-shape} (P2S) latent diffusion model and a \emph{masked-parameter-prediction} (MPP) model. In the planning stage, cross-attention maps from the P2S model pinpoint the segments that need modification and offer editing masks. The MPP model then infills these masks with semantically valid edits in the generation stage. During verification, the P2S model embeds each candidate sequence in shape-latent space, measures its distance to the target shape, and selects the closest one. The three stages leverage the inherent geometric consciousness and design knowledge in pretrained priors, and thus tackle structure preservation, semantic validity, and shape fidelity respectively. Besides, both P2S and MPP models are trained without triplet data, bypassing the data-scarcity bottleneck. CADMorph surpasses GPT-4o and specialized CAD baselines, and supports downstream applications such as iterative editing and reverse-engineering enhancement.

Group Relative Policy Optimization (GRPO) fine-tuning has demonstrated significant enhancements in reasoning tasks. However, it often relies on high quality labeled dataset, which is typically difficult to obtain. To address this challenge, we introduce \textbf{N}oise-\textbf{A}ware \textbf{D}ual-\textbf{R}eward \textbf{O}ptimization (\textbf{NaDRO}) to effectively enhances the training of Large Language Models (LLMs) under noisy or ambiguous supervision. NaDRO operates through two key components: \textbf{(1) Preference-based Outcome Reward (POR)},which makes a principled bias-variance tradeoff, reducing training variance by learning from robust preference rankings instead of overfitting to single-best estimates; and \textbf{(2) Context Perception Reward (CPR) mechanism}, which ensures that LLMs conduct necessary qualitative assessment of the current problem state to foster deeper situational understanding prior to decision-making. To validate our approach in a realistic decision-making testbed, we model classic combinatorial optimization problems like the Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) as Markov Decision Processes, generating training data via cost-limited exploration. Our results demonstrate that the fine-tuned Qwen 7B and Llama 3.1-8B models achieve statistically robust performance, significantly outperforming leading LLM baselines and standard fine-tuning methods on these complex benchmarks. Code is released at \url{https://github.com/microsoft/HeurAgenix/tree/NaDRO}.

World models aim to capture the dynamics of the environment, enabling agents to predict and plan for future states. In most scenarios of interest, the dynamics are highly centered on interactions among objects within the environment. This motivates the development of world models that operate on object-centric rather than monolithic representations, with the goal of more effectively capturing environment dynamics and enhancing compositional generalization. However, the development of object-centric world models has largely been explored in environments with limited visual complexity (such as basic geometries). It remains underexplored whether such models can be effective in more challenging settings. In this paper, we fill this gap by introducing Dyn-O, an enhanced structured world model built upon object-centric representations. Compared to prior work in object-centric representations, Dyn-O improves in both learning representations and modeling dynamics. On the challenging Procgen games, we demonstrate that our method can learn object-centric world models directly from pixel observations, outperforming DreamerV3 in rollout prediction accuracy. Furthermore, by decoupling object centric features into dynamic-agnostic and dynamic-aware components, we enable finer-grained manipulation of these features and generate more diverse imagined trajectories. The code of Dyn-O can be found at: https://github.com/wangzizhao/dyn-O.

Latent action models (LAMs) aim to learn action-relevant changes from unlabeled videos by compressing changes between frames as latents. However, differences between video frames can be caused by \textit{controllable changes} as well as exogenous noise, leading to an important concern -- do latents capture the changes caused by actions or irrelevant noise? This paper studies this issue analytically, presenting a linear model that encapsulates the essence of LAM learning, while being tractable. This provides several insights, including connections between LAM and principal component analysis (PCA), desiderata of the data-generating policy, and justification of strategies to encourage learning controllable changes using data augmentation, data cleaning, and auxiliary action-prediction. We also provide illustrative results based on numerical simulation, shedding light on the specific structure of observations, actions, and noise in data that influence LAM learning.

Time series forecasting plays a crucial role in data mining, driving rapid advancements across numerous industries. With the emergence of large models, time series foundation models (TSFMs) have exhibited remarkable generalization capabilities, such as zero-shot learning, through large-scale pre-training. Meanwhile, Retrieval-Augmented Generation (RAG) methods have been widely employed to enhance the performance of foundation models on unseen data, allowing models to access to external knowledge. In this paper, we introduceTimeRAF, aRetrieval-AugmentedForecasting model that enhance zero-shot time series forecasting through retrieval-augmented techniques. We develop customized time series knowledge bases that are tailored to the specific forecasting tasks. TimeRAF employs an end-to-end learnable retriever to extract valuable information from the knowledge base. Additionally, we propose Channel Prompting for knowledge integration, which effectively extracts relevant information from the retrieved knowledge along the channel dimension. Extensive experiments demonstrate the effectiveness of our model, showing significant improvement across various domains and datasets.

Machine learning methods for conditional data generation usually build a mapping from source conditional data X to target data Y. The target Y (e.g., text, speech, music, image, video) is usually high-dimensional and complex, and contains information that does not exist in source data, which hinders effective and efficient learning on the source-target mapping. In this paper, we present a learning paradigm called regeneration learning for data generation, which first generates Y' (an abstraction/representation of Y) from X and then generates Y from Y'. During training, Y' is obtained from Y through either handcrafted rules or self-supervised learning and is used to learn X-->Y' and Y'-->Y. Regeneration learning extends the concept of representation learning to data generation tasks, and can be regarded as a counterpart of traditional representation learning, since 1) regeneration learning handles the abstraction (Y') of the target data Y for data generation while traditional representation learning handles the abstraction (X') of source data X for data understanding; 2) both the processes of Y'-->Y in regeneration learning and X-->X' in representation learning can be learned in a self-supervised way (e.g., pre-training); 3) both the mappings from X to Y' in regeneration learning and from X' to Y in representation learning are simpler than the direct mapping from X to Y. We show that regeneration learning can be a widely-used paradigm for data generation (e.g., text generation, speech recognition, speech synthesis, music composition, image generation, and video generation) and can provide valuable insights into developing data generation methods.

Yunseon Choi, Sangmin Bae, Seonghyun Ban, Minchan Jeong, Chuheng Zhang, Lei Song, Li Zhao, Jiang Bian, Kee-Eung Kim. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency. Compared to single agent RL, the sample efficiency for Multi-Agent Reinforcement Learning (MARL) is more challenging because of its inherent partial observability, non-stationary training, and enormous strategy space. Although much effort has been devoted to developing new methods and enhancing sample efficiency, we look at the widely used episodic training mechanism. In each training step, tens of frames are collected, but only one gradient step is made. We argue that this episodic training could be a source of poor sample efficiency. To better exploit the data already collected, we propose to increase the frequency of the gradient updates per environment interaction (a.k.a. Replay Ratio or Update-To-Data ratio). To show its generality, we evaluate 3 MARL methods on 6 SMAC tasks. The empirical results validate that a higher replay ratio significantly improves the sample efficiency for MARL algorithms. The codes to reimplement the results presented in this paper are open-sourced at https://github.com/egg-west/rr_for_MARL.

Recently, diffusion probabilistic models have attracted attention in generative time series forecasting due to their remarkable capacity to generate high-fidelity samples. However, the effective utilization of their strong modeling ability in the probabilistic time series forecasting task remains an open question, partially due to the challenge of instability arising from their stochastic nature. To address this challenge, we introduce a novel Multi-Granularity Time Series Diffusion (MG-TSD) model, which achieves state-of-the-art predictive performance by leveraging the inherent granularity levels within the data as given targets at intermediate diffusion steps to guide the learning process of diffusion models. The way to construct the targets is motivated by the observation that forward process of the diffusion model, which sequentially corrupts the data distribution to a standard normal distribution, intuitively aligns with the process of smoothing fine-grained data into a coarse-grained representation, both of which result in a gradual loss of fine distribution features. In the study, we derive a novel multi-granularity guidance diffusion loss function and propose a concise implementation method to effectively utilize coarse-grained data across various granularity levels. More importantly, our approach does not rely on additional external data, making it versatile and applicable across various domains. Extensive experiments conducted on real-world datasets demonstrate that our MG-TSD model outperforms existing time series prediction methods.

Large Language Models (LLMs) excel in various tasks, but they rely on carefully crafted prompts that often demand substantial human effort. To automate this process, in this paper, we propose a novel framework for discrete prompt optimization, called EvoPrompt, which borrows the idea of evolutionary algorithms (EAs) as they exhibit good performance and fast convergence. To enable EAs to work on discrete prompts, which are natural language expressions that need to be coherent and human-readable, we connect LLMs with EAs. This approach allows us to simultaneously leverage the powerful language processing capabilities of LLMs and the efficient optimization performance of EAs. Specifically, abstaining from any gradients or parameters, EvoPrompt starts from a population of prompts and iteratively generates new prompts with LLMs based on the evolutionary operators, improving the population based on the development set. We optimize prompts for both closed- and open-source LLMs including GPT-3.5 and Alpaca, on 31 datasets covering language understanding, generation tasks, as well as BIG-Bench Hard (BBH) tasks. EvoPrompt significantly outperforms human-engineered prompts and existing methods for automatic prompt generation (e.g., up to 25% on BBH). Furthermore, EvoPrompt demonstrates that connecting LLMs with EAs creates synergies, which could inspire further research on the combination of LLMs and conventional algorithms.

Zero-shot talking avatar generation aims at synthesizing natural talking videos from speech and a single portrait image. Previous methods have relied on domain-specific heuristics such as warping-based motion representation and 3D Morphable Models, which limit the naturalness and diversity of the generated avatars. In this work, we introduce GAIA (Generative AI for Avatar), which eliminates the domain priors in talking avatar generation. In light of the observation that the speech only drives the motion of the avatar while the appearance of the avatar and the background typically remain the same throughout the entire video, we divide our approach into two stages: 1) disentangling each frame into motion and appearance representations; 2) generating motion sequences conditioned on the speech and reference portrait image. We collect a large-scale high-quality talking avatar dataset and train the model on it with different scales (up to 2B parameters). Experimental results verify the superiority, scalability, and flexibility of GAIA as 1) the resulting model beats previous baseline models in terms of naturalness, diversity, lip-sync quality, and visual quality; 2) the framework is scalable since larger models yield better results; 3) it is general and enables different applications like controllable talking avatar generation and text-instructed avatar generation.

Speech conveys more information than text, as the same word can be uttered in various voices to convey diverse information. Compared to traditional text-to-speech (TTS) methods relying on speech prompts (reference speech) for voice variability, using text prompts (descriptions) is more user-friendly since speech prompts can be hard to find or may not exist at all. TTS approaches based on the text prompt face two main challenges: 1) the one-to-many problem, where not all details about voice variability can be described in the text prompt, and 2) the limited availability of text prompt datasets, where vendors and large cost of data labeling are required to write text prompts for speech. In this work, we introduce PromptTTS 2 to address these challenges with a variation network to provide variability information of voice not captured by text prompts, and a prompt generation pipeline to utilize the large language models (LLM) to compose high quality text prompts. Specifically, the variation network predicts the representation extracted from the reference speech (which contains full information about voice variability) based on the text prompt representation. For the prompt generation pipeline, it generates text prompts for speech with a speech language understanding model to recognize voice attributes (e.g., gender, speed) from speech and a large language model to formulate text prompts based on the recognition results. Experiments on a large-scale (44K hours) speech dataset demonstrate that compared to the previous works, PromptTTS 2 generates voices more consistent with text prompts and supports the sampling of diverse voice variability, thereby offering users more choices on voice generation. Additionally, the prompt generation pipeline produces high-quality text prompts, eliminating the large labeling cost. The demo page of PromptTTS 2 is available (https://speechresearch.github.io/prompttts2).

Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is important to capture the diversity in human speech such as speaker identities, prosodies, and styles (e.g., singing). Current large TTS systems usually quantize speech into discrete tokens and use language models to generate these tokens one by one, which suffer from unstable prosody, word skipping/repeating issue, and poor voice quality. In this paper, we develop NaturalSpeech 2, a TTS system that leverages a neural audio codec with residual vector quantizers to get the quantized latent vectors and uses a diffusion model to generate these latent vectors conditioned on text input. To enhance the zero-shot capability that is important to achieve diverse speech synthesis, we design a speech prompting mechanism to facilitate in-context learning in the diffusion model and the duration/pitch predictor. We scale NaturalSpeech 2 to large-scale datasets with 44K hours of speech and singing data and evaluate its voice quality on unseen speakers. NaturalSpeech 2 outperforms previous TTS systems by a large margin in terms of prosody/timbre similarity, robustness, and voice quality in a zero-shot setting, and performs novel zero-shot singing synthesis with only a speech prompt. Audio samples are available at https://naturalspeech2.github.io/.

Battery degradation remains a pivotal concern in the energy storage domain, with machine learning emerging as a potent tool to drive forward insights and solutions. However, this intersection of electrochemical science and machine learning poses complex challenges. Machine learning experts often grapple with the intricacies of battery science, while battery researchers face hurdles in adapting intricate models tailored to specific datasets. Beyond this, a cohesive standard for battery degradation modeling, inclusive of data formats and evaluative benchmarks, is conspicuously absent. Recognizing these impediments, we present BatteryML—a one-step, all-encompass, and open-source platform designed to unify data preprocessing, feature extraction, and the implementation of both traditional and state-of-the-art models. This streamlined approach promises to enhance the practicality and efficiency of research applications. BatteryML seeks to fill this void, fostering an environment where experts from diverse specializations can collaboratively contribute, thus elevating the collective understanding and advancement of battery research.

Whittle index is a heuristic tool that leads to good performance for the restless bandits problem. In this paper, we extend Whittle index to a new multi-agent reinforcement learning (MARL) setting with multiple discrete actions and a possibly changing constraint on the state space, resulting in WIMS (Whittle Index with Multiple actions and State constraint). This setting is common for inventory management where each agent chooses a replenishing quantity level for the corresponding stock-keeping-unit (SKU) such that the total profit is maximized while the total inventory does not exceed a certain limit. Accordingly, we propose a deep MARL algorithm based on WIMS for inventory management. Empirically, our algorithm is evaluated on real large-scale inventory management problems with up to 2307 SKUs and outperforms operation-research-based methods and baseline MARL algorithms.

While recent large-scale text-to-speech (TTS) models have achieved significant progress, they still fall shorts in speech quality, similarity, and prosody. Considering that speech intricately encompasses various attributes (e.g., content, prosody, timbre, and acoustic details) that pose significant challenges for generation, a natural idea is to factorize speech into individual subspaces representing different attributes and generate them individually. Motivated by it, we propose a TTS system with novel factorized diffusion models to generate natural speech in a zero-shot way. Specifically, 1) we design a neural codec with factorized vector quantization (FVQ) to disentangle speech waveform into subspaces of content, prosody, timbre, and acoustic details; 2) we propose a factorized diffusion model, which generates attributes in each subspace following its corresponding prompt. With this factorization design, our method can effectively and efficiently model the intricate speech with disentangled subspaces in a divide-and-conquer way. Experimental results show that our method outperforms the state-of-the-art TTS systems on quality, similarity, prosody, and intelligibility.

Recent advancements in solving large-scale traveling salesman problems (TSP) utilize the heatmap-guided Monte Carlo tree search (MCTS) paradigm, where machine learning (ML) models generate heatmaps, indicating the probability distribution of each edge being part of the optimal solution, to guide MCTS in solution finding. However, our theoretical and experimental analysis raises doubts about the effectiveness of ML-based heatmap generation. In support of this, we demonstrate that a simple baseline method can outperform complex ML approaches in heatmap generation. Furthermore, we question the practical value of the heatmap-guided MCTS paradigm. To substantiate this, our findings show its inferiority to the LKH-3 heuristic despite the paradigm’s reliance on problem-specific, hand-crafted strategies. For the future, we suggest research directions focused on developing more theoretically sound heatmap generation methods and exploring autonomous, generalizable ML approaches for combinatorial problems. The code is available for review: https://github.com/xyfffff/rethink_mcts_for_tsp.

Audio generation is a major branch of generative AI research. Compared with prior works in this area that are commonly task-specific with heavy domain knowledge, this paper advocates building universal audio generation models that can handle various tasks in a unified manner. As recent research on large language models (LLMs) has demonstrated their strong ability to handle multiple tasks, this work presents UniAudio, an LLM-based audio generation model that supports a wide range of audio generation tasks. Based on various input conditions, such as phoneme, text description, or audio itself, UniAudio can generate speech, sound, music, and singing voice. The proposed UniAudio is built with 100k hours of multi-source open-available audio data and is scaled to 1B parameters. The audio tokenization method and language model architecture are also specifically designed for both performance and efficiency. Experimentally, UniAuido supports 11 audio generation tasks and achieves competitive results on all tasks consistently. We also show that UniAudio can support new tasks seamlessly via simple fine-tuning.

Tabular data is foundational to predictive modeling in various crucial industries, including healthcare, finance, retail, sustainability, etc. Despite the progress made in specialized models, there is an increasing demand for universal models that can transfer knowledge, generalize from limited data, and follow human instructions. These are challenges that current tabular deep learning approaches have not fully tackled. Here we introduce Generative Tabular Learning (GTL), a novel framework that integrates the advanced functionalities of large language models (LLMs)-such as prompt-based zero-shot generalization and in-context learning-into tabular deep learning. GTL capitalizes on the pre-training of LLMs on diverse tabular data, enhancing their understanding of domain-specific knowledge, numerical sequences, and statistical dependencies critical for accurate predictions. Our empirical study spans 384 public datasets, rigorously analyzing GTL's convergence and scaling behaviors and assessing the impact of varied data templates. The GTL-enhanced LLaMA-2 model demonstrates superior zero-shot and in-context learning capabilities across numerous classification and regression tasks. Notably, it achieves this without fine-tuning, outperforming traditional methods and rivaling state-of-the-art models like GPT-4 in certain cases. Through GTL, we not only foster a deeper integration of LLMs' sophisticated abilities into tabular data comprehension and application but also offer a new training resource and a test bed for LLMs to enhance their ability to comprehend tabular data. To facilitate reproducible research, we release our code, data, and model checkpoints at https://github.com/microsoft/Industrial-Foundation-Models.

Zhujin Gao, Junliang Guo, Xu Tan, Yongxin Zhu, Fang Zhang, Jiang Bian, Linli Xu. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

The advent of large language models (LLMs) has revolutionized the field of natural language processing, yet they might be attacked to produce harmful content. Despite efforts to ethically align LLMs, these are often fragile and can be circumvented by jailbreaking attacks through optimized or manual adversarial prompts. To address this, we introduce the Information Bottleneck Protector (IBProtector), a defense mechanism grounded in the information bottleneck principle, and we modify the objective to avoid trivial solutions. The IBProtector selectively compresses and perturbs prompts, facilitated by a lightweight and trainable extractor, preserving only essential information for the target LLMs to respond with the expected answer. Moreover, we further consider a situation where the gradient is not visible to be compatible with any LLM. Our empirical evaluations show that IBProtector outperforms current defense methods in mitigating jailbreak attempts, without overly affecting response quality or inference speed. Its effectiveness and adaptability across various attack methods and target LLMs underscore the potential of IBProtector as a novel, transferable defense that bolsters the security of LLMs without requiring modifications to the underlying models.

Data-driven decision-making processes increasingly utilize end-to-end learnable deep neural networks to render final decisions. Sometimes, the output of the forward functions in certain layers is determined by the solutions to mathematical optimization problems, leading to the emergence of differentiable optimization layers that permit gradient back-propagation. However, real-world scenarios often involve large-scale datasets and numerous constraints, presenting significant challenges. Current methods for differentiating optimization problems typically rely on implicit differentiation, which necessitates costly computations on the Jacobian matrices, resulting in low efficiency. In this paper, we introduce BPQP, a differentiable convex optimization framework designed for efficient end-to-end learning. To enhance efficiency, we reformulate the backward pass as a simplified and decoupled quadratic programming problem by leveraging the structural properties of the Karush–Kuhn–Tucker (KKT) matrix. This reformulation enables the use of first-order optimization algorithms in calculating the backward pass gradients, allowing our framework to potentially utilize any state-of-the-art solver. As solver technologies evolve, BPQP can continuously adapt and improve its efficiency. Extensive experiments on both simulated and real-world datasets demonstrate that BPQP achieves a significant improvement in efficiency—typically an order of magnitude faster in overall execution time compared to other differentiable optimization layers. Our results not only highlight the efficiency gains of BPQP but also underscore its superiority over differential optimization layer baselines.

Delivering precise point and distributional forecasts across a spectrum of prediction horizons represents a significant and enduring challenge in the application of time-series forecasting within various industries.Prior research on developing deep learning models for time-series forecasting has often concentrated on isolated aspects, such as long-term point forecasting or short-term probabilistic estimations. This narrow focus may result in skewed methodological choices and hinder the adaptability of these models to uncharted scenarios.While there is a rising trend in developing universal forecasting models, a thorough understanding of their advantages and drawbacks, especially regarding essential forecasting needs like point and distributional forecasts across short and long horizons, is still lacking.In this paper, we present ProbTS, a benchmark tool designed as a unified platform to evaluate these fundamental forecasting needs and to conduct a rigorous comparative analysis of numerous cutting-edge studies from recent years.We dissect the distinctive data characteristics arising from disparate forecasting requirements and elucidate how these characteristics can skew methodological preferences in typical research trajectories, which often fail to fully accommodate essential forecasting needs.Building on this, we examine the latest models for universal time-series forecasting and discover that our analyses of methodological strengths and weaknesses are also applicable to these universal models.Finally, we outline the limitations inherent in current research and underscore several avenues for future exploration.

Numerous industrial sectors necessitate models capable of providing robust forecasts across various horizons. Despite the recent strides in crafting specific architectures for time-series forecasting and developing pre-trained universal models, a comprehensive examination of their capability in accommodating varied-horizon forecasting during inference is still lacking. This paper bridges this gap through the design and evaluation of the Elastic Time-Series Transformer (ElasTST). The ElasTST model incorporates a non-autoregressive design with placeholders and structured self-attention masks, warranting future outputs that are invariant to adjustments in inference horizons. A tunable version of rotary position embedding is also integrated into ElasTST to capture time-series-specific periods and enhance adaptability to different horizons. Additionally, ElasTST employs a multi-scale patch design, effectively integrating both fine-grained and coarse-grained information. During the training phase, ElasTST uses a horizon reweighting strategy that approximates the effect of random sampling across multiple horizons with a single fixed horizon setting. Through comprehensive experiments and comparisons with state-of-the-art time-series architectures and contemporary foundation models, we demonstrate the efficacy of ElasTST's unique design elements. Our findings position ElasTST as a robust solution for the practical necessity of varied-horizon forecasting.

Significant progress has been made in text-to-video generation through the use of powerful generative models and large-scale internet data. However, substantial challenges remain in precisely controlling individual elements within the generated video, such as the movement and appearance of specific characters and the manipulation of viewpoints. In this work, we propose a novel paradigm that generates each element in 3D representation separately and then composites them with priors from Large Language Models (LLMs) and 2D diffusion models. Specifically, given an input textual query, our scheme consists of four stages: 1) we leverage the LLMs as the director to first decompose the complex query into several sub-queries, where each sub-query describes each element of the generated video; 2) to generate each element, pre-trained models are invoked by the LLMs to obtain the corresponding 3D representation; 3) to composite the generated 3D representations, we prompt multi-modal LLMs to produce coarse guidance on the scale, location, and trajectory of different objects; 4) to make the results adhere to natural distribution, we further leverage 2D diffusion priors and use score distillation sampling to refine the composition. Extensive experiments demonstrate that our method can generate high-fidelity videos from text with flexible control over each element.

Talking face generation aims at generating photo-realistic video portraits of a target person driven by input audio. According to the nature of audio to lip motions mapping, the same speech content may have different appearances even for the same person at different occasions. Such one-to-many mapping problem brings ambiguity during training and thus causes inferior visual results. Although this one-to-many mapping could be alleviated in part by a two-stage framework (i.e., an audio-to-expression model followed by a neural-rendering model), it is still insufficient since the prediction is produced without enough information (e.g., emotions, wrinkles, etc.). In this paper, we propose MemFace to complement the missing information with an implicit memory and an explicit memory that follow the sense of the two stages respectively. More specifically, the implicit memory is employed in the audio-to-expression model to capture high-level semantics in the audio-expression shared space, while the explicit memory is employed in the neural-rendering model to help synthesize pixel-level details. Our experimental results show that our proposed MemFace surpasses all the state-of-the-art results across multiple scenarios consistently and significantly.

During the COVID-19 pandemic, forecasting COVID-19 trends to support planning and response was a priority for scientists and decision makers alike. In the United States, COVID-19 forecasting was coordinated by a large group of universities, companies, and government entities led by the Centers for Disease Control and Prevention and the US COVID-19 Forecast Hub (https://covid19forecasthub.org). We evaluated approximately 9.7 million forecasts of weekly state-level COVID-19 cases for predictions 1-4 weeks into the future submitted by 24 teams from August 2020 to December 2021. We assessed coverage of central prediction intervals and weighted interval scores (WIS), adjusting for missing forecasts relative to a baseline forecast, and used a Gaussian generalized estimating equation (GEE) model to evaluate differences in skill across epidemic phases that were defined by the effective reproduction number. Overall, we found high variation in skill across individual models, with ensemble-based forecasts outperforming other approaches. Forecast skill relative to the baseline was generally higher for larger jurisdictions (e.g., states compared to counties). Over time, forecasts generally performed worst in periods of rapid changes in reported cases (either in increasing or decreasing epidemic phases) with 95% prediction interval coverage dropping below 50% during the growth phases of the winter 2020, Delta, and Omicron waves. Ideally, case forecasts could serve as a leading indicator of changes in transmission dynamics. However, while most COVID-19 case forecasts outperformed a naïve baseline model, even the most accurate case forecasts were unreliable in key phases. Further research could improve forecasts of leading indicators, like COVID-19 cases, by leveraging additional real-time data, addressing performance across phases, improving the characterization of forecast confidence, and ensuring that forecasts were coherent across spatial scales. In the meantime, it is critical for forecast users to appreciate current limitations and use a broad set of indicators to inform pandemic-related decision making.

Wind is one kind of high-efficient, environmentally-friendly, and cost-effective energy source. Wind power, as one of the largest renewable energy in the world, has been playing a more and more important role in supplying electricity. Though growing dramatically in recent years, the amount of generated wind power can be directly or latently affected by multiple uncertain factors, such as wind speed, wind direction, temperatures, and so on. More importantly, there exist very complicated dependencies of the generated power on the latent composition of these multiple time-evolving variables, which are always ignored by existing works and thus largely hinder the prediction performances. To this end, we propose DEWP , a novel D eep E xpansion learning for W ind P ower forecasting framework to carefully model the complicated dependencies with adequate expressiveness. DEWP starts with a stack-by-stack architecture, where each stack is composed of (i) a variable expansion block that makes use of convolutional layers to capture dependencies among multiple variables; (ii) a time expansion block that applies Fourier series and backcast/forecast mechanism to learn temporal dependencies in sequential patterns. These two tailored blocks expand raw inputs into different latent feature spaces which can model different levels of dependencies of time-evolving sequential data. Moreover, we propose an inference block corresponding for each stack, which applies multi-head self-attentions to acquire attentive features and maps expanded latent representations into generated wind power. In addition, to make DEWP more expressive in handling deep neural architectures, we adapt doubly residue learning to process stack-by-stack outputs. Accurate wind power forecasting (WPF) is then better achieved through fine-grained outputs by continuously removing stack residues and accumulating useful stack forecasts. Finally, we present extensive experiments in the real-world WPF application on two datasets from two different turbines, in order to demonstrate the effectiveness of our approach.

Recent years have witnessed increasing attention being paid to AI-based quantitative investment. Compared to traditional low-frequency data (e.g., daily, weekly), high-frequency data (e.g., minute-level) is often underutilized for low-frequency stock trend prediction, leaving the vast potential for improvement. However, valuable and noisy information coexist in high-frequency data. The learning process of high-frequency factor extractors can easily be overwhelmed by noise, leading to overfitting. Moreover, common techniques used to prevent overfitting often result in poor performance on this task since they usually roughly restrict the model’s capacity, making it challenging to model complex trading signals in high-frequency data. When designing high-frequency factor extractors, we face a tough dilemma. A high-capacity model may easily overfit to noise, while a simple but robust model may not capture complex high-frequency patterns. To address these problems, we propose maintaining model capacity while preventing overfitting by constructing two components that balance information and noise through interactions between them. Specifically, we propose a novel learning framework calledDigger-Guiderto extract informative stock representations from noisy high-frequency data. We develop a high-capacity model calledDiggerto extract local and detailed features from the high-frequency data, and we design a robust model calledGuiderto capture global tendency features and help the Digger overcome the noise. The Digger and Guider enhance each other through mutual distillation during training, serving as data-driven regularizations that work well on this task. Extensive experiments on real-world datasets demonstrate that our framework can produce powerful high-frequency stock factors that significantly improve stock trend prediction performance and our understanding of the finance market.

Traveling Salesman Problem (TSP), as a classic routing optimization problem originally arising in the domain of transportation and logistics, has become a critical task in broader domains, such as manufacturing and biology. Recently, Deep Reinforcement Learning (DRL) has been increasingly employed to solve TSP due to its high inference efficiency. Nevertheless, most of existing end-to-end DRL algorithms only perform well on small TSP instances and can hardly generalize to large scale because of the drastically soaring memory consumption and computation time along with the enlarging problem scale. In this paper, we propose a novel end-to-end DRL approach, referred to as Pointerformer, based on multi-pointer Transformer. Particularly, Pointerformer adopts both reversible residual network in the encoder and multi-pointer network in the decoder to effectively contain memory consumption of the encoder-decoder architecture. To further improve the performance of TSP solutions, Pointerformer employs a feature augmentation method to explore the symmetries of TSP at both training and inference stages as well as an enhanced context embedding approach to include more comprehensive context information in the query. Extensive experiments on a randomly generated benchmark and a public benchmark have shown that, while achieving comparative results on most small-scale TSP instances as state-of-the-art DRL approaches do, Pointerformer can also well generalize to large-scale TSPs.

We propose an end-to-end learning framework based on hierarchical reinforcement learning, called H-TSP, for addressing the large-scale Traveling Salesman Problem (TSP). The proposed H-TSP constructs a solution of a TSP instance starting from the scratch relying on two components: the upper-level policy chooses a small subset of nodes (up to 200 in our experiment) from all nodes that are to be traversed, while the lower-level policy takes the chosen nodes as input and outputs a tour connecting them to the existing partial route (initially only containing the depot). After jointly training the upper-level and lower-level policies, our approach can directly generate solutions for the given TSP instances without relying on any time-consuming search procedures. To demonstrate effectiveness of the proposed approach, we have conducted extensive experiments on randomly generated TSP instances with different numbers of nodes. We show that H-TSP can achieve comparable results (gap 3.42% vs. 7.32%) as SOTA search-based approaches, and more importantly, we reduce the time consumption up to two orders of magnitude (3.32s vs. 395.85s). To the best of our knowledge, H-TSP is the first end-to-end deep reinforcement learning approach that can scale to TSP instances of up to 10000 nodes. Although there are still gaps to SOTA results with respect to solution quality, we believe that H-TSP will be useful for practical applications, particularly those that are time-sensitive e.g., on-call routing and ride hailing service.

Video dubbing aims to translate the original speech in a film or television program into the speech in a target language, which can be achieved with a cascaded system consisting of speech recognition, machine translation and speech synthesis. To ensure the translated speech to be well aligned with the corresponding video, the length/duration of the translated speech should be as close as possible to that of the original speech, which requires strict length control. Previous works usually control the number of words or characters generated by the machine translation model to be similar to the source sentence, without considering the isochronicity of speech as the speech duration of words/characters in different languages varies. In this paper, we propose VideoDubber, a machine translation system tailored for the task of video dubbing, which directly considers the speech duration of each token in translation, to match the length of source and target speech. Specifically, we control the speech length of generated sentence by guiding the prediction of each word with the duration information, including the speech duration of itself as well as how much duration is left for the remaining words. We design experiments on four language directions (German -> English, Spanish -> English, Chinese English), and the results show that VideoDubber achieves better length control ability on the generated speech than baseline methods. To make up the lack of real-world datasets, we also construct a real-world test set collected from films to provide comprehensive evaluations on the video dubbing task.

Physics-Informed Neural Network (PINN) has become a commonly used machine learning approach to solve partial differential equations (PDE). But, facing high-dimensional secondorder PDE problems, PINN will suffer from severe scalability issues since its loss includes second-order derivatives, the computational cost of which will grow along with the dimension during stacked back-propagation. In this work, we develop a novel approach that can significantly accelerate the training of Physics-Informed Neural Networks. In particular, we parameterize the PDE solution by the Gaussian smoothed model and show that, derived from Stein’s Identity, the second-order derivatives can be efficiently calculated without back-propagation. We further discuss the model capacity and provide variance reduction methods to address key limitations in the derivative estimation. Experimental results show that our proposed method can achieve competitive error compared to standard PINN training but is significantly faster.

3D Morphable Models (3DMMs) demonstrate great potential for reconstructing faithful and animatable 3D facial surfaces from a single image. The facial surface is influenced by the coarse shape, as well as the static detail (e.g., person-specific appearance) and dynamic detail (e.g., expression-driven wrinkles). Previous work struggles to decouple the static and dynamic details through image-level supervision, leading to reconstructions that are not realistic. In this paper, we aim at high-fidelity 3D face reconstruction and propose HiFace to explicitly model the static and dynamic details. Specifically, the static detail is modeled as the linear combination of a displacement basis, while the dynamic detail is modeled as the linear interpolation of two displacement maps with polarized expressions. We exploit several loss functions to jointly learn the coarse shape and fine details with both synthetic and real-world datasets, which enable HiFace to reconstruct high-fidelity 3D shapes with animatable details. Extensive quantitative and qualitative experiments demonstrate that HiFace presents state-of-the-art reconstruction quality and faithfully recovers both the static and dynamic details. Our project page: https://project-hiface.github.io.

Unsupervised Anomaly Detection (UAD) is a key data mining problem owing to its wide real-world applications. Due to the complete absence of supervision signals, UAD methods rely on implicit assumptions about anomalous patterns (e.g., scattered/sparsely/densely clustered) to detect anomalies. However, real-world data are complex and vary significantly across different domains. No single assumption can describe such complexity and be valid in all scenarios. This is also confirmed by recent research that shows no UAD method is omnipotent [1]. Based on above observations, instead of searching for a magic universal winner assumption, we seek to design a general UAD Booster (UADB) that empowers any UAD models with adaptability to different data. This is a challenging task given the heterogeneous model structures and assumptions adopted by existing UAD methods. To achieve this, we dive deep into the UAD problem and find that compared to normal data, anomalies (i) lack clear structure/pattern in feature space, thus (ii) harder to learn by model without a suitable assumption, and finally, leads to (iii) high variance between different learners. In light of these findings, we propose to (i) distill the knowledge of the source UAD model to an imitation learner (booster) that holds no data assumption, then (ii) exploit the variance between them to perform automatic correction, and thus (iii) improve the booster over the original UAD model. We use a neural network as the booster for its strong expressive power as a universal approximator and ability to perform flexible posthoc tuning. Note that UADB is a model-agnostic framework that can enhance heterogeneous UAD models in a unified way. Extensive experiments on over 80 tabular datasets demonstrate the effectiveness of UADB. To facilitate further research, code, figures, and datasets are available at UADB’s Github repository1.

In many real-world tasks, some parts of state features, called contexts, are independent of action signals, e.g., customer demand in inventory control, speed of lead car in autonomous driving, etc. One of the challenges of reinforcement learning in these applications is that the true context transitions can be easily exposed some unknown source of contamination, leading to a shift of context transitions between source domains and target domains, which could cause performance degradation for RL algorithms. However, existing methods on robust RL aim at learning robust policies against the deviations of the entire system dynamics. To tackle this problem, this paper proposes the framework of robust situational Markov decision process (RS-MDP) which captures the possible deviations of context transitions explicitly. To scale to large context space, we introduce the softmin smoothed robust Bellman operator to learn the robust Q-value approximately, and apply our RS-MDP framework to existing RL algorithm SAC to learn the desired robust policies. We conduct experiments on several robot control tasks with dynamic contexts and inventory control tasks to demonstrate that our algorithm can generalize better and more robust against deviations of context transitions, and outperform existing robust RL algorithms.

Order execution is a fundamental task in quantitative finance, aiming at finishing acquisition or liquidation for a number of trading orders of the specific assets. Recent advance in model-free reinforcement learning (RL) provides a data-driven solution to the order execution problem. However, the existing works always optimize execution for an individual order, overlooking the practice that multiple orders are specified to execute simultaneously, resulting in suboptimality and bias. In this paper, we first present a multi-agent RL (MARL) method for multi-order execution considering practical constraints. Specifically, we treat every agent as an individual operator to trade one specific order, while keeping communicating with each other and collaborating for maximizing the overall profits. Nevertheless, the existing MARL algorithms often incorporate communication among agents by exchanging only the information of their partial observations, which is inefficient in complicated financial market. To improve collaboration, we then propose a learnable multi-round communication protocol, for the agents communicating the intended actions with each other and refining accordingly. It is optimized through a novel action value attribution method which is provably consistent with the original learning objective yet more efficient. The experiments on the data from two real-world markets have illustrated superior performance with significantly better collaboration effectiveness achieved by our method.

As one of the major threats to the healthy development of various online platforms, fraud has become increasingly committed in the form of gangs since collusive fraudulent activities are much easier to obtain illicit benefits with lower exposure risk. To detect fraudsters in a gang, spatio-temporal graph neural network models have been widely applied to detect both temporal and spatial collusive patterns. However, a closer peek into real-world records of fraudsters can reveal that fraud gangs usually conduct community-level camouflage, specified by two types, i.e., temporal and spatial camouflage. Such camouflage can disguise gangs as benign communities by concealing collusive patterns and thus deceiving many existing graph neural network models. In the meantime, many existing graph neural network models suffer from the challenge of extreme sample imbalance caused by rare fraudsters hidden among massive users. To handle all these challenges, in this paper, we propose a generative adversarial network framework, named Adversarial Camouflage Detector, to detect fraudsters. Concretely, this ACD framework consists of four modules, in charge of community division, camouflage identification, fraudster detection, and camouflage generation, respectively. The first three modules form up a discriminator that uses spatio-temporal graph neural networks as the foundation model and enhance fraudster detection by amplifying the gangs' collusive patterns through automatically identifying and removing camouflage. Meanwhile, the camouflage generation module plays as the generator role that generates fraudsters samples by competing against the discriminator to alleviate the challenge of sample imbalance and increase the model robustness. The experimental result shows that our proposed method outperforms other methods on real-world datasets.

The aging of global population is witnessing increasing prevalence of spinal disorders. According to latest statistics, nearly five percent of the global population is suffering from spinal disorders. To relieve the pain, many spine patients tend to choose surgeries. However, recent evidences reveal that some spine patients can self-heal over time with nonoperative treatment and even surgeries may not ease the pain for some others, which raises a critical question regarding the appropriateness of such surgeries. Furthermore, the complex and time-consuming diagnostic process places a great burden on both clinicians and patients. Due to the development of web technology, it is possible for spine patients to obtain decision making suggestions on the Internet. The uniqueness of web technology, including its popularity, convenience, and immediacy, makes intelligent healthcare techniques, especially Treatment Outcome Forecasting (TOF), able to support clinical decision-making for doctors and healthcare providers. Despite a few machine-learning-based methods have been proposed for TOF, their performance and feasibility are mostly unsatisfactory due to the neglect of a few practical challenges (caused by applying on the Internet), including biased data selection, noisy supervision, and patient noncompliance. In light of this, we propose DeepTOF, a novel end-to-end deep learning model to cope with the unique challenges in web-based long-term continuous spine TOF. In particular, we combine different patient groups and train a unified predictive model to eliminate the data selection bias. Towards robust learning, we further take advantage of indirect but fine-grained supervision signals to mutually calibrate with the noisy training labels. Additionally, a feature selector was co-trained with DeepTOF to select the most important features (i.e., answers/indicators that need to be collected) for inference, thus easing the use of DeepTOF during web-based real-world application. The proposed DeepTOF could bring great benefits to the rehabilitation of spine patients. Comprehensive experiments and analysis show that DeepTOF outperforms conventional solutions by a large margin.

Irregularly sampled multivariate time series are ubiquitous in various fields, particularly in healthcare, and exhibit two key characteristics: intra-series irregularity and inter-series discrepancy. Intra-series irregularity refers to the fact that time-series signals are often recorded at irregular intervals, while inter-series discrepancy refers to the significant variability in sampling rates among diverse series. However, recent advances in irregular time series have primarily focused on addressing intra-series irregularity, overlooking the issue of inter-series discrepancy. To bridge this gap, we present Warpformer, a novel approach that fully considers these two characteristics. In a nutshell, Warpformer has several crucial designs, including a specific input representation that explicitly characterizes both intra-series irregularity and inter-series discrepancy, a warping module that adaptively unifies irregular time series in a given scale, and a customized attention module for representation learning. Additionally, we stack multiple warping and attention modules to learn at different scales, producing multi-scale representations that balance coarse-grained and fine-grained signals for downstream tasks. We conduct extensive experiments on widely used datasets and a new large-scale benchmark built from clinical databases. The results demonstrate the superiority of Warpformer over existing state-of-the-art approaches.

While recent research has made significant progress in speech-driven talking face generation, the quality of the generated video still lags behind that of real recordings. One reason for this is the use of handcrafted intermediate representations like facial landmarks and 3DMM coefficients, which are designed based on human knowledge and are insufficient to precisely describe facial movements. Additionally, these methods require an external pretrained model for extracting these representations, whose performance sets an upper bound on talking face generation. To address these limitations, we propose a novel method called DAE-Talker that leverages data-driven latent representations obtained from a diffusion autoencoder (DAE). DAE contains an image encoder that encodes an image into a latent vector and a DDIM-based image decoder that reconstructs the image from it. We train our DAE on talking face video frames and then extract their latent representations as the training target for a Conformer-based speech2latent model. During inference, DAE-Talker first predicts the latents from speech and then generates the video frames with the image decoder in DAE from the predicted latents. This allows DAE-Talker to synthesize full video frames and produce natural head movements that align with the content of speech, rather than relying on a predetermined head pose from a template video. We also introduce pose modelling in speech2latent for pose controllability. Additionally, we propose a novel method for generating continuous video frames with the DDIM-based image decoder trained on individual frames, eliminating the need for modelling the joint distribution of consecutive frames directly. Our experiments show that DAE-Talker outperforms existing popular methods in lip-sync, video fidelity, and pose naturalness. We also conduct ablation studies to analyze the effectiveness of the proposed techniques and demonstrate the pose controllability of DAE-Talker.

Multi-objective reinforcement learning (MORL) has been proposed to learn control policies over multiple competing objectives with each possible preference over returns. However, current MORL algorithms fail to account for distributional preferences over the multi-variate returns, which are particularly important in real-world scenarios such as autonomous driving. To address this issue, we extend the concept of Pareto-optimality in MORL into distributional Pareto-optimality, which captures the optimality of return distributions, rather than the expectations. Our proposed method, called Distributional Pareto-Optimal Multi-Objective Reinforcement Learning~(DPMORL), is capable of learning distributional Pareto-optimal policies that balance multiple objectives while considering the return uncertainty. We evaluated our method on several benchmark problems and demonstrated its effectiveness in discovering distributional Pareto-optimal policies and satisfying diverse distributional preferences compared to existing MORL methods.

Diffusion models are a class of generative models that serve to establish a stochastic transport map between an empirically observed, yet unknown, target distribution and a known prior. Despite their remarkable success in real-world applications, a theoretical understanding of their generalization capabilities remains underdeveloped. This work embarks on a comprehensive theoretical exploration of the generalization attributes of diffusion models. We establish the theoretical estimates of the generalization gap that evolves in tandem with the training dynamics of score-based diffusion models, suggesting a polynomially small generalization error ($O(n^{-2/5}+m^{-4/5})$) on both the sample size $n$ and the model capacity $m$, evading the curse of dimensionality (i.e., independent of the data dimension) when *early-stopped*. Furthermore, we extend our quantitative analysis to a *data-dependent* scenario, wherein target distributions are portrayed as a succession of densities with progressively increasing distances between modes. This precisely elucidates the *adverse* effect of "*modes shift*'' in ground truths on the model generalization. Furthermore, these estimates are not solely theoretical constructs but have also been confirmed through numerical simulations. Our findings contribute to the rigorous understanding of diffusion models' generalization properties and provide insights that may guide practical applications.

Audio editing is applicable for various purposes, such as adding background sound effects, replacing a musical instrument, and repairing damaged audio. Recently, some diffusion-based methods achieved zero-shot audio editing by using a diffusion and denoising process conditioned on the text description of the output audio. However, these methods still have some problems: 1) they have not been trained on editing tasks and cannot ensure good editing effects; 2) they can erroneously modify audio segments that do not require editing; 3) they need a complete description of the output audio, which is not always available or necessary in practical scenarios. In this work, we propose AUDIT, an instruction-guided audio editing model based on latent diffusion models. Specifically, \textbf{AUDIT} has three main design features: 1) we construct triplet training data (instruction, input audio, output audio) for different audio editing tasks and train a diffusion model using instruction and input (to be edited) audio as conditions and generating output (edited) audio; 2) it can automatically learn to only modify segments that need to be edited by comparing the difference between the input and output audio; 3) it only needs edit instructions instead of full target audio descriptions as text input. AUDIT achieves state-of-the-art results in both objective and subjective metrics for several audio editing tasks (e.g., adding, dropping, replacement, inpainting, super-resolution). Demo samples are available at https://audit-demopage.github.io/.

In many real-world scenarios, we often deal with streaming data that is sequentially collected over time. Due to the non-stationary nature of the environment, the streaming data distribution may change in unpredictable ways, which is known as the concept drift in the literature. To handle concept drift, previous methods first detect when/where the concept drift happens and then adapt models to fit the distribution of the latest data. However, there are still many cases that some underlying factors of environment evolution are predictable, making it possible to model the future concept drift trend of the streaming data, while such cases are not fully explored in previous work. In this paper, we propose a novel method DDG-DA, that can effectively forecast the evolution of data distribution and improve the performance of models. Specifically, we first train a predictor to estimate the future data distribution, then leverage it to generate training samples, and finally train models on the generated data. We conduct experiments on three real-world tasks (forecasting on stock price trend, electricity load and solar irradiance) and obtained significant improvement on multiple widely-used models.

Continuous glucose monitoring prediction is a crucial yet challenging task in precision medicine. This paper presents a novel neural ODE based approach for predicting continuous glucose monitoring (CGM) levels purely based on sporadic self-monitoring signals. We integrate the expert knowledge from physiological model into our model to improve the accuracy. Experiments on the real-world data demonstrate that our method outperforms other state-of-the-art methods on NRMSE metrics.

Energy markets enable matching supply and demand through inter- and intra-region electricity trading. Due to the interconnected nature of the energy markets, the supply-demand constraints in one region can impact prices in another connected region. To incorporate these spatiotemporal relationships, we propose a novel graph neural network architecture incorporating multidimensional time-series features to forecast price (node attribute) and energy flow (edge attribute) between regions simultaneously. To the best of our knowledge, this paper is the first attempt to combine node and edge level forecasting in energy markets. We show that our proposed approach has a mean absolute prediction percentage error of 12.8%, which significantly beats the state-of-the-art baseline techniques.

Learning the embeddings of knowledge graphs (KG) is vital in artificial intelligence, and can benefit various downstream applications, such as recommendation and question answering. In recent years, many research efforts have been proposed for knowledge graph embedding (KGE). However, most previous KGE methods ignore the semantic similarity between the related entities and entity-relation couples in different triples since they separately optimize each triple with the scoring function. To address this problem, we propose a simple yet efficient contrastive learning framework for tensor decomposition based (TDB) KGE, which can shorten the semantic distance of the related entities and entity-relation couples in different triples and thus improve the performance of KGE. We evaluate our proposed method on three standard KGE datasets: WN18RR, FB15k-237 and YAGO3-10. Our method can yield some new state-of-the-art results, achieving 51.2% MRR, 46.8% Hits@1 on the WN18RR dataset, 37.8% MRR, 28.6% Hits@1 on FB15k-237 dataset, and 59.1% MRR, 51.8% Hits@1 on the YAGO3-10 dataset.

We consider an offline reinforcement learning (RL) setting where the agent needs to learn from a dataset collected by rolling out multiple behavior policies. There are two challenges for this setting: 1) The optimal trade-off between optimizing the RL signal and the behavior cloning (BC) signal changes on different states due to the variation of the action coverage induced by different behavior policies. Previous methods fail to handle this by only controlling the global trade-off. 2) For a given state, the action distribution generated by different behavior policies may have multiple modes. The BC regularizers in many previous methods are mean-seeking, resulting in policies that select out-of-distribution (OOD) actions in the middle of the modes. In this paper, we address both challenges by using adaptively weighted reverse Kullback-Leibler (KL) divergence as the BC regularizer based on the TD3 algorithm. Our method not only trades off the RL and BC signals with per-state weights (i.e., strong BC regularization on the states with narrow action coverage, and vice versa) but also avoids selecting OOD actions thanks to the mode-seeking property of reverse KL. Empirically, our algorithm can outperform existing offline RL algorithms in the MuJoCo locomotion tasks with the standard D4RL datasets as well as the mixed datasets that combine the standard datasets.

It is challenging for reinforcement learning (RL) algorithms to succeed in real-world applications. Take financial trading as an example, the market information is noisy yet imperfect and the macroeconomic regulation or other factors may shift between training and evaluation, thus it requires both generalization and high sample efficiency for resolving the task. However, directly applying typical RL algorithms can lead to poor performance in such scenarios. To derive a robust and applicable RL algorithm, in this work, we design a simple but effective method named Ensemble Proximal Policy Optimization (EPPO), which learns ensemble policies in an end-to-end manner. Notably, EPPO combines each policy and the policy ensemble organically and optimizes both simultaneously. In addition, EPPO adopts a diversity enhancement regularization over the policy space which helps to generalize to unseen states and promotes exploration. We theoretically prove that EPPO can increase exploration efficacy, and through comprehensive experimental evaluations on various tasks, we demonstrate that EPPO achieves higher efficiency and is robust for real-world applications compared with vanilla policy optimization algorithms and other ensemble methods. Code and supplemental materials are available at https://seqml.github.io/eppo.

Modeling sequential patterns from data is at the core of various time series forecasting tasks. Deep learning models have greatly outperformed many traditional models, but these black-box models generally lack explainability in prediction and decision making. To reveal the underlying trend with understandable mathematical expressions, scientists and economists tend to use partial differential equations (PDEs) to explain the highly nonlinear dynamics of sequential patterns. However, it usually requires domain expert knowledge and a series of simplified assumptions, which is not always practical and can deviate from the ever-changing world. Is it possible to learn the differential relations from data dynamically to explain the time-evolving dynamics? In this work, we propose an learning framework that can automatically obtain interpretable PDE models from sequential data. Particularly, this framework is comprised of learnable differential blocks, named P-blocks, which is proved to be able to approximate any time-evolving complex continuous functions in theory. Moreover, to capture the dynamics shift, this framework introduces a meta-learning controller to dynamically optimize the hyper-parameters of a hybrid PDE model. Extensive experiments on times series forecasting of financial, engineering, and health data show that our model can provide valuable interpretability and achieve comparable performance to state-of-the-art models. From empirical studies, we find that learning a few differential operators may capture the major trend of sequential dynamics without massive computational complexity.

As a longstanding learning paradigm, multi-task learning has been widely applied into a variety of machine learning applications. Nonetheless, identifying which tasks should be learned together is still a challenging fundamental problem because the possible task combinations grow exponentially with the number of tasks, and existing solutions heavily relying on heuristics may probably lead to ineffective groupings with severe performance degradation. To bridge this gap, we develop a systematic multi-task grouping framework with a new meta-learning problem on task combinations, which is to predict the per-task performance gains of multi-task learning over single-task learning for any combination. Our underlying assumption is that no matter how large the space of task combinations is, the relationships between task combinations and performance gains lie in some low-dimensional manifolds and thus can be learnable. Accordingly, we develop a neural meta learner, MTG-Net, to capture these relationships, and design an active learning strategy to progressively select meta-training samples. In this way, even with limited meta samples, MTG-Net holds the potential to produce reasonable gain estimations on arbitrary task combinations. Extensive experiments on diversified multi-task scenarios demonstrate the efficiency and effectiveness of our method. Specifically, in a large-scale evaluation with $27$ tasks, which produce over one hundred million task combinations, our method almost doubles the performance obtained by the existing best solution given roughly the same computational cost. Data and code are available at https://github.com/ShawnKS/MTG-Net.

Time-series prediction is of high practical value in a wide range of applications such as econometrics and meteorology, where the data are commonly formed by temporal patterns. Most prior works ignore the diversity of dynamic pattern frequency, i.e., different granularities, suffering from insufficient information exploitation. Thus, multi-granularity learning is still under-explored for time-series prediction. In this paper, we propose a Multi-granularity Residual Learning Framework (MRLF) for more effective time series prediction. For a given time series, intuitively, there are more or less semantic overlaps and validity differences among its representations of different granularities. Due to the information redundancy, straightforward methods that leverage multi-granularity data, such as concatenation or ensemble, can easily lead to the model being dominated by the redundant coarse-grained trend information. Therefore, we design a novel residual learning net to model the prior knowledge of the fine-grained data’s distribution through the coarse-grained one. Then, by calculating the residual between multi-granularity data, the redundant information be removed. Furthermore, to alleviate the side effect of validity differences, we introduce a self-supervised objective for confidence estimation, which delivers more effective optimization without the requirement of additional annotation efforts. Extensive experiments on the real-world datasets indicate that multi-granular information significantly improves the time series prediction performance, and our model is superior in capturing such information.

Recently the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real tasks) through data selection, loss function design, etc. Learning to reweight, which is a specific kind of teaching that reweights training data using a teacher model, receives much attention due to its simplicity and effectiveness. In existing learning to reweight works, the teacher model only utilizes shallow/surface information such as training iteration number and loss/accuracy of the student model from training/validation sets, but ignores the internal states of the student model, which limits the potential of learning to reweight. In this work, we propose an improved data reweighting algorithm, in which the student model provides its internal states to the teacher model, and the teacher model returns adaptive weights of training samples to enhance the training of the student model. The teacher model is jointly trained with the student model using meta gradients propagated from a validation set. Experiments on image classification with clean/noisy labels and neural machine translation empirically demonstrate that our algorithm makes significant improvement over previous methods.

As a fundamental problem in algorithmic trading, order execution aims at fulfilling a specific trading order, either liquidation or acquirement, for a given instrument. Towards effective execution strategy, recent years have witnessed the shift from the analytical view with model-based market assumptions to model-free perspective, i.e., reinforcement learning, due to its nature of sequential decision optimization. However, the noisy and yet imperfect market information that can be leveraged by the policy has made it quite challenging to build up sample efficient reinforcement learning methods to achieve effective order execution. In this paper, we propose a novel universal trading policy optimization framework to bridge the gap between the noisy yet imperfect market states and the optimal action sequences for order execution. Particularly, this framework leverages a policy distillation method that can better guide the learning of the common policy towards practically optimal execution by an oracle teacher with perfect information to approximate the optimal trading strategy. The extensive experiments have shown significant improvements of our method over various strong baselines, with reasonable trading actions.

Stock trend prediction plays a crucial role in quantitative investing. Given the prediction task on a certain granularity (e.g., daily trend), a large portion of existing studies merely leverage market data of the same granularity (e.g., daily market data). In financial investment scenarios, however, there exist amounts of finer-grained information (e.g., high-frequency data) that contain more detailed investment signals beyond the original granularity data. This motivates us to investigate how to leverage multi-granularity market data to enhance the accuracy of stock trend prediction. Some straightforward methods, such as concatenating finer-grained data as features or fusing with a model based on finer-grained features, may not lead to more precise stock trend prediction due to some unique challenges. First, the inconsistency of granularity between the target trend and finer-grained data could substantially increase optimization difficulty, such as the relative sparsity of the target trend compared with higher dimensions of finer-grained features. Moreover, the continuously changing financial market state could result in varying efficacy of heterogeneous multi-granularity information, which consequently requires a dynamic approach for proper fusion among them. In this paper, we propose the Contrastive Multi-Granularity Learning Framework (CMLF) to address these challenges. Particularly, we first design two novel contrastive learning objectives at the pre-training stage to address the inconsistency issue by constructing additional self-supervised signals relying on the inherent character of stock data. We also design a gate mechanism based on market-aware technical indicators to fuse the multi-granularity features at each time step adaptively. Extensive experiments on three real-world datasets show significant improvements of our approach over the state-of-the-art baselines on stock trend prediction and profitability in real investing scenarios.

The outbreak of the COVID-19 pandemic has largely influenced the world and our normal daily lives. To combat this pandemic efficiently, governments usually need to coordinate essential resources across multiple regions and adjust intervention polices at the right time, which all call for accurate and robust forecasting of future epidemic trends. However, designing such a forecasting system is non-trivial, since we need to handle all kinds of locations at different administrative levels, which include pretty different epidemic-evolving patterns. Moreover, there are dynamic and volatile correlations of pandemic conditions among these locations, which further enlarge the difficulty in forecasting. With these challenges in mind, we develop a novel spatial-temporal forecasting framework. First, to accommodate all kinds of locations at different administrative levels, we propose a unified hierarchical view, which mimics the aggregation procedure of pandemic statistics. Then, this view motivates us to facilitate joint learning across administrative levels and inspires us to design the cross-level consistency loss as an extra regularization to stabilize model training. Besides, to capture those dynamic and volatile spatial correlations, we design a customized spatial module with adaptive edge gates, which can both reinforce effective messages and disable irrelevant ones. We put this framework into production to help the battle against COVID-19 in the United States. A comprehensive online evaluation across three months demonstrates that our projections are the most competitive ones among all results produced by dozens of international group and even surpass the official ensemble in many cases. We also visualize our unique edge gates to understand the evolvement of spatial correlations and present intuitive case studies. Besides, we open source our implementation at https://github.com/dolphin-zs/HierST to facilitate future research towards better epidemic modeling.

Value function decomposition (VFD) methods under the popular paradigm of centralized training and decentralized execution (CTDE) have promoted multi-agent reinforcement learning progress. However, existing VFD methods proceed from a group's value function decomposition to only solve cooperative tasks. With the individual value function decomposition, we propose MFVFD, a novel multi-agent Q-learning approach for solving cooperative and non-cooperative tasks based on mean-field theory. Our analysis on the Hawk-Dove and Nonmonotonic Cooperation matrix games evaluate MFVFD's convergent solution. Empirical studies on the challenging mixed cooperative-competitive tasks where hundreds of agents coexist demonstrate that MFVFD significantly outperforms existing baselines.

Most of existing advantage function estimation methods in reinforcement learning suffer from the problem of high variance, which scales unfavorably with the time horizon. To address this challenge, we propose to identify the independence property between current action and future states in environments, which can be further leveraged to effectively reduce the variance of the advantage estimation. In particular, the recognized independence property can be naturally utilized to construct a novel importance sampling advantage estimator with close-to-zero variance even when the Monte-Carlo return signal yields a large variance. To further remove the risk of the high variance introduced by the new estimator, we combine it with existing Monte-Carlo estimator via a reward decomposition model learned by minimizing the estimation variance. Experiments demonstrate that our method achieves higher sample efficiency compared with existing advantage estimation methods in complex environments.

Successful quantitative investment usually relies on precise predictions of the future movement of the stock price. Recently, machine learning based solutions have shown their capacity to give more accurate stock prediction and become indispensable components in modern quantitative investment systems. However, the i.i.d. assumption behind existing methods is inconsistent with the existence of diverse trading patterns in the stock market, which inevitably limits their ability to achieve better stock prediction performance. In this paper, we propose a novel architecture, Temporal Routing Adaptor (TRA), to empower existing stock prediction models with the ability to model multiple stock trading patterns. Essentially, TRA is a lightweight module that consists of a set of independent predictors for learning multiple patterns as well as a router to dispatch samples to different predictors. Nevertheless, the lack of explicit pattern identifiers makes it quite challenging to train an effective TRA-based model. To tackle this challenge, we further design a learning algorithm based on Optimal Transport (OT) to obtain the optimal sample to predictor assignment and effectively optimize the router with such assignment through an auxiliary loss term. Experiments on the real-world stock ranking task show that compared to the state-of-the-art baselines, e.g., Attention LSTM and Transformer, the proposed method can improve information coefficient (IC) from 0.053 to 0.059 and 0.051 to 0.056 respectively. Our dataset and code used in this work are publicly available2: https://github.com/microsoft/qlib.

Stock trend forecasting, aiming at predicting the stock future trends, is crucial for investors to seek maximized profits from the stock market. Many event-driven methods utilized the events extracted from news, social media, and discussion board to forecast the stock trend in recent years. However, existing event-driven methods have two main shortcomings: 1) overlooking the influence of event information differentiated by the stock-dependent properties; 2) neglecting the effect of event information from other related stocks. In this paper, we propose a relational event-driven stock trend forecasting (REST) framework, which can address the shortcoming of existing methods. To remedy the first shortcoming, we propose to model the stock context and learn the effect of event information on the stocks under different contexts. To address the second shortcoming, we construct a stock graph and design a new propagation layer to propagate the effect of event information from related stocks. The experimental studies on the real-world data demonstrate the efficiency of our REST framework. The results of investment simulation show that our framework can achieve a higher return of investment than baselines.

For a target task where the labeled data are unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the global source and target distributions without considering the relationships between two subdomains within the same category of different domains, leading to unsatisfying transfer learning performance without capturing the fine-grained information. Recently, more and more researchers pay attention to subdomain adaptation that focuses on accurately aligning the distributions of the relevant subdomains. However, most of them are adversarial methods that contain several loss functions and converge slowly. Based on this, we present a deep subdomain adaptation network (DSAN) that learns a transfer network by aligning the relevant subdomain distributions of domain-specific layer activations across different domains based on a local maximum mean discrepancy (LMMD). Our DSAN is very simple but effective, which does not need adversarial training and converges fast. The adaptation can be achieved easily with most feedforward network models by extending them with LMMD loss, which can be trained efficiently via backpropagation. Experiments demonstrate that DSAN can achieve remarkable results on both object recognition tasks and digit classification tasks. Our code will be available at https://github.com/easezyc/deep-transfer-learning.

Model compression has become necessary when applying neural networks (NN) into many real application tasks that can accept slightly-reduced model accuracy but with strict tolerance to model complexity. Recently, Knowledge Distillation, which distills the knowledge from well-trained and highly complex teacher model into a compact student model, has been widely used for model compression. However, under the strict requirement on the resource cost, it is quite challenging to make student model achieve comparable performance with the teacher one, essentially due to the drastically-reduced expressiveness ability of the compact student model. Inspired by the nature of the expressiveness ability in NN, we propose to use multi-segment activation, which can significantly improve the expressiveness ability with very little cost, in the compact student model. Specifically, we propose a highly efficient multi-segment activation, called Light Multi-segment Activation (LMA), which can rapidly produce multiple linear regions with very few parameters by leveraging the statistical information. With using LMA, the compact student model is capable of achieving much better performance effectively and efficiently, than the ReLU-equipped one with same model complexity. Furthermore, the proposed method is compatible with other model compression techniques, such as quantization, which means they can be used jointly for better compression performance. Experiments on state-of-the-art NN architectures over the real-world tasks demonstrate the effectiveness and extensibility of the LMA.

Many real-world applications reveal difficulties in learning classifiers from imbalanced data. The rising big data era has been witnessing more classification tasks with large-scale but extremely imbalance and low-quality datasets. Most of existing learning methods suffer from poor performance or low computation efficiency under such a scenario. To tackle this problem, we conduct deep investigations into the nature of class imbalance, which reveals that not only the disproportion between classes, but also other difficulties embedded in the nature of data, especially, noises and class overlapping, prevent us from learning effective classifiers. Taking those factors into consideration, we propose a novel framework for imbalance classification that aims to generate a strong ensemble by self-paced harmonizing data hardness via under-sampling. Extensive experiments have shown that this new framework, while being very computationally efficient, can lead to robust performance even under highly overlapping classes and extremely skewed distribution. Note that, our methods can be easily adapted to most of existing learning methods (e.g., C4.5, SVM, GBDT and Neural Network) to boost their performance on imbalanced data.

It is fundamental to measure model complexity of deep neural networks. A good model complexity measure can help to tackle many challenging problems, such as overfitting detection, model selection, and performance improvement. The existing literature on model complexity mainly focuses on neural networks with piecewise linear activation functions. Model complexity of neural networks with general curve activation functions remains an open problem. To tackle the challenge, in this paper, we first propose linear approximation neural network (LANN for short), a piecewise linear framework to approximate a given deep model with curve activation function. LANN constructs individual piecewise linear approximation for the activation function of each neuron, and minimizes the number of linear regions to satisfy a required approximation degree. Then, we analyze the upper bound of the number of linear regions formed by LANNs, and derive the complexity measure based on the upper bound. To examine the usefulness of the complexity measure, we experimentally explore the training process of neural networks and detect overfitting. Our results demonstrate that the occurrence of overfitting is positively correlated with the increase of model complexity during training. We find that the L1 and L2 regularizations suppress the increase of model complexity. Finally, we propose two approaches to prevent overfitting by directly constraining model complexity, namely neuron pruning and customized L1 regularization.

Imbalanced learning (IL), i.e., learning unbiased models from class-imbalanced data, is a challenging problem. Typical IL methods including resampling and reweighting were designed based on some heuristic assumptions. They often suffer from unstable performance, poor applicability, and high computational cost in complex tasks where their assumptions do not hold. In this paper, we introduce a novel ensemble IL framework named MESA. It adaptively resamples the training set in iterations to get multiple classifiers and forms a cascade ensemble model. MESA directly learns the sampling strategy from data to optimize the final metric beyond following random heuristics. Moreover, unlike prevailing meta-learning-based IL solutions, we decouple the model-training and meta-training in MESA by independently train the meta-sampler over task-agnostic meta-data. This makes MESA generally applicable to most of the existing learning models and the meta-sampler can be efficiently applied to new tasks. Extensive experiments on both synthetic and real-world tasks demonstrate the effectiveness, robustness, and transferability of MESA. Our code is available at https://github.com/ZhiningLiu1998/mesa.

Evolution Strategies (ES), a class of black-box optimization algorithms, has recently been demonstrated to be a viable alternative to popular MDP-based RL techniques such as Qlearning and Policy Gradients. ES achieves fairly good performance on challenging reinforcement learning problems and is easier to scale in a distributed setting. However, standard ES algorithms perform one gradient update per data sample, which is not very efficient. In this paper, with the purpose of more efficient using of sampled data, we propose a novel iterative procedure that optimizes a surrogate objective function, enabling to reuse data sample for multiple epochs of updates. We prove monotonic improvement guarantee for such procedure. By making several approximations to the theoretically-justified procedure, we further develop a practical algorithm called Trust Region Evolution Strategies (TRES). Our experiments demonstrate the effectiveness of TRES on a range of popular MuJoCo locomotion tasks in the OpenAI Gym, achieving better performance than ES algorithm.

Recent years have witnessed significant progress in solving challenging problems across various domains using deep reinforcement learning (RL). Despite the success, the weak robustness has risen as a big obstacle for applying existing RL algorithms into real problems. In this paper, we propose unified policy optimization (UPO), a sample-efficient shared policy framework that allows a policy to update itself by considering different gradients generated by different policy gradient (PG) methods. Specifically, we propose two algorithms called UPO-MAB and UPO-ES, to leverage these different gradients by adopting the idea of multi-arm bandit (MAB) and evolution strategies (ES), with the purpose of finding the gradient direction leading to more performance gain with less extra data cost. Extensive experiments show that our approach can lead to stronger robustness and better performance than baselines.

Shun Zheng, Wei Cao, Wei Xu, Jiang Bian. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Stock trend prediction, aiming at predicting future price trend of stocks, plays a key role in seeking maximized profit from the stock investment. Recent years have witnessed increasing efforts in applying machine learning techniques, especially deep learning, to pursue more promising stock prediction. While deep learning has given rise to significant improvement, human investors still retain the leading position due to their understanding on stock intrinsic properties, which can imply invaluable principles for stock prediction. In this paper, we propose to extract and explore stock intrinsic properties to enhance stock trend prediction. Fortunately, we discover that the repositories of investment behaviors within mutual fund portfolio data form up a gold mine to extract latent representations of stock properties, since such collective investment behaviors can reflect the professional fund managers' common beliefs on stock intrinsic properties. Powered by extracted stock properties, we further propose to model the dynamic market state and trend using stock representations so as to generate the dynamic correlation between the stock and the market, and then we aggregate such correlation with dynamic stock indicators to achieve more accurate stock prediction. Extensive experiments on real-world stock market data demonstrate the effectiveness of stock properties extracted from collective investment behaviors in the task of stock prediction.

Online prediction has become one of the most essential tasks in many real-world applications. Two main characteristics of typical online prediction tasks include tabular input space and online data generation. Specifically, tabular input space indicates the existence of both sparse categorical features and dense numerical ones, while online data generation implies continuous task-generated data with potentially dynamic distribution. Consequently, effective learning with tabular input space as well as fast adaption to online data generation become two vital challenges for obtaining the online prediction model. Although Gradient Boosting Decision Tree (GBDT) and Neural Network (NN) have been widely used in practice, either of them yields their own weaknesses. Particularly, GBDT can hardly be adapted to dynamic online data generation, and it tends to be ineffective when facing sparse categorical features; NN, on the other hand, is quite difficult to achieve satisfactory performance when facing dense numerical features. In this paper, we propose a new learning framework, DeepGBM, which integrates the advantages of the both NN and GBDT by using two corresponding NN components: (1) CatNN, focusing on handling sparse categorical features. (2) GBDT2NN, focusing on dense numerical features with distilled knowledge from GBDT. Powered by these two components, DeepGBM can leverage both categorical and numerical features while retaining the ability of efficient online update. Comprehensive experiments on a variety of publicly available datasets have demonstrated that DeepGBM can outperform other well-recognized baselines in various online prediction tasks.

As one of the most important investing approaches, technical analysis attempts to forecast stock movement by interpreting the inner rules from historic price and volume data. To address the vital noisy nature of financial market, generic technical analysis develops technical trading indicators, as mathematical summarization of historic price and volume data, to form up the foundation for robust and profitable investment strategies. However, an observation reveals that stocks with different properties have different affinities over technical indicators, which discloses a big challenge for the indicator-oriented stock selection and investment. To address this problem, in this paper, we design a Technical Trading Indicator Optimization(TTIO) framework that manages to optimize the original technical indicator by leveraging stock-wise properties. To obtain effective representations of stock properties, we propose a Skip-gram architecture to learn stock embedding inspired by a valuable knowledge repository formed by fund manager's collective investment behaviors. Based on the learned stock representations, TTIO further learns a re-scaling network to optimize the indicator's performance. Extensive experiments on real-world stock market data demonstrate that our method can obtain the very stock representations that are invaluable for technical indicator optimization since the optimized indicators can result in strong investing signals than original ones.

Distributional Reinforcement Learning (RL) differs from traditional RL in that, rather than the expectation of total returns, it estimates distributions and has achieved state-of-the-art performance on Atari Games. The key challenge in practical distributional RL algorithms lies in how to parameterize estimated distributions so as to better approximate the true continuous distribution. Existing distributional RL algorithms parameterize either the probability side or the return value side of the distribution function, leaving the other side uniformly fixed as in C51, QR-DQN or randomly sampled as in IQN. In this paper, we propose fully parameterized quantile function that parameterizes both the quantile fraction axis (i.e., the x-axis) and the value axis (i.e., y-axis) for distributional RL. Our algorithm contains a fraction proposal network that generates a discrete set of quantile fractions and a quantile value network that gives corresponding quantile values. The two networks are jointly trained to find the best approximation of the true distribution. Experiments on 55 Atari Games show that our algorithm significantly outperforms existing distributional RL algorithms and creates a new record for the Atari Learning Environment for non-distributed agents.

Neural machine translation (NMT) heavily relies on parallel bilingual corpora for training. Since large-scale, high-quality parallel corpora are usually costly to collect, it is appealing to exploit monolingual corpora to improve NMT. Inspired by the law of total probability, which connects the probability of a given target-side monolingual sentence to the conditional probability of translating from a source sentence to the target one, we propose to explicitly exploit this connection and help the training procedure of NMT models using monolingual data. The key technical challenge of this approach is that there are exponentially many source sentences for a target monolingual sentence while computing the sum of the conditional probability given each possible source sentence. We address this challenge by leveraging the reverse translation model (target-to-source translation model) to sample several mostly likely source-side sentences and avoid enumerating all possible candidate source sentences. Then we propose two different methods to leverage the law of total probability, including marginal distribution regularization and likelihood maximization of monolingual corpora. Experiment results on English-French and German-English tasks demonstrate that our methods achieve significant improvement over several strong baselines.

Neural machine translation (NMT) heavily relies on parallel bilingual data for training. Since large-scale, high-quality parallel corpora are usually costly to collect, it is appealing to exploit monolingual corpora to improve NMT. Inspired by the law of total probability, which connects the probability of a given target-side monolingual sentence to the conditional probability of translating from a source sentence to the target one, we propose to explicitly exploit this connection to learn from and regularize the training of NMT models using monolingual data. The key technical challenge of this approach is that there are exponentially many source sentences for a target monolingual sentence while computing the sum of the conditional probability given each possible source sentence. We address this challenge by leveraging the dual translation model (target-to-source translation) to sample several mostly likely source-side sentences and avoid enumerating all possible candidate source sentences. That is, we transfer the knowledge contained in the dual model to boost the training of the primal model (source-to-target translation), and we call such an approach dual transfer learning. Experiment results on English-French and German-English tasks demonstrate that dual transfer learning achieves significant improvement over several strong baselines and obtains new state-of-the-art results.

Stock trading is a popular investment approach in real world. However, since lacking enough domain knowledge and experience, it is very difficult for common investors to analyze thousands of stocks manually. Algorithmic investment provides another rational way to formulate human knowledge as a trading agent. However, it still requires well-built knowledge and experience to design effective trading algorithms in such a volatile market. Fortunately, various kinds of historical trading records are easy to obtain in this big-data era, it is invaluable of us to extract the trading knowledge hidden in the data to help people make better decisions. In this paper, we propose a reinforcement learning driven Investor-Imitator framework to formalize the trading knowledge, by imitating an investor's behavior with a set of logic descriptors. In particular, to instantiate specific logic descriptors, we introduce the Rank-Invest model that can keep the diversity of logic descriptors by learning to optimize different evaluation metrics. In the experiment, we first simulate three types of investors, representing different degrees of information disclosure we may meet in real market. By learning towards these investors, we can tell the inherent trading logic of the target investor with the Investor-Imitator empirically, and the extracted interpretable knowledge can help us better understand and construct trading portfolios. Experimental results in this paper sufficiently demonstrate the designed purpose of Investor-Imitator, it makes the Investor-Imitator an applicable and meaningful intelligent trading framework in financial investment research.

Stock trend prediction plays a critical role in seeking maximized profit from the stock investment. However, precise trend prediction is very difficult since the highly volatile and non-stationary nature of the stock market. Exploding information on the Internet together with the advancing development of natural language processing and text mining techniques have enabled investors to unveil market trends and volatility from online content. Unfortunately, the quality, trustworthiness, and comprehensiveness of online content related to stock market vary drastically, and a large portion consists of the low-quality news, comments, or even rumors. To address this challenge, we imitate the learning process of human beings facing such chaotic online news, driven by three principles: sequential content dependency, diverse influence, and effective and efficient learning. In this paper, to capture the first two principles, we designed a Hybrid Attention Networks(HAN) to predict the stock trend based on the sequence of recent related news. Moreover, we apply the self-paced learning mechanism to imitate the third principle. Extensive experiments on real-world stock market data demonstrate the effectiveness of our framework. A further simulation illustrates that a straightforward trading strategy based on our proposed framework can significantly increase the annualized return.

Many supervised learning tasks are emerged in dual forms, e.g., English-to-French translation vs. French-to-English translation, speech recognition vs. text to speech, and image classification vs. image generation. Two dual tasks have intrinsic connections with each other due to the probabilistic correlation between their models. This connection is, however, not effectively utilized today, since people usually train the models of two dual tasks separately and independently. In this work, we propose training the models of two dual tasks simultaneously, and explicitly exploiting the probabilistic correlation between them to regularize the training process. For ease of reference, we call the proposed approach dual supervised learning. We demonstrate that dual supervised learning can improve the practical performances of both tasks, for various applications including machine translation, image processing, and sentiment analysis.

Recent years have witnessed the rapid development of machine learning in solving artificial intelligence (AI) tasks in many domains, including translation, speech, image, etc. Within these domains, AI tasks are usually not independent. As a specific type of relationship, structural duality does exist between many pairs of AI tasks, such as translation from one language to another vs. its opposite direction, speech recognition vs. speech synthetization, image classification vs. image generation, etc. The importance of such duality has been magnified by some recent studies, which revealed that it can boost the learning of two tasks in the dual form. However, there has been little investigation on how to leverage this invaluable relationship into the inference stage of AI tasks. In this paper, we propose a general framework of dual inference which can take advantage of both existing models from two dual tasks, without re-training, to conduct inference for one individual task. Empirical studies on three pairs of specific dual tasks, including machine translation, sentiment analysis, and image processing have illustrated that dual inference can significantly improve the performance of each of individual tasks.

Verbal comprehension questions appear very frequently in Intelligence Quotient (IQ) tests, which measure human's verbal ability including the understanding of the words with multiple senses, the synonyms and antonyms, and the analogies among words.In this work, we explore whether such tests can be solved automatically by the deep learning technologies for text data.We found that the task was quite challenging, and simply applying existing technologies like word embedding could not achieve a good performance, due to the multiple senses of words and the complex relations among words.To tackle these challenges, we propose a novel framework to automatically solve the verbal IQ questions by leveraging improved word embedding by jointly considering the multi-sense nature of words and the relational information among words.Experimental results have shown that the proposed framework can not only outperform existing methods for solving verbal comprehension questions but also exceed the average performance of the Amazon Mechanical Turk workers involved in the study.

In recent years, deep learning has been a very hot topic in the machine learning community. It has brought break-through results in image classification and speech recognition. Most recently, researchers have also got many promising results in natural language processing using deep learning techniques. As machine learning techniques are widely used in the Web search and data mining applications, many researchers and practitioners are studying the possibility of applying the recently-developed deep learning techniques into these applications. Some of them have made very promising progress, and thus it is a good time to hold a workshop to discuss and share the problems and progress in using deep learning techniques to improve Web search and data mining tasks.

Learning to rank arises in many data mining applications, ranging from web search engine, online advertising to recommendation system. In learning to rank, the performance of a ranking model is strongly affected by the number of labeled examples in the training set; on the other hand, obtaining labeled examples for training data is very expensive and time-consuming. This presents a great need for the active learning approaches to select most informative examples for ranking learning; however, in the literature there is still very limited work to address active learning for ranking. In this paper, we propose a general active learning framework, expected loss optimization (ELO), for ranking. The ELO framework is applicable to a wide range of ranking functions. Under this framework, we derive a novel algorithm, expected discounted cumulative gain (DCG) loss optimization (ELO-DCG), to select most informative examples. Then, we investigate both query and document level active learning for raking and propose a two-stage ELO-DCG algorithm which incorporate both query and document selection into active learning. Furthermore, we show that it is flexible for the algorithm to deal with the skewed grade distribution problem with the modification of the loss function. Extensive experiments on real-world web search data sets have demonstrated great potential and effectiveness of the proposed framework and algorithms.

The Earth Mover’s Distance (EMD) is a well-known distance metric for data represented as probability distributions over a predefined feature space. Supporting EMD-based similarity search has attracted intensive research effort. Despite the plethora of literature, most existing solutions are optimized for$L^p$feature spaces (e.g., Euclidean space); while in a spectrum of applications, the relationships between features are better captured using networks. In this paper, we study the problem of answering$k$-nearest neighbor ($k$-NN) queries under network-based EMD metrics (NEMD). We proposeOasis, a new access method which leverages the network structure of feature space and enables efficient NEMD-based similarity search. Specifically,Oasisemploys three novel techniques: (i)Range Oracle, a scalable model to estimate the range of$k$-th nearest neighbor under NEMD, (ii)Boundary Index, a structure that efficiently fetches candidates within given range, and (iii)Network Compression Hierarchy, an incremental filtering mechanism that effectively prunes false positive candidates to save unnecessary computation. Through extensive experiments using both synthetic and real data sets, we confirmed thatOasissignificantly outperforms the state-of-the-art methods in query processing cost.

Neural network techniques are widely applied to obtain high-quality distributed representations of words (i.e., word embeddings) to address text mining, information retrieval, and natural language processing tasks. Most recent efforts have proposed several efficient methods to learn word embeddings from context such that they can encode both semantic and syntactic relationships between words. However, it is quite challenging to handle unseen or rare words with insufficient context. Inspired by the study on the word recognition process in cognitive psychology, in this article, we propose to take advantage of seemingly less obvious but essentially important morphological knowledge to address these challenges. In particular, we introduce a novel neural network architecture called KNET that leverages both words’ contextual information and morphological knowledge to learn word embeddings. Meanwhile, this new learning architecture is also able to benefit from noisy knowledge and balance between contextual information and morphological knowledge. Experiments on an analogical reasoning task and a word similarity task both demonstrate that the proposed KNET framework can greatly enhance the effectiveness of word embeddings.

Click prediction is one of the fundamental problems in sponsored search. Most of existing studies took advantage of machine learning approaches to predict ad click for each event of ad view independently. However, as observed in the real-world sponsored search system, user's behaviors on ads yield high dependency on how the user behaved along with the past time, especially in terms of what queries she submitted, what ads she clicked or ignored, and how long she spent on the landing pages of clicked ads, etc. Inspired by these observations, we introduce a novel framework based on Recurrent Neural Networks (RNN). Compared to traditional methods, this framework directly models the dependency on user's sequential behaviors into the click prediction process through the recurrent structure in RNN. Large scale evaluations on the click-through logs from a commercial search engine demonstrate that our approach can significantly improve the click prediction accuracy, compared to sequence-independent approaches.

Representing words into vectors in continuous space can form up a potentially powerful basis to generate high-quality textual features for many text mining and natural language processing tasks. Some recent efforts, such as the skip-gram model, have attempted to learn word representations that can capture both syntactic and semantic information among text corpus. However, they still lack the capability of encoding the properties of words and the complex relationships among words very well, since text itself often contains incomplete and ambiguous information. Fortunately, knowledge graphs provide a golden mine for enhancing the quality of learned word representations. In particular, a knowledge graph, usually composed by entities (words, phrases, etc.), relations between entities, and some corresponding meta information, can supply invaluable relational knowledge that encodes the relationship between entities as well as categorical knowledge that encodes the attributes or properties of entities. Hence, in this paper, we introduce a novel framework called RC-NET to leverage both the relational and categorical knowledge to produce word representations of higher quality. Specifically, we build the relational knowledge and the categorical knowledge into two separate regularization functions, and combine both of them with the original objective function of the skip-gram model. By solving this combined optimization problem using back propagation neural networks, we can obtain word representations enhanced by the knowledge graph. Experiments on popular text mining and natural language processing tasks, including analogical reasoning, word similarity, and topic prediction, have all demonstrated that our model can significantly improve the quality of word representations.

Precise prediction of the probability that users click on ads plays a key role in sponsored search. State-of-the-art sponsored search systems typically employ a machine learning approach to conduct click prediction. While paying much attention to extracting useful features and building effective models, previous studies have overshadowed seemingly less obvious but essentially important challenges in terms of data sampling. To fulfill the learning objective of click prediction, it is not only necessary to ensure that the sampled training data implies the similar input distribution compared with the real world one, but also to guarantee that the sampled training data yield the consistent conditional output distribution, i.e. click-through rate (CTR), with the real world data. However, due to the sparseness of clicks in sponsored search, it is a bit contradictory to address these two challenges simultaneously. In this paper, we first take a theoretical analysis to reveal this sampling dilemma, followed by a thorough data analysis which demonstrates that the straightforward random sampling method may not be effective to balance these two kinds of consistency in sampling dilemma simultaneously. To address this problem, we propose a new sampling algorithm which can succeed in retaining the consistency between the sampled data and real world in terms of both input distribution and conditional output distribution. Large scale evaluations on the click-through logs from a commercial search engine demonstrate that this new sampling algorithm can effectively address the sampling dilemma. Further experiments illustrate that, by using the training data obtained by our new sampling algorithm, we can learn the model with much higher accuracy in click prediction.

Web portal services have become an important medium to deliver digital content (e.g. news, advertisements, etc.) to Web users in a timely fashion. To attract more users to various content modules on the Web portal, it is necessary to design a recommender system that can effectively achieve Web portal content optimization by automatically estimating content item attractiveness and relevance to user interests. The state-of-the-art online learning methodology adapts dedicated pointwise models to independently estimate the attractiveness score for each candidate content item. Although such pointwise models can be easily adapted for online recommendation, there still remain a few critical problems. First, this pointwise methodology fails to use invaluable user preferences between content items. Moreover, the performance of pointwise models decreases drastically when facing the problem of sparse learning samples. To address these problems, we propose exploring a new dynamic pairwise learning methodology for Web portal content optimization in which we exploit dynamic user preferences extracted based on users' actions on portal services to compute the attractiveness scores of content items. In this article, we introduce two specific pairwise learning algorithms, a straightforward graph-based algorithm and a formalized Bayesian modeling one. Experiments on large-scale data from a commercial Web portal demonstrate the significant improvement of pairwise methodologies over the baseline pointwise models. Further analysis illustrates that our new pairwise learning approaches can benefit personalized recommendation more than pointwise models, since the data sparsity is more critical for personalized content optimization.

Precise click prediction is one of the key components in the sponsored search system. Previous studies usually took advantage of two major kinds of information for click prediction, i.e., relevance information representing the similarity between ads and queries and historical click-through information representing users' previous preferences on the ads. These existing works mainly focused on interpreting ad clicks in terms of what users seek (i.e., relevance information) and how users choose to click (historically clicked-through information). However, few of them attempted to understand why users click the ads. In this paper, we aim at answering this ``why'' question. In our opinion, users click those ads that can convince them to take further actions, and the critical factor is if those ads can trigger users' desires in their hearts. Our data analysis on a commercial search engine reveals that specific text patterns, e.g., ``official site'', ``$x\%$ off'', and ``guaranteed return in $x$ days'', are very effective in triggering users' desires, and therefore lead to significant differences in terms of click-through rate (CTR). These observations motivate us to systematically model user psychological desire in order for a precise prediction on ad clicks. To this end, we propose modeling user psychological desire in sponsored search according to Maslow's desire theory, which categorizes psychological desire into five levels and each one is represented by a set of textual patterns automatically mined from ad texts. We then construct novel features for both ads and users based on our definition on psychological desire and incorporate them into the learning framework of click prediction. Large scale evaluations on the click-through logs from a commercial search engine demonstrate that this approach can result in significant improvement in terms of click prediction accuracy, for both the ads with rich historical data and those with rare one. Further analysis reveals that specific pattern combinations are especially effective in driving click-through rates, which provides a good guideline for advertisers to improve their ad textual descriptions.

Web portal services have become an important medium to deliver digital content and service, such as news, advertisements, and so on, to Web users in a timely fashion. To attract more users to various content modules on the Web portal, it is necessary to design a recommender system that can effectively achieve online content optimization by automatically estimating content items' attractiveness and relevance to users' interests. User interaction plays a vital role in building effective content optimization, as both implicit user feedbacks and explicit user ratings on the recommended items form the basis for designing and learning recommendation models. However, user actions on real-world Web portal services are likely to represent many implicit signals about users' interests and content attractiveness, which need more accurate interpretation to be fully leveraged in the recommendation models. To address this challenge, we investigate a couple of critical aspects of the online learning framework for personalized content optimization on Web portal services, and, in this paper, we propose deeper user action interpretation to enhance those critical aspects. In particular, we first propose an approach to leverage historical user activity to build behavior-driven user segmentation; then, we introduce an approach for interpreting users' actions from the factors of both user engagement and position bias to achieve unbiased estimation of content attractiveness. Our experiments on the large-scale data from a commercial Web recommender system demonstrate that recommendation models with our user action interpretation can reach significant improvement in terms of online content optimization over the baseline method. The effectiveness of our user action interpretation is also proved by the online test results on real user traffic.

With the rapid growth of E-Commerce on the Internet, online product search service has emerged as a popular and effective paradigm for customers to find desired products and select transactions. Most product search engines today are based on adaptations of relevance models devised for information retrieval. However, there is still a big gap between the mechanism of finding products that customers really desire to purchase and that of retrieving products of high relevance to customers' query. In this paper, we address this problem by proposing a new ranking framework for enhancing product search based on dynamic best-selling prediction in E-Commerce. Specifically, we first develop an effective algorithm to predict the dynamic best-selling, i.e. the volume of sales, for each product item based on its transaction history. By incorporating such best-selling prediction with relevance, we propose a new ranking model for product search, in which we rank higher the product items that are not only relevant to the customer's need but with higher probability to be purchased by the customer. Results of a large scale evaluation, conducted over the dataset from a commercial product search engine, demonstrate that our new ranking method is more effective for locating those product items that customers really desire to buy at higher rank positions without hurting the search relevance.

Local search service (e.g. Yelp, Yahoo! Local) has emerged as a popular and effective paradigm for a wide range of information needs for local businesses; it now provides a viable and even more effective alternative to general purpose web search for queries on local businesses. However, due to the diversity of information needs behind local search, it is necessary to use different information retrieval strategies for different query types in local search. In this paper, we explore a taxonomy of local search driven by users' information needs, which categorizes local search queries into three types: business category, chain business, and non-chain business. To decide which search strategy to use for each category in this taxonomy without placing the burden on the web users, it is indispensable to build an automatic local query classifier. However, since local search queries yield few online features and it is expensive to obtain editorial labels, it is insufficient to use only a supervised learning approach. In this paper, we address these problems by developing a semi-supervised approach for mining information needs from a vast amount of unlabeled data from local query logs to boost local query classification. Results of a large scale evaluation over queries from a commercial local search site illustrate that the proposed semi-supervised method allow us to accurately classify a substantially larger proportion of local queries than the supervised learning approach.

User interaction plays a vital role in recommender systems. Previous studies on algorithmic recommender systems have mainly focused on modeling techniques and feature development. Traditionally, implicit user feedback or explicit user ratings on the recommended items form the basis for designing and training of recommendation algorithms. But user interactions in real-world Web applications (e.g., a portal website with different recommendation modules in the interface) are unlikely to be as ideal as those assumed by previously proposed models. To address this problem, we build an online learning framework for personalized recommendation. We argue that appropriate user action interpretation is critical for a recommender system. The main contribution in this paper is an approach of interpreting users' actions for the online learning to achieve better item relevance estimation. Our experiments on the large-scale data from a commercial Web recommender system demonstrate significant improvement in terms of a precision metric over the baseline model that does not incorporate user action interpretation. The efficacy of this new algorithm is also proved by the online test results on real user traffic.

Mobile search is still in infancy compared with general purpose web search. With limited training data and weak relevance features, the ranking performance in mobile search is far from satisfactory. To address this problem, we propose to leverage the knowledge of Web search to enhance the ranking of mobile search. In this paper, we first develop an equivalent page conversion between web search and mobile search, then we design a few novel ranking features, generated from the click-through data in web search, for estimating the relevance of mobile search. Large scale evaluations demonstrate that the knowledge from web search is quite effective for boosting the relevance of ranking on mobile search.

In this paper, we proposed a novel divide-and-conquer approach to optimize the overall relevance in an unified framework for query clustering and query-based ranking. In our model, latent topics and specialized ranking models are learned iteratively so that an unified objective function, which lower-bounds the conditional probability of observed grades annotated by human editors on training data, is maximized. We conducted experiments comparing the proposed method with several baseline approaches on two data-sets. Experimental results illustrate that our method can significantly improve the ranking relevance over these baselines

Queries describe the users' search intent and therefore they play an essential role in the context of ranking for information retrieval and Web search. However, most of existing approaches for ranking do not explicitly take into consideration the fact that queries vary significantly along several dimensions and entail different treatments regarding the ranking models. In this paper, we propose to incorporate query difference into ranking by introducing query-dependent loss functions. In the context of Web search, query difference is usually represented as different query categories; and, queries are usually classified according to search intent such as navigational, informational and transactional queries. Based on the observation that such kind of query categorization has high correlation with the user's different expectation on the result accuracy on different rank positions, we develop position-sensitive query-dependent loss functions exploring such kind of query categorization. Beyond the simple learning method that builds ranking functions with pre-defined query categorization, we further propose a new method that learns both ranking functions and query categorization simultaneously. We apply the query-dependent loss functions to two particular ranking algorithms, RankNet and ListMLE. Experimental results demonstrate that query-dependent loss functions can be exploited to significantly improve the accuracy of learned ranking functions. We also show that the ranking function jointly learned with query categorization can achieve better performance than that learned with pre-defined query categorization. Finally, we provide analysis and conduct additional experiments to gain deeper understanding on the advantages of ranking with query-dependent loss functions over other query-dependent ranking approaches and query-independent approaches.

Many ranking algorithms applying machine learning techniques have been proposed in informational retrieval and Web search. However, most of existing approaches do not explicitly take into account the fact that queries vary significantly in terms of ranking and entail different treatments regarding the ranking models. In this paper, we apply a divide-and-conquer framework for ranking specialization, i.e. learning multiple ranking models by addressing query difference. We first generate query representation by aggregating ranking features through pseudo feedbacks, and employ unsupervised clustering methods to identify a set of ranking-sensitive query topics based on training queries. To learn multiple ranking models for respective ranking-sensitive query topics, we define a global loss function by combining the ranking risks of all query topics, and we propose a unified SVM-based learning process to minimize the global loss. Moreover, we employ an ensemble approach to generate the ranking result for each test query by applying a set of ranking models of the most appropriate query topics. We conduct experiments using a benchmark dataset for learning ranking functions as well as a dataset from a commercial search engine. Experimental results show that our proposed approach can significantly improve the ranking performance over existing single-model approaches as well as straightforward local ranking approaches, and the automatically identified ranking-sensitive topics are more useful for enhancing ranking performance than pre-defined query categorization.

Community Question Answering (CQA) has emerged as a popular forum for users to pose questions for other users to answer. Over the last few years, CQA portals such as Naver and Yahoo! Answers have exploded in popularity, and now provide a viable alternative to general purpose Web search. At the same time, the answers to past questions submitted in CQA sites comprise a valuable knowledge repository which could be a gold mine for information retrieval and automatic question answering. Unfortunately, the quality of the submitted questions and answers varies widely- increasingly so that a large fraction of the content is not usable for answering queries. Previous approaches for retrieving relevant and high quality content have been proposed, but they require large amounts of manually labeled data – which

Question Answering Communities such as Naver, Baidu Knows, and Yahoo! Answers have emerged as popular, and often effective, means of information seeking on the web. By posting questions for other participants to answer, information seekers can obtain specific answers to their questions. Users of CQA portals have already contributed millions of questions, and received hundreds of millions of answers from other participants. However, CQA is not always effective: in some cases, a user may obtain a perfect answer within minutes, and in others it may require hours—and sometimes days—until a satisfactory answer is contributed. We investigate the problem of predicting information seeker satisfaction in collaborative question answering communities, where we attempt to predict whether a question author will be satisfied with the answers submitted by the community participants. We present a general prediction model, and develop a variety of content, structure, and community-focused features for this task. Our experimental results, obtained from a large-scale evaluation over thousands of real questions and user ratings, demonstrate the feasibility of modeling and predicting asker satisfaction. We complement our results with a thorough investigation of the interactions and information seeking patterns in question answering communities that correlate with information seeker satisfaction. We also explore personalized models of asker satisfaction, and show that when sufficient interaction history exists, personalization can significantly improve prediction accuracy over a “one-size-fits-all” model. Our models and predictions could be useful for a variety of applications, such as user intent inference, answer ranking, interface design, and query suggestion and routing.

Question answering communities such as Naver and Yahoo! Answers have emerged as popular, and often effective, means of information seeking on the web. By posting questions for other participants to answer, information seekers can obtain specific answers to their questions. Users of popular portals such as Yahoo! Answers already have submitted millions of questions and received hundreds of millions of answers from other participants. However, it may also take hours --and sometime days-- until a satisfactory answer is posted. In this paper we introduce the problem of predicting information seeker satisfaction in collaborative question answering communities, where we attempt to predict whether a question author will be satisfied with the answers submitted by the community participants. We present a general prediction model, and develop a variety of content, structure, and community-focused features for this task. Our experimental results, obtained from a largescale evaluation over thousands of real questions and user ratings, demonstrate the feasibility of modeling and predicting asker satisfaction. We complement our results with a thorough investigation of the interactions and information seeking patterns in question answering communities that correlate with information seeker satisfaction. Our models and predictions could be useful for a variety of applications such as user intent inference, answer ranking, interface design, and query suggestion and routing.

Community Question Answering has emerged as a popular and effective paradigm for a wide range of information needs. For example, to find out an obscure piece of trivia, it is now possible and even very effective to post a question on a popular community QA site such as Yahoo! Answers, and to rely on other users to provide answers, often within minutes. The importance of such community QA sites is magnified as they create archives of millions of questions and hundreds of millions of answers, many of which are invaluable for the information needs of other searchers. However, to make this immense body of knowledge accessible, effective answer retrieval is required. In particular, as any user can contribute an answer to a question, the majority of the content reflects personal, often unsubstantiated opinions. A ranking that combines both relevance and quality is required to make such archives usable for factual information retrieval. This task is challenging, as the structure and the contents of community QA archives differ significantly from the web setting. To address this problem we present a general ranking framework for factual information retrieval from social media. Results of a large scale evaluation demonstrate that our method is highly effective at retrieving well-formed, factual answers to questions, as evaluated on a standard factoid QA benchmark. We also show that our learning framework can be tuned with the minimum of manual labeling. Finally, we provide result analysis to gain deeper understanding of which features are significant for social media search and retrieval. Our system can be used as a crucial building block for combining results from a variety of social media content with general web search results, and to better integrate social media content for effective information access.

Social annotation has gained increasing popularity in many Web-based applications, leading to an emerging research area in text analysis and information retrieval. This paper is concerned with developing probabilistic models and computational algorithms for social annotations. We propose a unified framework to combine the modeling of social annotations with the language modeling-based methods for information retrieval. The proposed approach consists of two steps: (1) discovering topics in the contents and annotations of documents while categorizing the users by domains; and (2) enhancing document and query language models by incorporating user domain interests as well as topical background models. In particular, we propose a new general generative model for social annotations, which is then simplified to a computationally tractable hierarchical Bayesian network. Then we apply smoothing techniques in a risk minimization framework to incorporate the topical information to language models. Experiments are carried out on a realworld annotation data set sampled from del.icio.us. Our results demonstrate significant improvements over traditional approaches.