Source author record

Zengfeng Huang

Zengfeng Huang appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Machine Learning Artificial Intelligence Data Structures and Algorithms Cryptography and Security Databases eess.IV Information Theory math.IT physics.optics

Catalog footprint

What is connected

14works

9topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

DiRL: An Efficient Post-Training Framework for Diffusion Language Models

Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models. While recent efforts have validated their pre-training potential and accelerated inference speeds, the post-training landscape for dLLMs remains underdeveloped. Existing methods suffer from computational inefficiency and objective mismatches between training and inference, severely limiting performance on complex reasoning tasks such as mathematics. To address this, we introduce DiRL, an efficient post-training framework that tightly integrates FlexAttention-accelerated blockwise training with LMDeploy-optimized inference. This architecture enables a streamlined online model update loop, facilitating efficient two-stage post-training (Supervised Fine-Tuning followed by Reinforcement Learning). Building on this framework, we propose DiPO, the first unbiased Group Relative Policy Optimization (GRPO) implementation tailored for dLLMs. We validate our approach by training DiRL-8B-Instruct on high-quality math data. Our model achieves state-of-the-art math performance among dLLMs and surpasses comparable models in the Qwen2.5 series on several benchmarks.

preprint2026arXiv

Re$^2$Math: Benchmarking Theorem Retrieval in Research-Level Mathematics

Large language models are increasingly capable at closed-world mathematical reasoning, but research assistance also requires source-grounded use of the literature. When a proof reaches a non-trivial step, a useful assistant should determine whether the needed tool (e.g., a lemma) already exists, identify a suitable scholarly source, and verify that its assumptions align with the current proof context. To rigorously evaluate such capabilities, we introduce Re$^2$Math, a benchmark for tool-grounded retrieval from partial mathematical proofs. Each instance is built from a candidate instrumental citation in the proof of a main theorem, with hierarchical context and an optional leakage-controlled anchor hint. We also make the task source-grounded yet citation-agnostic in that any admissible theorem sufficient for the proof transition is accepted. Evaluation uses a release-frozen retrieval artifact, ensuring reproducibility, while the benchmark itself supports automatic, continual expansion with newly constructed instances. On the current benchmark test set, the best fixed-judge ToolAcc reaches 7.0%, despite substantially higher rates of source grounding, indicating that current systems often retrieve valid statements but fail to establish their applicability to the local proof step. By decoupling citation recall, grounding, and proof-gap sufficiency, Re$^2$Math transforms literature-grounded mathematical tool use into a controlled diagnostic task.

preprint2022arXiv

BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation

Many representative graph neural networks, e.g., GPR-GNN and ChebNet, approximate graph convolutions with graph spectral filters. However, existing work either applies predefined filter weights or learns them without necessary constraints, which may lead to oversimplified or ill-posed filters. To overcome these issues, we propose BernNet, a novel graph neural network with theoretical support that provides a simple but effective scheme for designing and learning arbitrary graph spectral filters. In particular, for any filter over the normalized Laplacian spectrum of a graph, our BernNet estimates it by an order-$K$ Bernstein polynomial approximation and designs its spectral property by setting the coefficients of the Bernstein basis. Moreover, we can learn the coefficients (and the corresponding filter weights) based on observed graphs and their associated signals and thus achieve the BernNet specialized for the data. Our experiments demonstrate that BernNet can learn arbitrary spectral filters, including complicated band-rejection and comb filters, and it achieves superior performance in real-world graph modeling tasks. Code is available at https://github.com/ivam-he/BernNet.

preprint2022arXiv

BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction

Given the ubiquitous existence of graph-structured data, learning the representations of nodes for the downstream tasks ranging from node classification, link prediction to graph classification is of crucial importance. Regarding missing link inference of diverse networks, we revisit the link prediction techniques and identify the importance of both the structural and attribute information. However, the available techniques either heavily count on the network topology which is spurious in practice or cannot integrate graph topology and features properly. To bridge the gap, we propose a bicomponent structural and attribute learning framework (BSAL) that is designed to adaptively leverage information from topology and feature spaces. Specifically, BSAL constructs a semantic topology via the node attributes and then gets the embeddings regarding the semantic view, which provides a flexible and easy-to-implement solution to adaptively incorporate the information carried by the node attributes. Then the semantic embedding together with topology embedding is fused together using an attention mechanism for the final prediction. Extensive experiments show the superior performance of our proposal and it significantly outperforms baselines on diverse research benchmarks.

preprint2022arXiv

Compressive Sensing Approaches for Sparse Distribution Estimation Under Local Privacy

Recent years, local differential privacy (LDP) has been adopted by many web service providers like Google \cite{erlingsson2014rappor}, Apple \cite{apple2017privacy} and Microsoft \cite{bolin2017telemetry} to collect and analyse users' data privately. In this paper, we consider the problem of discrete distribution estimation under local differential privacy constraints. Distribution estimation is one of the most fundamental estimation problems, which is widely studied in both non-private and private settings. In the local model, private mechanisms with provably optimal sample complexity are known. However, they are optimal only in the worst-case sense; their sample complexity is proportional to the size of the entire universe, which could be huge in practice. In this paper, we consider sparse or approximately sparse (e.g.\ highly skewed) distribution, and show that the number of samples needed could be significantly reduced. This problem has been studied recently \cite{acharya2021estimating}, but they only consider strict sparse distributions and the high privacy regime. We propose new privatization mechanisms based on compressive sensing. Our methods work for approximately sparse distributions and medium privacy, and have optimal sample and communication complexity.

preprint2022arXiv

One-Bit Matrix Completion with Differential Privacy

As a prevailing collaborative filtering method for recommendation systems, one-bit matrix completion requires data collected by users to provide personalized service. Due to insidious attacks and unexpected inference, the release of users' data often raises serious privacy concerns. To address this issue, differential privacy(DP) has been widely used in standard matrix completion models. To date, however, little has been known about how to apply DP to achieve privacy protection in one-bit matrix completion. In this paper, we propose a unified framework for ensuring a strong privacy guarantee of one-bit matrix completion with DP. In our framework, we develop four different private perturbation mechanisms corresponding to different stages of one-bit matrix completion. For each mechanism, we design a privacy-preserving algorithm and provide a theoretical recovery error bound under the proper conditions. Numerical experiments on synthetic and real-world datasets demonstrate the effectiveness of our proposal. Compared to the one-bit matrix completion without privacy protection, our proposed mechanisms can maintain high-level privacy protection with marginal loss of completion accuracy.

preprint2022arXiv

Optimal Clustering with Noisy Queries via Multi-Armed Bandit

Motivated by many applications, we study clustering with a faulty oracle. In this problem, there are $n$ items belonging to $k$ unknown clusters, and the algorithm is allowed to ask the oracle whether two items belong to the same cluster or not. However, the answer from the oracle is correct only with probability $\frac{1}{2}+\fracδ{2}$. The goal is to recover the hidden clusters with minimum number of noisy queries. Previous works have shown that the problem can be solved with $O(\frac{nk\log n}{δ^2} + \text{poly}(k,\frac{1}δ, \log n))$ queries, while $Ω(\frac{nk}{δ^2})$ queries is known to be necessary. So, for any values of $k$ and $δ$, there is still a non-trivial gap between upper and lower bounds. In this work, we obtain the first matching upper and lower bounds for a wide range of parameters. In particular, a new polynomial time algorithm with $O(\frac{n(k+\log n)}{δ^2} + \text{poly}(k,\frac{1}δ, \log n))$ queries is proposed. Moreover, we prove a new lower bound of $Ω(\frac{n\log n}{δ^2})$, which, combined with the existing $Ω(\frac{nk}{δ^2})$ bound, matches our upper bound up to an additive $\text{poly}(k,\frac{1}δ,\log n)$ term. To obtain the new results, our main ingredient is an interesting connection between our problem and multi-armed bandit, which might provide useful insights for other similar problems.

preprint2020arXiv

Ghost imaging based on Y-net: a dynamic coding and conjugate-decoding approach

Ghost imaging incorporating deep learning technology has recently attracted much attention in the optical imaging field. However, deterministic illumination and multiple exposure are still essential in most scenarios. Here we propose a ghost imaging scheme based on a novel conjugate-decoding deep learning framework (Y-net), which works well under both deterministic and indeterministic illumination. Benefited from the end-to-end characteristic of our network, the image of a sample can be achieved directly from a pair of correlated speckles collected by the detectors, and the sample is illuminated only once in the experiment. The spatial distribution of the speckles encoding the sample in the experiment can be completely different from that of the simulation speckles for training, as long as the statistical characteristics of the speckles remain unchanged. This approach is particularly important to high-resolution x-ray ghost imaging applications due to its potential for improving image quality and reducing radiation damage. And the idea of conjugate-decoding network may also be applied to other learning-based imaging

preprint2020arXiv

Personalized PageRank to a Target Node, Revisited

Personalized PageRank (PPR) is a widely used node proximity measure in graph mining and network analysis. Given a source node $s$ and a target node $t$, the PPR value $π(s,t)$ represents the probability that a random walk from $s$ terminates at $t$, and thus indicates the bidirectional importance between $s$ and $t$. The majority of the existing work focuses on the single-source queries, which asks for the PPR value of a given source node $s$ and every node $t \in V$. However, the single-source query only reflects the importance of each node $t$ with respect to $s$. In this paper, we consider the {\em single-target PPR query}, which measures the opposite direction of importance for PPR. Given a target node $t$, the single-target PPR query asks for the PPR value of every node $s\in V$ to a given target node $t$. We propose RBS, a novel algorithm that answers approximate single-target queries with optimal computational complexity. We show that RBS improves three concrete applications: heavy hitters PPR query, single-source SimRank computation, and scalable graph neural networks. We conduct experiments to demonstrate that RBS outperforms the state-of-the-art algorithms in terms of both efficiency and precision on real-world benchmark datasets.

preprint2020arXiv

Simple and Deep Graph Convolutional Networks

Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datasets. Despite their success, most of the current GCN models are shallow, due to the {\em over-smoothing} problem. In this paper, we study the problem of designing and analyzing deep graph convolutional networks. We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: {\em Initial residual} and {\em Identity mapping}. We provide theoretical and empirical evidence that the two techniques effectively relieves the problem of over-smoothing. Our experiments show that the deep GCNII model outperforms the state-of-the-art methods on various semi- and full-supervised tasks. Code is available at https://github.com/chennnM/GCNII .

preprint2016arXiv

Dynamic Graph Stream Algorithms in $o(n)$ Space

In this paper we study graph problems in dynamic streaming model, where the input is defined by a sequence of edge insertions and deletions. As many natural problems require $Ω(n)$ space, where $n$ is the number of vertices, existing works mainly focused on designing $\tilde{O}(n)$ space algorithms. Although sublinear in the number of edges for dense graphs, it could still be too large for many applications (e.g. $n$ is huge or the graph is sparse). In this work, we give single-pass algorithms beating this space barrier for two classes of problems. We present $o(n)$ space algorithms for estimating the number of connected components with additive error $\varepsilon n$ and $(1+\varepsilon)$-approximating the weight of minimum spanning tree, for any small constant $\varepsilon>0$. The latter improves previous $\tilde{O}(n)$ space algorithm given by Ahn et al. (SODA 2012) for connected graphs with bounded edge weights. We initiate the study of approximate graph property testing in the dynamic streaming model, where we want to distinguish graphs satisfying the property from graphs that are $\varepsilon$-far from having the property. We consider the problem of testing $k$-edge connectivity, $k$-vertex connectivity, cycle-freeness and bipartiteness (of planar graphs), for which, we provide algorithms using roughly $\tilde{O}(n^{1-\varepsilon})$ space, which is $o(n)$ for any constant $\varepsilon$. To complement our algorithms, we present $Ω(n^{1-O(\varepsilon)})$ space lower bounds for these problems, which show that such a dependence on $\varepsilon$ is necessary.

preprint2016arXiv

Top-k Spatial-keyword Publish/Subscribe Over Sliding Window

With the prevalence of social media and GPS-enabled devices, a massive amount of geo-textual data has been generated in a stream fashion, leading to a variety of applications such as location-based recommendation and information dissemination. In this paper, we investigate a novel real-time top-k monitoring problem over sliding window of streaming data; that is, we continuously maintain the top-k most relevant geo-textual messages (e.g., geo-tagged tweets) for a large number of spatial-keyword subscriptions (e.g., registered users interested in local events) simultaneously. To provide the most recent information under controllable memory cost, sliding window model is employed on the streaming geo-textual data. To the best of our knowledge, this is the first work to study top-k spatial-keyword publish/subscribe over sliding window. A novel centralized system, called Skype (Topk Spatial-keyword Publish/Subscribe), is proposed in this paper. In Skype, to continuously maintain top-k results for massive subscriptions, we devise a novel indexing structure upon subscriptions such that each incoming message can be immediately delivered on its arrival. To reduce the expensive top-k re-evaluation cost triggered by message expiration, we develop a novel cost-based k-skyband technique to reduce the number of re-evaluations in a cost-effective way. Extensive experiments verify the great efficiency and effectiveness of our proposed techniques. Furthermore, to support better scalability and higher throughput, we propose a distributed version of Skype, namely, DSkype, on top of Storm, which is a popular distributed stream processing system. With the help of fine-tuned subscription/message distribution mechanisms, DSkype can achieve orders of magnitude speed-up than its centralized version.

preprint2014arXiv

Tracking the Frequency Moments at All Times

The traditional requirement for a randomized streaming algorithm is just {\em one-shot}, i.e., algorithm should be correct (within the stated $\eps$-error bound) at the end of the stream. In this paper, we study the {\em tracking} problem, where the output should be correct at all times. The standard approach for solving the tracking problem is to run $O(\log m)$ independent instances of the one-shot algorithm and apply the union bound to all $m$ time instances. In this paper, we study if this standard approach can be improved, for the classical frequency moment problem. We show that for the $F_p$ problem for any $1 < p \le 2$, we actually only need $O(\log \log m + \log n)$ copies to achieve the tracking guarantee in the cash register model, where $n$ is the universe size. Meanwhile, we present a lower bound of $Ω(\log m \log\log m)$ bits for all linear sketches achieving this guarantee. This shows that our upper bound is tight when $n=(\log m)^{O(1)}$. We also present an $Ω(\log^2 m)$ lower bound in the turnstile model, showing that the standard approach by using the union bound is essentially optimal.

preprint2011arXiv

Randomized Algorithms for Tracking Distributed Count, Frequencies, and Ranks

We show that randomization can lead to significant improvements for a few fundamental problems in distributed tracking. Our basis is the {\em count-tracking} problem, where there are $k$ players, each holding a counter $n_i$ that gets incremented over time, and the goal is to track an $\eps$-approximation of their sum $n=\sum_i n_i$ continuously at all times, using minimum communication. While the deterministic communication complexity of the problem is $Θ(k/\eps \cdot \log N)$, where $N$ is the final value of $n$ when the tracking finishes, we show that with randomization, the communication cost can be reduced to $Θ(\sqrt{k}/\eps \cdot \log N)$. Our algorithm is simple and uses only O(1) space at each player, while the lower bound holds even assuming each player has infinite computing power. Then, we extend our techniques to two related distributed tracking problems: {\em frequency-tracking} and {\em rank-tracking}, and obtain similar improvements over previous deterministic algorithms. Both problems are of central importance in large data monitoring and analysis, and have been extensively studied in the literature.

Zengfeng Huang

What is connected

Connect this record

See the researcher in context

Building this map preview

14 published item(s)

DiRL: An Efficient Post-Training Framework for Diffusion Language Models

Re$^2$Math: Benchmarking Theorem Retrieval in Research-Level Mathematics

BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation

BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction

Compressive Sensing Approaches for Sparse Distribution Estimation Under Local Privacy

One-Bit Matrix Completion with Differential Privacy

Optimal Clustering with Noisy Queries via Multi-Armed Bandit

Ghost imaging based on Y-net: a dynamic coding and conjugate-decoding approach

Personalized PageRank to a Target Node, Revisited

Simple and Deep Graph Convolutional Networks

Dynamic Graph Stream Algorithms in $o(n)$ Space

Top-k Spatial-keyword Publish/Subscribe Over Sliding Window

Tracking the Frequency Moments at All Times

Randomized Algorithms for Tracking Distributed Count, Frequencies, and Ranks