Tong Zhao

Pengcheng Li, Qiang Fang, Tong Zhao et al.

Adversarial Imitation Learning (AIL) is a dominant framework in imitation learning that infers rewards from expert demonstrations to guide policy optimization. Although providing more expert demonstrations typically leads to improved performance and greater stability, collecting such demonstrations can be challenging in certain scenarios. Inspired by the success of diffusion models in data generation, we propose SD2AIL, which utilizes synthetic demonstrations via diffusion models. We first employ a diffusion model in the discriminator to generate synthetic demonstrations as pseudo-expert data that augment the expert demonstrations. To selectively replay the most valuable demonstrations from the large pool of (pseudo-) expert demonstrations, we further introduce a prioritized expert demonstration replay strategy (PEDR). The experimental results on simulation tasks demonstrate the effectiveness and robustness of our method. In particular, in the Hopper task, our method achieves an average return of 3441, surpassing the state-of-the-art method by 89. Our code will be available at https://github.com/positron-lpc/SD2AIL.

Donald Loveland, Xinyi Wu, Tong Zhao et al.

Collaborative Filtering (CF) methods dominate real-world recommender systems given their ability to learn high-quality, sparse ID-embedding tables that effectively capture user preferences. These tables scale linearly with the number of users and items, and are trained to ensure high similarity between embeddings of interacted user-item pairs, while maintaining low similarity for non-interacted pairs. Despite their high performance, encouraging dispersion for non-interacted pairs necessitates expensive regularization (e.g., negative sampling), hurting runtime and scalability. Existing research tends to address these challenges by simplifying the learning process, either by reducing model complexity or sampling data, trading performance for runtime. In this work, we move beyond model-level modifications and study the properties of the embedding tables under different learning strategies. Through theoretical analysis, we find that the singular values of the embedding tables are intrinsically linked to different CF loss functions. These findings are empirically validated on real-world datasets, demonstrating the practical benefits of higher stable rank, a continuous version of matrix rank which encodes the distribution of singular values. Based on these insights, we propose an efficient warm-start strategy that regularizes the stable rank of the user and item embeddings. We show that stable rank regularization during early training phases can promote higher-quality embeddings, resulting in training speed improvements of up to 66%. Additionally, stable rank regularization can act as a proxy for negative sampling, allowing for performance gains of up to 21% over loss functions with small negative sampling ratios. Overall, our analysis unifies current CF methods under a new perspective, their optimization of stable rank, motivating a flexible regularization method.

Changlin Wan, Wennan Chang, Tong Zhao et al.

Boolean tensor has been broadly utilized in representing high dimensional logical data collected on spatial, temporal and/or other relational domains. Boolean Tensor Decomposition (BTD) factorizes a binary tensor into the Boolean sum of multiple rank-1 tensors, which is an NP-hard problem. Existing BTD methods have been limited by their high computational cost, in applications to large scale or higher order tensors. In this work, we presented a computationally efficient BTD algorithm, namely \textit{Geometric Expansion for all-order Tensor Factorization} (GETF), that sequentially identifies the rank-1 basis components for a tensor from a geometric perspective. We conducted rigorous theoretical analysis on the validity as well as algorithemic efficiency of GETF in decomposing all-order tensor. Experiments on both synthetic and real-world data demonstrated that GETF has significantly improved performance in reconstruction accuracy, extraction of latent structures and it is an order of magnitude faster than other state-of-the-art methods.

Yang Zhou, Tong Zhao, Meng Jiang

Textual patterns (e.g., Country's president Person) are specified and/or generated for extracting factual information from unstructured data. Pattern-based information extraction methods have been recognized for their efficiency and transferability. However, not every pattern is reliable: A major challenge is to derive the most complete and accurate facts from diverse and sometimes conflicting extractions. In this work, we propose a probabilistic graphical model which formulates fact extraction in a generative process. It automatically infers true facts and pattern reliability without any supervision. It has two novel designs specially for temporal facts: (1) it models pattern reliability on two types of time signals, including temporal tag in text and text generation time; (2) it models commonsense constraints as observable variables. Experimental results demonstrate that our model significantly outperforms existing methods on extracting true temporal facts from news data.

Shenglin Zhao, Tong Zhao, Irwin King et al.

Point-of-interest (POI) recommendation is an important application in location-based social networks (LBSNs), which learns the user preference and mobility pattern from check-in sequences to recommend POIs. However, previous POI recommendation systems model check-in sequences based on either tensor factorization or Markov chain model, which cannot capture contextual check-in information in sequences. The contextual check-in information implies the complementary functions among POIs that compose an individual's daily check-in sequence. In this paper, we exploit the embedding learning technique to capture the contextual check-in information and further propose the \textit{\textbf{SE}}quential \textit{\textbf{E}}mbedding \textit{\textbf{R}}ank (\textit{SEER}) model for POI recommendation. In particular, the \textit{SEER} model learns user preferences via a pairwise ranking model under the sequential constraint modeled by the POI embedding learning method. Furthermore, we incorporate two important factors, i.e., temporal influence and geographical influence, into the \textit{SEER} model to enhance the POI recommendation system. Due to the temporal variance of sequences on different days, we propose a temporal POI embedding model and incorporate the temporal POI representations into a temporal preference ranking model to establish the \textit{T}emporal \textit{SEER} (\textit{T-SEER}) model. In addition, We incorporate the geographical influence into the \textit{T-SEER} model and develop the \textit{\textbf{Geo-Temporal}} \textit{\textbf{SEER}} (\textit{GT-SEER}) model.