Yanyan Lan

AAAI Conference 2026 Conference Paper

Learning Protein–Ligand Binding in Hyperbolic Space

• Jianhui Wang
• Wenyu Zhu
• Bowen Gao
• Xin Hong
• Ya-Qin Zhang
• Wei-Ying Ma
• Yanyan Lan

Protein-ligand binding prediction is central to virtual screening and affinity ranking, two fundamental tasks in drug discovery. While recent retrieval-based methods embed ligands and protein pockets into Euclidean space for similarity-based search, the geometry of Euclidean embeddings often fails to capture the hierarchical structure and fine-grained affinity variations intrinsic to molecular interactions. In this work, we propose HypSeek, a hyperbolic representation learning framework that embeds ligands, protein pockets, and sequences into Lorentz-model hyperbolic space. By leveraging the exponential geometry and negative curvature of hyperbolic space, HypSeek enables expressive, affinity-sensitive embeddings that can effectively model both global activity and subtle functional differences–particularly in challenging cases such as activity cliffs, where structurally similar ligands exhibit large affinity gaps. Our model unifies virtual screening and affinity ranking in a single framework, introducing a protein-guided three-tower architecture to enhance representational structure. HypSeek improves early enrichment in virtual screening on DUD-E from 42.63 to 51.44 (+20.7%) and affinity ranking correlation on JACS from 0.5774 to 0.7239 (+25.4%), demonstrating the benefits of hyperbolic geometry across both tasks and highlighting its potential as a powerful inductive bias for protein-ligand modeling.

AAAI Conference 2026 Conference Paper

S²Drug: Bridging Protein Sequence and 3D Structure in Contrastive Representation Learning for Virtual Screening

• Bowei He
• Bowen Gao
• Yankai Chen
• Yanyan Lan
• Chen Ma
• Philip S. Yu
• Ya-Qin Zhang
• Wei-Ying Ma

Virtual screening (VS) is an essential task in drug discovery, focusing on the identification of small-molecule ligands that bind to specific protein pockets. Existing deep learning methods, from early regression models to recent contrastive learning approaches, primarily rely on structural data while overlooking protein sequences, which are more accessible and can enhance generalizability. However, directly integrating protein sequences poses challenges due to the redundancy and noise in large-scale protein-ligand datasets. To address these limitations, we propose S²Drug, a two-stage framework that explicitly incorporates protein Sequence information and 3D Structure context in protein-ligand contrastive representation learning. In the first stage, we perform protein sequence pretraining on ChemBL using an ESM2-based backbone, combined with a tailored data sampling strategy to reduce redundancy and noise on both protein and ligand sides. In the second stage, we fine-tune on PDBBind by fusing sequence and structure information through a residue-level gating module, while introducing an auxiliary binding site prediction task. This auxiliary task guides the model to accurately localize binding residues within the protein sequence and capture their 3D spatial arrangement, thereby refining protein-ligand matching. Across multiple benchmarks, S²Drug consistently improves virtual screening performance and achieves strong results on binding site prediction, demonstrating the value of bridging sequence and structure in contrastive learning.

NeurIPS Conference 2025 Conference Paper

AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation

• Wenyu Zhu
• Jianhui Wang
• Bowen Gao
• Yinjun Jia
• Haichuan Tan
• Ya-Qin Zhang
• Wei-Ying Ma
• Yanyan Lan

Virtual screening (VS) is a critical component of modern drug discovery, yet most existing methods—whether physics-based or deep learning-based—are developed around holo protein structures with known ligand-bound pockets. Consequently, their performance degrades significantly on apo or predicted structures such as those from AlphaFold2, which are more representative of real-world early-stage drug discovery, where pocket information is often missing. In this paper, we introduce an alignment-and-aggregation framework to enable accurate virtual screening under structural uncertainty. Our method comprises two core components: (1) a tri-modal contrastive learning module that aligns representations of the ligand, the holo pocket, and cavities detected from structures, thereby enhancing robustness to pocket localization error; and (2) a cross-attention based adapter for dynamically aggregating candidate binding sites, enabling the model to learn from activity data even without precise pocket annotations. We evaluated our method on a newly curated benchmark of apo structures, where it significantly outperforms state-of-the-art methods in blind apo setting, improving the early enrichment factor (EF1\%) from 11. 75 to 37. 19. Notably, it also maintains strong performance on holo structures. These results demonstrate the promise of our approach in advancing first-in-class drug discovery, particularly in scenarios lacking experimentally resolved protein-ligand complexes. Our implementation is publicly available at https: //github. com/Wiley-Z/AANet.

NeurIPS Conference 2025 Conference Paper

CIDD: Collaborative Intelligence for Structure-Based Drug Design Empowered by LLMs

• Bowen Gao
• Yanwen Huang
• Yiqiao Liu
• Wenxuan Xie
• Bowei He
• Haichuan Tan
• Wei-Ying Ma
• Ya-Qin Zhang

Structure-guided molecular generation is pivotal in early-stage drug discovery, enabling the design of compounds tailored to specific protein targets. However, despite recent advances in 3D generative modeling, particularly in improving docking scores, these methods often produce rare and intrinsically irrational molecular structures that deviate from drug-like chemical space. To quantify this issue, we propose a novel metric, the Molecule Reasonable Ratio (MRR), which measures structural rationality and reveals a critical gap between existing models and real-world approved drugs. To address this, we introduce the Collaborative Intelligence Drug Design (CIDD) framework, the first approach to unify the 3D interaction modeling capabilities of generative models with the general knowledge and reasoning power of large language models (LLMs). By leveraging LLM-based Chain-of-Thought reasoning, CIDD generates molecules that not only bind effectively to protein pockets but also exhibit strong structural drug-likeness, rationality, and synthetic accessibility. On the CrossDocked2020 benchmark, CIDD consistently improves drug-likeness metrics, including QED, SA, and MRR, across different base generative models, while maintaining competitive binding affinity. Notably, it raises the combined success rate (balancing drug-likeness and binding) from 15. 72% to 34. 59%, more than doubling previous results. These findings demonstrate the value of integrating knowledge reasoning with geometric generation to advance AI-driven drug design.

NeurIPS Conference 2025 Conference Paper

CPSea: Large-scale cyclic peptide-protein complex dataset for machine learning in cyclic peptide design

• Ziyi Yang
• Hanyuan Xie
• Yinjun Jia
• Xiangzhe Kong
• Jiqing Zheng
• Ziting Zhang
• Yang Liu
• Lei Liu

Cyclic peptides exhibit better binding affinity and proteolytic stability compared to their linear counterparts. However, the development of cyclic peptide design models is hindered by the scarcity of data. To address this, we introduce **CPSea**(**C**yclic **P**eptide **Sea**), a dataset of 2. 71 million cyclic peptide-receptor complexes, curated through systematic mining of the AlphaFold Database (AFDB). Our pipeline extracts compact domains from AFDB, identifies cyclization sites using the $\beta$-carbon (C$_\beta$) distance thresholds, and applies multi-stage filtering to ensure structure fidelity and binding compatibility. Compared with experimental data of cyclic peptides, CPSea shows similar distributions in metrics on structure fidelity and wet-lab compatibility. To our knowledge, CPSea is the largest cyclic peptide-receptor dataset to date, enabling end-to-end model training for the first time. The dataset also showcases the feasibility of simulating inter-chain interactions using intra-chain interactions, expanding available resources for machine-learning models on protein-protein interactions. The dataset and relevant scripts are accessible on GitHub ([https: //github. com/YZY010418/CPSea](https: //github. com/YZY010418/CPSea)).

NeurIPS Conference 2025 Conference Paper

FIGRDock: Fast Interaction-Guided Regression for Flexible Docking

• Shikun Feng
• Bicheng Lin
• Yuanhuan Mo
• Yuyan Ni
• Wenyu Zhu
• Bowen Gao
• Wei-Ying Ma
• Haitao Li

Flexible docking, which predicts the binding conformations of both proteins and small molecules by modeling their structural flexibility, plays a vital role in structure-based drug design. Although recent generative approaches, particularly diffusion-based models, have shown promising results, they require iterative sampling to generate candidate structures and depend on separate scoring functions for pose selection. This leads to an inefficient pipeline that is difficult to scale in real-world drug discovery workflows. To overcome these challenges, we introduce FIGRDock, a fast and accurate flexible docking framework that understands complicated interactions between molecules and proteins with a regression-based approach. FIGRDock leverages initial docking poses from conventional tools to distill interaction-aware distance patterns, which serve as explicit structural conditions to directly guide the prediction of the final protein-ligand complex via a regression model. This one-shot inference paradigm enables rapid and precise pose prediction without reliance on multi-step sampling or external scoring stages. Experimental results show that FIGRDock achieves up to 100× faster inference than diffusion-based docking methods, while consistently surpassing them in accuracy across standard benchmarks. These results suggest that FIGRDock has the potential to offer a scalable and efficient solution for flexible docking, advancing the pace of structure-based drug discovery.

NeurIPS Conference 2025 Conference Paper

Manipulating 3D Molecules in a Fixed-Dimensional E(3)-Equivariant Latent Space

• Zitao Chen
• Yinjun Jia
• Zitong Tian
• Wei-Ying Ma
• Yanyan Lan

Medicinal chemists often optimize drugs considering their 3D structures and designing structurally distinct molecules that retain key features, such as shapes, pharmacophores, or chemical properties. Previous deep learning approaches address this through supervised tasks like molecule inpainting or property-guided optimization. In this work, we propose a flexible zero-shot molecule manipulation method by navigating in a shared latent space of 3D molecules. We introduce a Variational AutoEncoder (VAE) for 3D molecules, named MolFLAE, which learns a fixed-dimensional, E(3)-equivariant latent space independent of atom counts. MolFLAE encodes 3D molecules using an E(3)-equivariant neural network into fixed number of latent nodes, distinguished by learned embeddings. The latent space is regularized, and molecular structures are reconstructed via a Bayesian Flow Network (BFN) conditioned on the encoder’s latent output. MolFLAE achieves competitive performance on standard unconditional 3D molecule generation benchmarks. Moreover, the latent space of MolFLAE enables zero-shot molecule manipulation, including atom number editing, structure reconstruction, and coordinated latent interpolation for both structure and properties. We further demonstrate our approach on a drug optimization task for the human glucocorticoid receptor, generating molecules with improved hydrophilicity while preserving key interactions, under computational evaluations. These results highlight the flexibility, robustness, and real-world utility of our method, opening new avenues for molecule editing and optimization.

ICLR Conference 2025 Conference Paper

Redefining the task of Bioactivity Prediction

• Yanwen Huang
• Bowen Gao
• Yinjun Jia
• Hongbo Ma
• Wei-Ying Ma
• Ya-Qin Zhang
• Yanyan Lan

Small molecules are vital to modern medicine, and accurately predicting their bioactivity against protein targets is crucial for therapeutic discovery and development. However, current machine learning models often rely on spurious features, leading to biased outcomes. Notably, a simple pocket-only baseline can achieve results comparable to, and sometimes better than, more complex models that incorporate both the protein pockets and the small molecules. Our analysis reveals that this phenomenon arises from insufficient training data and an improper evaluation process, which is typically conducted at the pocket level rather than the small molecule level. To address these issues, we redefine the bioactivity prediction task by introducing the SIU dataset-a million-scale Structural small molecule-protein Interaction dataset for Unbiased bioactivity prediction task, which is 50 times larger than the widely used PDBbind. The bioactivity labels in SIU are derived from wet experiments and organized by label types, ensuring greater accuracy and comparability. The complexes in SIU are constructed using a majority vote from three commonly used docking software programs, enhancing their reliability. Additionally, the structure of SIU allows for multiple small molecules to be associated with each protein pocket, enabling the redefinition of evaluation metrics like Pearson and Spearman correlations across different small molecules targeting the same protein pocket. Experimental results demonstrate that this new task provides a more challenging and meaningful benchmark for training and evaluating bioactivity prediction models, ultimately offering a more robust assessment of model performance.

ICLR Conference 2025 Conference Paper

Reframing Structure-Based Drug Design Model Evaluation via Metrics Correlated to Practical Needs

• Bowen Gao
• Haichuan Tan
• Yanwen Huang
• Minsi Ren
• Xiao Huang
• Wei-Ying Ma
• Ya-Qin Zhang
• Yanyan Lan

Recent advances in structure-based drug design (SBDD) have produced surprising results, with models often generating molecules that achieve better Vina docking scores than actual ligands. However, these results are frequently overly optimistic due to the limitations of docking score accuracy and the challenges of wet-lab validation. While generated molecules may demonstrate high QED (drug-likeness) and SA (synthetic accessibility) scores, they often lack true drug-like properties or synthesizability. To address these limitations, we propose a model-level evaluation framework that emphasizes practical metrics aligned with real-world applications. Inspired by recent findings on the utility of generated molecules in ligand-based virtual screening, our framework evaluates SBDD models by their ability to produce molecules that effectively retrieve active compounds from chemical libraries via similarity-based searches. This approach provides a direct indication of therapeutic potential, bridging the gap between theoretical performance and real-world utility. Our experiments reveal that while SBDD models may excel in theoretical metrics like Vina scores, they often fall short in these practical metrics. By introducing this new evaluation strategy, we aim to enhance the relevance and impact of SBDD models for pharmaceutical research and development.

NeurIPS Conference 2025 Conference Paper

Straight-Line Diffusion Model for Efficient 3D Molecular Generation

• Yuyan Ni
• Shikun Feng
• Haohan Chi
• Bowen Zheng
• Huan-ang Gao
• Wei-Ying Ma
• Zhi-Ming Ma
• Yanyan Lan

Diffusion-based models have shown great promise in molecular generation but often require a large number of sampling steps to generate valid samples. In this paper, we introduce a novel Straight-Line Diffusion Model (SLDM) to tackle this problem, by formulating the diffusion process to follow a linear trajectory. The proposed process aligns well with the noise sensitivity characteristic of molecular structures and uniformly distributes reconstruction effort across the generative process, thus enhancing learning efficiency and efficacy. Consequently, SLDM achieves state-of-the-art performance on 3D molecule generation benchmarks, delivering a 100-fold improvement in sampling efficiency.

ICLR Conference 2025 Conference Paper

UniGEM: A Unified Approach to Generation and Property Prediction for Molecules

• Shikun Feng
• Yuyan Ni
• Yan Lu
• Zhiming Ma
• Wei-Ying Ma
• Yanyan Lan

Molecular generation and molecular property prediction are both crucial for drug discovery, but they are often developed independently. Inspired by recent studies, which demonstrate that diffusion model, a prominent generative approach, can learn meaningful data representations that enhance predictive tasks, we explore the potential for developing a unified generative model in the molecular domain that effectively addresses both molecular generation and property prediction tasks. However, the integration of these tasks is challenging due to inherent inconsistencies, making simple multi-task learning ineffective. To address this, we propose UniGEM, the first unified model to successfully integrate molecular generation and property prediction, delivering superior performance in both tasks. Our key innovation lies in a novel two-phase generative process, where predictive tasks are activated in the later stages, after the molecular scaffold is formed. We further enhance task balance through innovative training strategies. Rigorous theoretical analysis and comprehensive experiments demonstrate our significant improvements in both tasks. The principles behind UniGEM hold promise for broader applications, including natural language processing and computer vision.

ICLR Conference 2024 Conference Paper

Multimodal Molecular Pretraining via Modality Blending

• Qiying Yu
• Yudi Zhang 0008
• Yuyan Ni
• Shikun Feng
• Yanyan Lan
• Hao Zhou
• Jingjing Liu

Self-supervised learning has recently gained growing interest in molecular modeling for scientific tasks such as AI-assisted drug discovery. Current studies consider leveraging both 2D and 3D molecular structures for representation learning. However, relying on straightforward alignment strategies that treat each modality separately, these methods fail to exploit the intrinsic correlation between 2D and 3D representations that reflect the underlying structural characteristics of molecules, and only perform coarse-grained molecule-level alignment. To derive fine-grained alignment and promote structural molecule understanding, we introduce an atomic-relation level "blend-then-predict" self-supervised learning approach, MoleBLEND, which first blends atom relations represented by different modalities into one unified relation matrix for joint encoding, then recovers modality-specific information for 2D and 3D structures individually. By treating atom relationships as anchors, MoleBLEND organically aligns and integrates visually dissimilar 2D and 3D modalities of the same molecule at fine-grained atomic level, painting a more comprehensive depiction of each molecule. Extensive experiments show that MoleBLEND achieves state-of-the-art performance across major 2D/3D molecular benchmarks. We further provide theoretical insights from the perspective of mutual-information maximization, demonstrating that our method unifies contrastive, generative (cross-modality prediction) and mask-then-predict (single-modality prediction) objectives into one single cohesive framework.

ICLR Conference 2024 Conference Paper

Protein-ligand binding representation learning from fine-grained interactions

• Shikun Feng
• Minghao Li
• Yinjun Jia
• Wei-Ying Ma
• Yanyan Lan

The binding between proteins and ligands plays a crucial role in the realm of drug discovery. Previous deep learning approaches have shown promising results over traditional computationally intensive methods, but resulting in poor generalization due to limited supervised data. In this paper, we propose to learn protein-ligand binding representation in a self-supervised learning manner. Different from existing pre-training approaches which treat proteins and ligands individually, we emphasize to discern the intricate binding patterns from fine-grained interactions. Specifically, this self-supervised learning problem is formulated as a prediction of the conclusive binding complex structure given a pocket and ligand with a Transformer based interaction module, which naturally emulates the binding process. To ensure the representation of rich binding information, we introduce two pre-training tasks, i.e. atomic pairwise distance map prediction and mask ligand reconstruction, which comprehensively model the fine-grained interactions from both structure and feature space. Extensive experiments have demonstrated the superiority of our method across various binding tasks, including protein-ligand affinity prediction, virtual screening and protein-ligand docking.

ICML Conference 2024 Conference Paper

Rethinking Specificity in SBDD: Leveraging Delta Score and Energy-Guided Diffusion

• Bowen Gao
• Minsi Ren
• Yuyan Ni
• Yanwen Huang
• Bo Qiang
• Zhiming Ma
• Wei-Ying Ma
• Yanyan Lan

In the field of Structure-based Drug Design (SBDD), deep learning-based generative models have achieved outstanding performance in terms of docking score. However, further study shows that the existing molecular generative methods and docking scores both have lacked consideration in terms of specificity, which means that generated molecules bind to almost every protein pocket with high affinity. To address this, we introduce the Delta Score, a new metric for evaluating the specificity of molecular binding. To further incorporate this insight for generation, we develop an innovative energy-guided approach using contrastive learning, with active compounds as decoys, to direct generative models toward creating molecules with high specificity. Our empirical results show that this method not only enhances the delta score but also maintains or improves traditional docking scores, successfully bridging the gap between SBDD and real-world needs.

ICLR Conference 2024 Conference Paper

Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment

• Bowen Gao
• Yinjun Jia
• Yuanle Mo
• Yuyan Ni
• Wei-Ying Ma
• Zhiming Ma
• Yanyan Lan

Pocket representations play a vital role in various biomedical applications, such as druggability estimation, ligand affinity prediction, and de novo drug design. While existing geometric features and pretrained representations have demonstrated promising results, they usually treat pockets independent of ligands, neglecting the fundamental interactions between them. However, the limited pocket-ligand complex structures available in the PDB database (less than 100 thousand non-redundant pairs) hampers large-scale pretraining endeavors for interaction modeling. To address this constraint, we propose a novel pocket pretraining approach that leverages knowledge from high-resolution atomic protein structures, assisted by highly effective pretrained small molecule representations. By segmenting protein structures into drug-like fragments and their corresponding pockets, we obtain a reasonable simulation of ligand-receptor interactions, resulting in the generation of over 5 million complexes. Subsequently, the pocket encoder is trained in a contrastive manner to align with the representation of pseudo-ligand furnished by some pretrained small molecule encoders. Our method, named ProFSA, achieves state-of-the-art performance across various tasks, including pocket druggability prediction, pocket matching, and ligand binding affinity prediction. Notably, ProFSA surpasses other pretraining methods by a substantial margin. Moreover, our work opens up a new avenue for mitigating the scarcity of protein-ligand complex data through the utilization of high-quality and diverse protein structure databases.

ICLR Conference 2024 Conference Paper

Sliced Denoising: A Physics-Informed Molecular Pre-Training Method

• Yuyan Ni
• Shikun Feng
• Wei-Ying Ma
• Zhiming Ma
• Yanyan Lan

While molecular pre-training has shown great potential in enhancing drug discovery, the lack of a solid physical interpretation in current methods raises concerns about whether the learned representation truly captures the underlying explanatory factors in observed data, ultimately resulting in limited generalization and robustness. Although denoising methods offer a physical interpretation, their accuracy is often compromised by ad-hoc noise design, leading to inaccurate learned force fields. To address this limitation, this paper proposes a new method for molecular pre-training, called sliced denoising (SliDe), which is based on the classical mechanical intramolecular potential theory. SliDe utilizes a novel noise strategy that perturbs bond lengths, angles, and torsion angles to achieve better sampling over conformations. Additionally, it introduces a random slicing approach that circumvents the computationally expensive calculation of the Jacobian matrix, which is otherwise essential for estimating the force field. By aligning with physical principles, SliDe shows a 42\% improvement in the accuracy of estimated force fields compared to current state-of-the-art denoising methods, and thus outperforms traditional baselines on various molecular property prediction tasks.

ICML Conference 2024 Conference Paper

UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning

• Shikun Feng
• Yuyan Ni
• Minghao Li
• Yanwen Huang
• Zhiming Ma
• Wei-Ying Ma
• Yanyan Lan

Recently, a noticeable trend has emerged in developing pre-trained foundation models in the domains of CV and NLP. However, for molecular pre-training, there lacks a universal model capable of effectively applying to various categories of molecular tasks, since existing prevalent pre-training methods exhibit effectiveness for specific types of downstream tasks. Furthermore, the lack of profound understanding of existing pre-training methods, including 2D graph masking, 2D-3D contrastive learning, and 3D denoising, hampers the advancement of molecular foundation models. In this work, we provide a unified comprehension of existing pre-training methods through the lens of contrastive learning. Thus their distinctions lie in clustering different views of molecules, which is shown beneficial to specific downstream tasks. To achieve a complete and general-purpose molecular representation, we propose a novel pre-training framework, named UniCorn, that inherits the merits of the three methods, depicting molecular views in three different levels. SOTA performance across quantum, physicochemical, and biological tasks, along with comprehensive ablation study, validate the universality and effectiveness of UniCorn.

ICML Conference 2023 Conference Paper

Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D

• Bo Qiang
• Yuxuan Song
• Minkai Xu
• Jingjing Gong
• Bowen Gao
• Hao Zhou 0012
• Wei-Ying Ma
• Yanyan Lan

Generating desirable molecular structures in 3D is a fundamental problem for drug discovery. Despite the considerable progress we have achieved, existing methods usually generate molecules in atom resolution and ignore intrinsic local structures such as rings, which leads to poor quality in generated structures, especially when generating large molecules. Fragment-based molecule generation is a promising strategy, however, it is nontrivial to be adapted for 3D non-autoregressive generations because of the combinational optimization problems. In this paper, we utilize a coarse-to-fine strategy to tackle this problem, in which a Hierarchical Diffusion-based model (i. e. HierDiff) is proposed to preserve the validity of local segments without relying on autoregressive modeling. Specifically, HierDiff first generates coarse-grained molecule geometries via an equivariant diffusion process, where each coarse-grained node reflects a fragment in a molecule. Then the coarse-grained nodes are decoded into fine-grained fragments by a message-passing process and a newly designed iterative refined sampling module. Lastly, the fine-grained fragments are then assembled to derive a complete atomic molecular structure. Extensive experiments demonstrate that HierDiff consistently improves the quality of molecule generation over existing methods.

NeurIPS Conference 2023 Conference Paper

DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening

• Bowen Gao
• Bo Qiang
• Haichuan Tan
• Yinjun Jia
• Minsi Ren
• Minsi Lu
• Jingjing Liu
• Wei-Ying Ma

Virtual screening, which identifies potential drugs from vast compound databases to bind with a particular protein pocket, is a critical step in AI-assisted drug discovery. Traditional docking methods are highly time-consuming, and can only work with a restricted search library in real-life applications. Recent supervised learning approaches using scoring functions for binding-affinity prediction, although promising, have not yet surpassed docking methods due to their strong dependency on limited data with reliable binding-affinity labels. In this paper, we propose a novel contrastive learning framework, DrugCLIP, by reformulating virtual screening as a dense retrieval task and employing contrastive learning to align representations of binding protein pockets and molecules from a large quantity of pairwise data without explicit binding-affinity scores. We also introduce a biological-knowledge inspired data augmentation strategy to learn better protein-molecule representations. Extensive experiments show that DrugCLIP significantly outperforms traditional docking and supervised learning methods on diverse virtual screening benchmarks with highly reduced computation time, especially in zero-shot setting.

NeurIPS Conference 2023 Conference Paper

Equivariant Flow Matching with Hybrid Probability Transport for 3D Molecule Generation

• Yuxuan Song
• Jingjing Gong
• Minkai Xu
• Ziyao Cao
• Yanyan Lan
• Stefano Ermon
• Hao Zhou
• Wei-Ying Ma

The generation of 3D molecules requires simultaneously deciding the categorical features (atom types) and continuous features (atom coordinates). Deep generative models, especially Diffusion Models (DMs), have demonstrated effectiveness in generating feature-rich geometries. However, existing DMs typically suffer from unstable probability dynamics with inefficient sampling speed. In this paper, we introduce geometric flow matching, which enjoys the advantages of both equivariant modeling and stabilized probability dynamics. More specifically, we propose a hybrid probability path where the coordinates probability path is regularized by an equivariant optimal transport, and the information between different modalities is aligned. Experimentally, the proposed method could consistently achieve better performance on multiple molecule generation benchmarks with 4. 75$\times$ speed up of sampling on average.

ICML Conference 2023 Conference Paper

Fractional Denoising for 3D Molecular Pre-training

• Shikun Feng
• Yuyan Ni
• Yanyan Lan
• Zhiming Ma
• Wei-Ying Ma

Coordinate denoising is a promising 3D molecular pre-training method, which has achieved remarkable performance in various downstream drug discovery tasks. Theoretically, the objective is equivalent to learning the force field, which is revealed helpful for downstream tasks. Nevertheless, there are two challenges for coordinate denoising to learn an effective force field, i. e. low coverage samples and isotropic force field. The underlying reason is that molecular distributions assumed by existing denoising methods fail to capture the anisotropic characteristic of molecules. To tackle these challenges, we propose a novel hybrid noise strategy, including noises on both dihedral angel and coordinate. However, denoising such hybrid noise in a traditional way is no more equivalent to learning the force field. Through theoretical deductions, we find that the problem is caused by the dependency of the input conformation for covariance. To this end, we propose to decouple the two types of noise and design a novel fractional denoising method (Frad), which only denoises the latter coordinate part. In this way, Frad enjoys both the merits of sampling more low-energy structures and the force field equivalence. Extensive experiments show the effectiveness of Frad in molecule representation, with a new state-of-the-art on 9 out of 12 tasks of QM9 and on 7 out of 8 targets of MD17.

NeurIPS Conference 2022 Conference Paper

When Does Group Invariant Learning Survive Spurious Correlations?

• Yimeng Chen
• Ruibin Xiong
• Zhi-Ming Ma
• Yanyan Lan

By inferring latent groups in the training data, recent works introduce invariant learning to the case where environment annotations are unavailable. Typically, learning group invariance under a majority/minority split is empirically shown to be effective in improving out-of-distribution generalization on many datasets. However, theoretical guarantee for these methods on learning invariant mechanisms is lacking. In this paper, we reveal the insufficiency of existing group invariant learning methods in preventing classifiers from depending on spurious correlations in the training set. Specifically, we propose two criteria on judging such sufficiency. Theoretically and empirically, we show that existing methods can violate both criteria and thus fail in generalizing to spurious correlation shifts. Motivated by this, we design a new group invariant learning method, which constructs groups with statistical independence tests, and reweights samples by group label proportion to meet the criteria. Experiments on both synthetic and real data demonstrate that the new method significantly outperforms existing group invariant learning methods in generalizing to spurious correlation shifts.

AAAI Conference 2021 Conference Paper

Learning to Truncate Ranked Lists for Information Retrieval

• Chen Wu
• Ruqing Zhang
• Jiafeng Guo
• Yixing Fan
• Yanyan Lan
• Xueqi Cheng

Ranked list truncation is of critical importance in a variety of professional information retrieval applications such as patent search or legal search. The goal is to dynamically determine the number of returned documents according to some userdefined objectives, in order to reach a balance between the overall utility of the results and user efforts. Existing methods formulate this task as a sequential decision problem and take some pre-defined loss as a proxy objective, which suffers from the limitation of local decision and non-direct optimization. In this work, we propose a global decision based truncation model named AttnCut, which directly optimizes user-defined objectives for the ranked list truncation. Specifically, we take the successful transformer architecture to capture the global dependency within the ranked list for truncation decision, and employ the reward augmented maximum likelihood (RAML) for direct optimization. We consider two types of user-defined objectives which are of practical usage. One is the widely adopted metric such as F1 which acts as a balanced objective, and the other is the best F1 under some minimal recall constraint which represents a typical objective in professional search. Empirical results over the Robust04 and MQ2007 datasets demonstrate the effectiveness of our approach as compared with the state-of-the-art baselines.

AAAI Conference 2021 Conference Paper

Probing Product Description Generation via Posterior Distillation

• Haolan Zhan
• Hainan Zhang
• Hongshen Chen
• Lei Shen
• Zhuoye Ding
• Yongjun Bao
• Weipeng Yan
• Yanyan Lan

In product description generation (PDG), the user-cared aspect is critical for the recommendation system, which can not only improve user’s experiences but also obtain more clicks. High-quality customer reviews can be considered as an ideal source to mine user-cared aspects. However, in reality, a large number of new products (known as long-tailed commodities) cannot gather sufficient amount of customer reviews, which brings a big challenge in the product description generation task. Existing works tend to generate the product description solely based on item information, i. e. , product attributes or title words, which leads to tedious contents and cannot attract customers effectively. To tackle this problem, we propose an adaptive posterior network based on Transformer architecture that can utilize user-cared information from customer reviews. Specifically, we first extend the selfattentive Transformer encoder to encode product titles and attributes. Then, we apply an adaptive posterior distillation module to utilize useful review information, which integrates user-cared aspects to the generation process. Finally, we apply a Transformer-based decoding phase with copy mechanism to automatically generate the product description. Besides, we also collect a large-scare Chinese product description dataset to support our work and further research in this field. Experimental results show that our model is superior to traditional generative models in both automatic indicators and human evaluation.

AAAI Conference 2021 Conference Paper

Sketch and Customize: A Counterfactual Story Generator

• Changying Hao
• Liang Pang
• Yanyan Lan
• Yan Wang
• Jiafeng Guo
• Xueqi Cheng

Recent text generation models are easy to generate relevant and fluent text for the given text, while lack of causal reasoning ability when we change some parts of the given text. Counterfactual story rewriting is a recently proposed task to test the causal reasoning ability for text generation models, which requires a model to predict the corresponding story ending when the condition is modified to a counterfactual one. Previous works have shown that the traditional sequence-tosequence model cannot well handle this problem, as it often captures some spurious correlations between the original and counterfactual endings, instead of the causal relations between conditions and endings. To address this issue, we propose a sketch-and-customize generation model guided by the causality implicated in the conditions and endings. In the sketch stage, a skeleton is extracted by removing words which are conflict to the counterfactual condition, from the original ending. In the customize stage, a generation model is used to fill proper words in the skeleton under the guidance of the counterfactual condition. In this way, the obtained counterfactual ending is both relevant to the original ending and consistent with the counterfactual condition. Experimental results show that the proposed model generates much better endings, as compared with the traditional sequence-to-sequence model.

NeurIPS Conference 2021 Conference Paper

Uncertainty Calibration for Ensemble-Based Debiasing Methods

• Ruibin Xiong
• Yimeng Chen
• Liang Pang
• Xueqi Cheng
• Zhi-Ming Ma
• Yanyan Lan

Ensemble-based debiasing methods have been shown effective in mitigating the reliance of classifiers on specific dataset bias, by exploiting the output of a bias-only model to adjust the learning target. In this paper, we focus on the bias-only model in these ensemble-based methods, which plays an important role but has not gained much attention in the existing literature. Theoretically, we prove that the debiasing performance can be damaged by inaccurate uncertainty estimations of the bias-only model. Empirically, we show that existing bias-only models fall short in producing accurate uncertainty estimations. Motivated by these findings, we propose to conduct calibration on the bias-only model, thus achieving a three-stage ensemble-based debiasing framework, including bias modeling, model calibrating, and debiasing. Experimental results on NLI and fact verification tasks show that our proposed three-stage debiasing framework consistently outperforms the traditional two-stage one in out-of-distribution accuracy.

IJCAI Conference 2020 Conference Paper

Evaluating Natural Language Generation via Unbalanced Optimal Transport

• Yimeng Chen
• Yanyan Lan
• Ruinbin Xiong
• Liang Pang
• Zhiming Ma
• Xueqi Cheng

Embedding-based evaluation measures have shown promising improvements on the correlation with human judgments in natural language generation. In these measures, various intrinsic metrics are used in the computation, including generalized precision, recall, F-score and the earth mover's distance. However, the relations between these metrics are unclear, making it difficult to determine which measure to use in real applications. In this paper, we provide an in-depth study on the relations between these metrics. Inspired by the optimal transportation theory, we prove that these metrics correspond to the optimal transport problem with different hard marginal constraints. However, these hard marginal constraints may cause the problem of incomplete and noisy matching in the evaluation process. Therefore we propose a family of new evaluation metrics, namely Lazy Earth Mover's Distances, based on the more general unbalanced optimal transport problem. Experimental results on WMT18 and WMT19 show that our proposed metrics have the ability to produce more consistent evaluation results with human judgements, as compared with existing intrinsic metrics.

IJCAI Conference 2020 Conference Paper

Modeling Topical Relevance for Multi-Turn Dialogue Generation

• Hainan Zhang
• Yanyan Lan
• Liang Pang
• Hongshen Chen
• Zhuoye Ding
• Dawei Yin

Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly. However, existing models usually use word or sentence level similarities to detect the relevant contexts, which fail to well capture the topical level relevance. In this paper, we propose a new model, named STAR-BTM, to tackle this problem. Firstly, the Biterm Topic Model is pre-trained on the whole training dataset. Then, the topic level attention weights are computed based on the topic representation of each context. Finally, the attention weights and the topic distribution are utilized in the decoding process to generate the corresponding responses. Experimental results on both Chinese customer services data and English Ubuntu dialogue data show that STAR-BTM significantly outperforms several state-of-the-art methods, in terms of both metric-based and human evaluations.

ICML Conference 2020 Conference Paper

On Layer Normalization in the Transformer Architecture

• Ruibin Xiong
• Yunchang Yang
• Di He 0001
• Kai Zheng 0007
• Shuxin Zheng
• Chen Xing
• Huishuai Zhang
• Yanyan Lan

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow down the optimization and bring more hyper-parameter tunings. In this paper, we first study theoretically why the learning rate warm-up stage is essential and show that the location of layer normalization matters. Specifically, we prove with mean field theory that at initialization, for the original-designed Post-LN Transformer, which places the layer normalization between the residual blocks, the expected gradients of the parameters near the output layer are large. Therefore, using a large learning rate on those gradients makes the training unstable. The warm-up stage is practically helpful for avoiding this problem. On the other hand, our theory also shows that if the layer normalization is put inside the residual blocks (recently proposed as Pre-LN Transformer), the gradients are well-behaved at initialization. This motivates us to remove the warm-up stage for the training of Pre-LN Transformers. We show in our experiments that Pre-LN Transformers without the warm-up stage can reach comparable results with baselines while requiring significantly less training time and hyper-parameter tuning on a wide range of applications.

ICML Conference 2020 Conference Paper

On the Relation between Quality-Diversity Evaluation and Distribution-Fitting Goal in Text Generation

• Jianing Li
• Yanyan Lan
• Jiafeng Guo
• Xueqi Cheng

The goal of text generation models is to fit the underlying real probability distribution of text. For performance evaluation, quality and diversity metrics are usually applied. However, it is still not clear to what extend can the quality-diversity evaluation reflect the distribution-fitting goal. In this paper, we try to reveal such relation in a theoretical approach. We prove that under certain conditions, a linear combination of quality and diversity constitutes a divergence metric between the generated distribution and the real distribution. We also show that the commonly used BLEU/Self-BLEU metric pair fails to match any divergence metric, thus propose CR/NRR as a substitute for quality/diversity metric pair.

AAAI Conference 2020 Conference Paper

Structure Learning for Headline Generation

• Ruqing Zhang
• Jiafeng Guo
• Yixing Fan
• Yanyan Lan
• Xueqi Cheng

Headline generation is an important problem in natural language processing, which aims to describe a document by a compact and informative headline. Some recent successes on this task have been achieved by advanced graph-based neural models, which marry the representational power of deep neural networks with the structural modeling ability of the relational sentence graphs. The advantages of graph-based neural models over traditional Seq2Seq models lie in that they can encode long-distance relationship between sentences beyond the surface linear structure. However, since documents are typically weakly-structured data, modern graph-based neural models usually rely on manually designed rules or some heuristics to construct the sentence graph a prior. This may largely limit the power and increase the cost of the graphbased methods. In this paper, therefore, we propose to incorporate structure learning into the graph-based neural models for headline generation. That is, we want to automatically learn the sentence graph using a data-driven way, so that we can unveil the document structure flexibly without prior heuristics or rules. To achieve this goal, we employ a deep & wide network to encode rich relational information between sentences for the sentence graph learning. For the deep component, we leverage neural matching models, either representation-focused or interaction-focused model, to learn semantic similarity between sentences. For the wide component, we encode a variety of discourse relations between sentences. A Graph Convolutional Network (GCN) is then applied over the sentence graph to generate high-level relational representations for headline generation. The whole model could be optimized end-to-end so that the structure and representation could be learned jointly. Empirical studies show that our model can significantly outperform the stateof-the-art headline generation models.

AAAI Conference 2019 Short Paper

An Adaptive Framework for Conversational Question Answering

• Lixin Su
• Jiafeng Guo
• Yixing Fan
• Yanyan Lan
• Ruqing Zhang
• Xueqi Cheng

In Conversational Question Answering (CoQA), humans propose a series of questions to satisfy their information needs. Based on our preliminary analysis, there are two major types of questions, namely verification questions and knowledgeseeking questions. The first one is to verify some existing facts, while the latter is to obtain new knowledge about some specific object. These two types of questions differ significantly in their answering ways. However, existing methods usually treat them uniformly, which may easily be biased by the dominant type of questions and obtain inferior overall performance. In this work, we propose an adaptive framework to handle these two types of questions in different ways based on their own characteristics. We conduct experiments on the recently released CoQA benchmark dataset, and the results demonstrate that our method outperforms the state-of-the-art baseline methods.

AAAI Conference 2019 Conference Paper

Differentiated Distribution Recovery for Neural Text Generation

• Jianing Li
• Yanyan Lan
• Jiafeng Guo
• Jun Xu
• Xueqi Cheng

Neural language models based on recurrent neural networks (RNNLM) have significantly improved the performance for text generation, yet the quality of generated text represented by Turing Test pass rate is still far from satisfying. Some researchers propose to use adversarial training or reinforcement learning to promote the quality, however, such methods usually introduce great challenges in the training and parameter tuning processes. Through our analysis, we find the problem of RNNLM comes from the usage of maximum likelihood estimation (MLE) as the objective function, which requires the generated distribution to precisely recover the true distribution. Such requirement favors high generation diversity which restricted the generation quality. This is not suitable when the overall quality is low, since high generation diversity usually indicates lot of errors rather than diverse good samples. In this paper, we propose to achieve differentiated distribution recovery, DDR for short. The key idea is to make the optimal generation probability proportional to the β-th power of the true probability, where β > 1. In this way, the generation quality can be greatly improved by sacrificing diversity from noises and rare patterns. Experiments on synthetic data and two public text datasets show that our DDR method achieves more flexible quality-diversity trade-off and higher Turing Test pass rate, as compared with baseline methods including RNNLM, SeqGAN and LeakGAN.

AAAI Conference 2019 Conference Paper

HAS-QA: Hierarchical Answer Spans Model for Open-Domain Question Answering

• Liang Pang
• Yanyan Lan
• Jiafeng Guo
• Jun Xu
• Lixin Su
• Xueqi Cheng

This paper is concerned with open-domain question answering (i. e. , OpenQA). Recently, some works have viewed this problem as a reading comprehension (RC) task, and directly applied successful RC models to it. However, the performances of such models are not so good as that in the RC task. In our opinion, the perspective of RC ignores three characteristics in OpenQA task: 1) many paragraphs without the answer span are included in the data collection; 2) multiple answer spans may exist within one given paragraph; 3) the end position of an answer span is dependent with the start position. In this paper, we first propose a new probabilistic formulation of OpenQA, based on a three-level hierarchical structure, i. e. , the question level, the paragraph level and the answer span level. Then a Hierarchical Answer Spans Model (HAS- QA) is designed to capture each probability. HAS-QA has the ability to tackle the above three problems, and experiments on public OpenQA datasets show that it significantly outperforms traditional RC baselines and recent OpenQA baselines.

AAAI Conference 2019 Short Paper

Teaching Machines to Extract Main Content for Machine Reading Comprehension

• Zhaohui Li
• Yue Feng
• Jun Xu
• Jiafeng Guo
• Yanyan Lan
• Xueqi Cheng

Machine reading comprehension, whose goal is to find answers from the candidate passages for a given question, has attracted a lot of research efforts in recent years. One of the key challenge in machine reading comprehension is how to identify the main content from a large, redundant, and overlapping set of candidate sentences. In this paper we propose to tackle the challenge with Markov Decision Process in which the main content identification is formalized as sequential decision making and each action corresponds to selecting a sentence. Policy gradient is used to learn the model parameters. Experimental results based on MSMARCO showed that the proposed model, called MC-MDP, can select high quality main contents and significantly improved the performances of answer span prediction.

IJCAI Conference 2018 Conference Paper

A Question Type Driven Framework to Diversify Visual Question Generation

• Zhihao Fan
• Zhongyu Wei
• Piji Li
• Yanyan Lan
• Xuanjing Huang

Visual question generation aims at asking questions about an image automatically. Existing research works on this topic usually generate a single question for each given image without considering the issue of diversity. In this paper, we propose a question type driven framework to produce multiple questions for a given image with different focuses. In our framework, each question is constructed following the guidance of a sampled question type in a sequence-to-sequence fashion. To diversify the generated questions, a novel conditional variational auto-encoder is introduced to generate multiple questions with a specific question type. Moreover, we design a strategy to conduct the question type distribution learning for each image to select the final questions. Experimental results on three benchmark datasets show that our framework outperforms the state-of-the-art approaches in terms of both relevance and diversity.

AAAI Conference 2018 Short Paper

Fast Approximate Nearest Neighbor Search via k-Diverse Nearest Neighbor Graph

• Yan Xiao
• Jiafeng Guo
• Yanyan Lan
• Jun Xu
• Xueqi Cheng

Approximate nearest neighbor search is a fundamental problem and has been studied for a few decades. Recently graphbased indexing methods have demonstrated their great efficiency, whose main idea is to construct neighborhood graph offline and perform a greedy search starting from some sampled points of the graph online. Most existing graph-based methods focus on either the precise k-nearest neighbor (k- NN) graph which has good exploitation ability, or the diverse graph which has good exploration ability. In this paper, we propose the k-diverse nearest neighbor (k-DNN) graph, which balances the precision and diversity of the graph, leading to good exploitation and exploration abilities simultaneously. We introduce an efficient indexing algorithm for the construction of the k-DNN graph inspired by a well-known diverse ranking algorithm in information retrieval (IR). Experimental results show that our method can outperform both state-of-the-art precise graph and diverse graph methods.

IJCAI Conference 2018 Conference Paper

Reinforcing Coherence for Sequence to Sequence Model in Dialogue Generation

• Hainan Zhang
• Yanyan Lan
• Jiafeng Guo
• Jun Xu
• Xueqi Cheng

Sequence to sequence (Seq2Seq) approach has gained great attention in the field of single-turn dialogue generation. However, one serious problem is that most existing Seq2Seq based models tend to generate common responses lacking specific meanings. Our analysis show that the underlying reason is that Seq2Seq is equivalent to optimizing Kullback–Leibler (KL) divergence, thus does not penalize the case whose generated probability is high while the true probability is low. However, the true probability is unknown, which poses challenges for tackling this problem. Inspired by the fact that the coherence (i. e. similarity) between post and response is consistent with human evaluation, we hypothesize that the true probability of a response is proportional to the coherence degree. The coherence scores are then used as the reward function in a reinforcement learning framework to penalize the case whose generated probability is high while the true probability is low. Three different types of coherence models, including an unlearned similarity function, a pretrained semantic matching function, and an end-to-end dual learning architecture, are proposed in this paper. Experimental results on both Chinese Weibo dataset and English Subtitle dataset show that the proposed models produce more specific and meaningful responses, yielding better performances against Seq2Seq models in terms of both metric-based and human evaluations.

TIST Journal 2017 Journal Article

Directly Optimize Diversity Evaluation Measures

• Jun Xu
• Long Xia
• Yanyan Lan
• Jiafeng Guo
• Xueqi Cheng

The queries issued to search engines are often ambiguous or multifaceted, which requires search engines to return diverse results that can fulfill as many different information needs as possible; this is called search result diversification. Recently, the relational learning to rank model, which designs a learnable ranking function following the criterion of maximal marginal relevance, has shown effectiveness in search result diversification [Zhu et al. 2014]. The goodness of a diverse ranking model is usually evaluated with diversity evaluation measures such as α-NDCG [Clarke et al. 2008], ERR-IA [Chapelle et al. 2009], and D#-NDCG [Sakai and Song 2011]. Ideally the learning algorithm would train a ranking model that could directly optimize the diversity evaluation measures with respect to the training data. Existing relational learning to rank algorithms, however, only train the ranking models by optimizing loss functions that loosely relate to the evaluation measures. To deal with the problem, we propose a general framework for learning relational ranking models via directly optimizing any diversity evaluation measure. In learning, the loss function upper-bounding the basic loss function defined on a diverse ranking measure is minimized. We can derive new diverse ranking algorithms under the framework, and several diverse ranking algorithms are created based on different upper bounds over the basic loss function. We conducted comparisons between the proposed algorithms with conventional diverse ranking methods using the TREC benchmark datasets. Experimental results show that the algorithms derived under the diverse learning to rank framework always significantly outperform the state-of-the-art baselines.

AAAI Conference 2017 Conference Paper

Efficient Delivery Policy to Minimize User Traffic Consumption in Guaranteed Advertising

• Jia Zhang
• Zheng Wang
• Qian Li
• Jialin Zhang
• Yanyan Lan
• Qiang Li
• Xiaoming Sun

In this work, we study the guaranteed delivery model which is widely used in online advertising. In the guaranteed delivery scenario, ad exposures (which are also called impressions in some works) to users are guaranteed by contracts signed in advance between advertisers and publishers. A crucial problem for the advertising platform is how to fully utilize the valuable user traffic to generate as much as possible revenue. Different from previous works which usually minimize the penalty of unsatisfied contracts and some other cost (e. g. representativeness), we propose the novel consumption minimization model, in which the primary objective is to minimize the user traffic consumed to satisfy all contracts. Under this model, we develop a near optimal method to deliver ads for users. The main advantage of our method lies in that it consumes nearly as least as possible user traffic to satisfy all contracts, therefore more contracts can be accepted to produce more revenue. It also enables the publishers to estimate how much user traffic is redundant or short so that they can sell or buy this part of traffic in bulk in the exchange market. Furthermore, it is robust with regard to priori knowledge of user type distribution. Finally, the simulation shows that our method outperforms the traditional state-of-the-art methods.

AAAI Conference 2016 Conference Paper

A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations

• Shengxian Wan
• Yanyan Lan
• Jiafeng Guo
• Jun Xu
• Liang Pang
• Xueqi Cheng

Matching natural language sentences is central for many applications such as information retrieval and question answering. Existing deep models rely on a single sentence representation or multiple granularity representations for matching. However, such methods cannot well capture the contextualized local information in the matching process. To tackle this problem, we present a new deep architecture to match two sentences with multiple positional sentence representations. Specifically, each positional sentence representation is a sentence representation at this position, generated by a bidirectional long short term memory (Bi-LSTM). The matching score is finally produced by aggregating interactions between these different positional sentence representations, through k-Max pooling and a multi-layer perceptron. Our model has several advantages: (1) By using Bi-LSTM, rich context of the whole sentence is leveraged to capture the contextualized local information in each positional sentence representation; (2) By matching with multiple positional sentence representations, it is flexible to aggregate different important contextualized local information in a sentence to support the matching; (3) Experiments on different tasks such as question answering and sentence completion demonstrate the superiority of our model.

AAAI Conference 2016 Conference Paper

Inside Out: Two Jointly Predictive Models for Word Representations and Phrase Representations

• Fei Sun
• Jiafeng Guo
• Yanyan Lan
• Jun Xu
• Xueqi Cheng

Distributional hypothesis lies in the root of most existing word representation models by inferring word meaning from its external contexts. However, distributional models cannot handle rare and morphologically complex words very well and fail to identify some fine-grained linguistic regularity as they are ignoring the word forms. On the contrary, morphology points out that words are built from some basic units, i. e. , morphemes. Therefore, the meaning and function of such rare words can be inferred from the words sharing the same morphemes, and many syntactic relations can be directly identified based on the word forms. However, the limitation of morphology is that it cannot infer the relationship between two words that do not share any morphemes. Considering the advantages and limitations of both approaches, we propose two novel models to build better word representations by modeling both external contexts and internal morphemes in a jointly predictive way, called BEING and SEING. These two models can also be extended to learn phrase representations according to the distributed morphology theory. We evaluate the proposed models on similarity tasks and analogy tasks. The results demonstrate that the proposed models can outperform state-of-the-art models significantly on both word and phrase representation learning.

IJCAI Conference 2016 Conference Paper

Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN

• Shengxian Wan
• Yanyan Lan
• Jun Xu
• Jiafeng Guo
• Liang Pang
• Xueqi Cheng

Semantic matching, which aims to determine the matching degree between two texts, is a fundamental problem for many NLP applications. Recently, deep learning approach has been applied to this problem and significant improvements have been achieved. In this paper, we propose to view the generation of the global interaction between two texts as a recursive process: i. e. ~the interaction of two texts at each position is a composition of the interactions between their prefixes as well as the word level interaction at the current position. Based on this idea, we propose a novel deep architecture, namely Match-SRNN, to model the recursive matching structure. Firstly, a tensor is constructed to capture the word level interactions. Then a spatial RNN is applied to integrate the local interactions recursively, with importance determined by four types of gates. Finally, the matching score is calculated based on the global interaction. We show that, after degenerated to the exact matching scenario, Match-SRNN can approximate the dynamic programming process of longest common subsequence. Thus, there exists a clear interpretation for Match-SRNN. Our experiments on two semantic matching tasks showed the effectiveness of Match-SRNN, and its ability of visualizing the learned matching structure.

AAAI Conference 2016 Conference Paper

SPAN: Understanding a Question with Its Support Answers

• Liang Pang
• Yanyan Lan
• Jiafeng Guo
• Jun Xu
• Xueqi Cheng

Matching a question to its best answer is a common task in community question answering. In this paper, we focus on the non-factoid questions and aim to pick out the best answer from its candidate answers. Most of the existing deep models directly measure the similarity between question and answer by their individual sentence embeddings. In order to tackle the problem of the information lack in question’s descriptions and the lexical gap between questions and answers, we propose a novel deep architecture namely SPAN in this paper. Specifically we introduce support answers to help understand the question, which are defined as the best answers of those similar questions to the original one. Then we can obtain two kinds of similarities, one is between question and the candidate answer, and the other one is between support answers and the candidate answer. The matching score is finally generated by combining them. Experiments on Yahoo! Answers demonstrate that SPAN can outperform the baseline models.

AAAI Conference 2016 Conference Paper

Text Matching as Image Recognition

• Liang Pang
• Yanyan Lan
• Jiafeng Guo
• Jun Xu
• Shengxian Wan
• Xueqi Cheng

Matching two texts is a fundamental problem in many natural language processing tasks. An effective way is to extract meaningful matching patterns from words, phrases, and sentences to produce the matching score. Inspired by the success of convolutional neural network in image recognition, where neurons can capture many complicated patterns based on the extracted elementary visual patterns such as oriented edges and corners, we propose to model text matching as the problem of image recognition. Firstly, a matching matrix whose entries represent the similarities between words is constructed and viewed as an image. Then a convolutional neural network is utilized to capture rich matching patterns in a layer-by-layer way. We show that by resembling the compositional hierarchies of patterns in image recognition, our model can successfully identify salient signals such as n-gram and n-term matchings. Experimental results demonstrate its superiority against the baselines.

AAAI Conference 2015 Conference Paper

A Probabilistic Model for Bursty Topic Discovery in Microblogs

• Xiaohui Yan
• Jiafeng Guo
• Yanyan Lan
• Jun Xu
• Xueqi Cheng

Bursty topics discovery in microblogs is important for people to grasp essential and valuable information. However, the task is challenging since microblog posts are particularly short and noisy. This work develops a novel probabilistic model, namely Bursty Biterm Topic Model (BBTM), to deal with the task. BBTM extends the Biterm Topic Model (BTM) by incorporating the burstiness of biterms as prior knowledge for bursty topic modeling, which enjoys the following merits: 1) It can well solve the data sparsity problem in topic modeling over short texts as the same as BTM; 2) It can automatical discover high quality bursty topics in microblogs in a principled and efficient way. Extensive experiments on a standard Twitter dataset show that our approach outperforms the state-of-the-art baselines significantly.

UAI Conference 2014 Conference Paper

Position-Aware ListMLE: A Sequential Learning Process for Ranking

• Yanyan Lan
• Yadong Zhu
• Jiafeng Guo
• Shuzi Niu
• Xueqi Cheng

ListMLE is a state-of-the-art listwise learning-torank algorithm, which has been shown to work very well in application. It defines the probability distribution based on Plackett-Luce Model in a top-down style to take into account the position information. However, both empirical contradiction and theoretical results indicate that ListM- LE cannot well capture the position importance, which is a key factor in ranking. To amend the problem, this paper proposes a new listwise ranking method, called position-aware ListMLE (p- ListMLE for short). It views the ranking problem as a sequential learning process, with each step learning a subset of parameters which maximize the corresponding stepwise probability distribution. To solve this sequential multi-objective optimization problem, we propose to use linear scalarization strategy to transform it into a single-objective optimization problem, which is efficient for computation. Our theoretical study shows that p-ListMLE is better than ListM- LE in statistical consistency with respect to typical ranking evaluation measure NDCG. Furthermore, our experiments on benchmark datasets demonstrate that the proposed method can significantly improve the performance of ListMLE and outperform state-of-the-art listwise learningto-rank algorithms as well.

UAI Conference 2013 Conference Paper

Stochastic Rank Aggregation

• Shuzi Niu
• Yanyan Lan
• Jiafeng Guo
• Xueqi Cheng

This paper addresses the problem of rank aggregation, which aims to find a consensus ranking among multiple ranking inputs. Traditional rank aggregation methods are deterministic, and can be categorized into explicit and implicit methods depending on whether rank information is explicitly or implicitly utilized. Surprisingly, experimental results on real data sets show that explicit rank aggregation methods would not work as well as implicit methods, although rank information is critical for the task. Our analysis indicates that the major reason might be the unreliable rank information from incomplete ranking inputs. To solve this problem, we propose to incorporate uncertainty into rank aggregation and tackle the problem in both unsupervised and supervised scenario. We call this novel framework stochastic rank aggregation (St. Agg for short). Specifically, we introduce a prior distribution on ranks, and transform the ranking functions or objectives in traditional explicit methods to their expectations over this distribution. Our experiments on benchmark data sets show that the proposed St. Agg outperforms the baselines in both unsupervised and supervised scenarios.

NeurIPS Conference 2012 Conference Paper

Statistical Consistency of Ranking Methods in A Rank-Differentiable Probability Space

• Yanyan Lan
• Jiafeng Guo
• Xueqi Cheng
• Tie-Yan Liu

This paper is concerned with the statistical consistency of ranking methods. Recently, it was proven that many commonly used pairwise ranking methods are inconsistent with the weighted pairwise disagreement loss (WPDL), which can be viewed as the true loss of ranking, even in a low-noise setting. This result is interesting but also surprising, given that the pairwise ranking methods have been shown very effective in practice. In this paper, we argue that the aforementioned result might not be conclusive, depending on what kind of assumptions are used. We give a new assumption that the labels of objects to rank lie in a rank-differentiable probability space (RDPS), and prove that the pairwise ranking methods become consistent with WPDL under this assumption. What is especially inspiring is that RDPS is actually not stronger than but similar to the low-noise setting. Our studies provide theoretical justifications of some empirical findings on pairwise ranking methods that are unexplained before, which bridge the gap between theory and applications.

ICML Conference 2009 Conference Paper

Generalization analysis of listwise learning-to-rank algorithms

• Yanyan Lan
• Tie-Yan Liu
• Zhiming Ma
• Hang Li 0001

This paper presents a theoretical framework for ranking, and demonstrates how to perform generalization analysis of listwise ranking algorithms using the framework. Many learning-to-rank algorithms have been proposed in recent years. Among them, the listwise approach has shown higher empirical ranking performance when compared to the other approaches. However, there is no theoretical study on the listwise approach as far as we know. In this paper, we propose a theoretical framework for ranking, which can naturally describe various listwise learning-to-rank algorithms. With this framework, we prove a theorem which gives a generalization bound of a listwise ranking algorithm, on the basis of Rademacher Average of the class of compound functions. The compound functions take listwise loss functions as outer functions and ranking models as inner functions. We then compute the Rademacher Averages for existing listwise algorithms of ListMLE, ListNet, and RankCosine. We also discuss the tightness of the bounds in different situations with regard to the list length and transformation function.

NeurIPS Conference 2009 Conference Paper

Ranking Measures and Loss Functions in Learning to Rank

• Wei Chen
• Tie-Yan Liu
• Yanyan Lan
• Zhi-Ming Ma
• Hang Li

Learning to rank has become an important research topic in machine learning. While most learning-to-rank methods learn the ranking function by minimizing the loss functions, it is the ranking measures (such as NDCG and MAP) that are used to evaluate the performance of the learned ranking function. In this work, we reveal the relationship between ranking measures and loss functions in learning-to-rank methods, such as Ranking SVM, RankBoost, RankNet, and ListMLE. We show that these loss functions are upper bounds of the measure-based ranking errors. As a result, the minimization of these loss functions will lead to the maximization of the ranking measures. The key to obtaining this result is to model ranking as a sequence of classification tasks, and define a so-called essential loss as the weighted sum of the classification errors of individual tasks in the sequence. We have proved that the essential loss is both an upper bound of the measure-based ranking errors, and a lower bound of the loss functions in the aforementioned methods. Our proof technique also suggests a way to modify existing loss functions to make them tighter bounds of the measure-based ranking errors. Experimental results on benchmark datasets show that the modifications can lead to better ranking performance, demonstrating the correctness of our analysis.

ICML Conference 2008 Conference Paper

Query-level stability and generalization in learning to rank

• Yanyan Lan
• Tie-Yan Liu
• Tao Qin 0001
• Zhiming Ma
• Hang Li 0001